da1ch812/advanced-comp-model
Text Generation
•
4B
•
Updated
•
68
Datasets:
messages
listlengths 10
50
| metadata
dict |
|---|---|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a countertop 1, a cabinet 1, a fridge 1, a microwave 1, a sinkbasin 1, a stoveburner 1, a stoveburner 2, a drawer 1, a drawer 2, a shelf 1, a shelf 2, a garbagecan 1, a toaster 1, a coffeemachine 1.\n\nYour task is to: put a apple in/on sinkbasin 1."
},
{
"role": "assistant",
"content": "Think: I should look for apple. Let me start with microwave 1.\nAct: go to microwave 1"
},
{
"role": "user",
"content": "The microwave 1 is open. In it, you see a mug 1."
},
{
"role": "assistant",
"content": "Think: apple is not here. Let me check cabinet 1.\nAct: go to cabinet 1"
},
{
"role": "user",
"content": "The cabinet 1 is closed."
},
{
"role": "assistant",
"content": "Think: I should open the cabinet 1 to check its contents.\nAct: open cabinet 1"
},
{
"role": "user",
"content": "You open the cabinet 1. The cabinet 1 is open. In it, you see a apple 1."
},
{
"role": "assistant",
"content": "Think: I found apple 1 on cabinet 1. I should pick it up.\nAct: take apple 1 from cabinet 1"
},
{
"role": "user",
"content": "You pick up the apple 1 from the cabinet 1."
},
{
"role": "assistant",
"content": "Think: Now I'll go to sinkbasin 1 to put apple 1 down.\nAct: go to sinkbasin 1"
},
{
"role": "user",
"content": "The sinkbasin 1 is clean."
},
{
"role": "assistant",
"content": "Think: Let me place apple 1 here.\nAct: put apple 1 in/on sinkbasin 1"
},
{
"role": "user",
"content": "You put the apple 1 in/on the sinkbasin 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a apple in/on sinkbasin 1.",
"room_type": "kitchen",
"difficulty": "normal",
"num_steps": 13
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a countertop 1, a countertop 2, a cabinet 1, a fridge 1, a microwave 1, a sinkbasin 1, a stoveburner 1, a drawer 1, a drawer 2, a drawer 3, a drawer 4, a drawer 5, a drawer 6, a shelf 1, a shelf 2, a shelf 3, a shelf 4, a garbagecan 1, a toaster 1, a coffeemachine 1.\n\nYour task is to: put a apple in/on cabinet 1."
},
{
"role": "assistant",
"content": "Think: apple might be at stoveburner 1. Let me go there.\nAct: go to stoveburner 1"
},
{
"role": "user",
"content": "On the stoveburner 1, you see a plate 2 and a apple 1."
},
{
"role": "assistant",
"content": "Think: I found apple 1 on stoveburner 1. I should pick it up.\nAct: take apple 1 from stoveburner 1"
},
{
"role": "user",
"content": "You pick up the apple 1 from the stoveburner 1."
},
{
"role": "assistant",
"content": "Think: Now I'll go to cabinet 1 to put apple 1 down.\nAct: go to cabinet 1"
},
{
"role": "user",
"content": "The cabinet 1 is closed."
},
{
"role": "assistant",
"content": "Think: The cabinet 1 is closed. I need to open it first.\nAct: open cabinet 1"
},
{
"role": "user",
"content": "You open the cabinet 1. The cabinet 1 is open. In it, you see a mug 1, a pan 2, and a bowl 1."
},
{
"role": "assistant",
"content": "Think: Now I'll set apple 1 down in/on cabinet 1.\nAct: put apple 1 in/on cabinet 1"
},
{
"role": "user",
"content": "You put the apple 1 in/on the cabinet 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a apple in/on cabinet 1.",
"room_type": "kitchen",
"difficulty": "easy",
"num_steps": 11
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a sofa 1, a coffeetable 1, a sidetable 1, a shelf 1, a shelf 2, a shelf 3, a shelf 4, a shelf 5, a shelf 6, a drawer 1, a drawer 2, a drawer 3, a dresser 1, a armchair 1, a desk 1, a garbagecan 1, a safe 1.\n\nYour task is to: put a keychain in/on desk 1."
},
{
"role": "assistant",
"content": "Think: I should look for keychain. Let me start with shelf 3.\nAct: go to shelf 3"
},
{
"role": "user",
"content": "On the shelf 3, you see a statue 2."
},
{
"role": "assistant",
"content": "Think: No luck. Let me look at shelf 6.\nAct: go to shelf 6"
},
{
"role": "user",
"content": "On the shelf 6, you see a tissuebox 1 and a keychain 1."
},
{
"role": "assistant",
"content": "Think: I can see keychain 1 on shelf 6. I'll grab it.\nAct: take keychain 1 from shelf 6"
},
{
"role": "user",
"content": "You pick up the keychain 1 from the shelf 6."
},
{
"role": "assistant",
"content": "Think: I should bring keychain 1 to desk 1 and place it there.\nAct: go to desk 1"
},
{
"role": "user",
"content": "On the desk 1, you see nothing."
},
{
"role": "assistant",
"content": "Think: I'll put keychain 1 in/on desk 1 now.\nAct: put keychain 1 in/on desk 1"
},
{
"role": "user",
"content": "You put the keychain 1 in/on the desk 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a keychain in/on desk 1.",
"room_type": "livingroom",
"difficulty": "normal",
"num_steps": 11
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a sinkbasin 1, a toilet 1, a bathtubbasin 1, a cabinet 1, a cabinet 2, a cabinet 3, a cabinet 4, a countertop 1, a countertop 2, a shelf 1, a shelf 2, a shelf 3, a shelf 4, a shelf 5, a towelholder 1, a garbagecan 1, a drawer 1, a drawer 2, a drawer 3, a drawer 4.\n\nYour task is to: put a soapbottle in/on toilet 1."
},
{
"role": "assistant",
"content": "Think: To complete this task, I need soapbottle. I'll search shelf 3.\nAct: go to shelf 3"
},
{
"role": "user",
"content": "On the shelf 3, you see a towel 2 and a soapbottle 1."
},
{
"role": "assistant",
"content": "Think: soapbottle wasn't there. Let me try garbagecan 1.\nAct: go to garbagecan 1"
},
{
"role": "user",
"content": "On the garbagecan 1, you see a soapbottle 2."
},
{
"role": "assistant",
"content": "Think: I can see soapbottle 2 on garbagecan 1. I'll grab it.\nAct: take soapbottle 2 from garbagecan 1"
},
{
"role": "user",
"content": "You pick up the soapbottle 2 from the garbagecan 1."
},
{
"role": "assistant",
"content": "Think: Now I need to place soapbottle 2 in/on toilet 1. Let me go there.\nAct: go to toilet 1"
},
{
"role": "user",
"content": "The toilet 1 is clean."
},
{
"role": "assistant",
"content": "Think: Now I'll set soapbottle 2 down in/on toilet 1.\nAct: put soapbottle 2 in/on toilet 1"
},
{
"role": "user",
"content": "You put the soapbottle 2 in/on the toilet 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a soapbottle in/on toilet 1.",
"room_type": "bathroom",
"difficulty": "normal",
"num_steps": 11
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a sofa 1, a coffeetable 1, a sidetable 1, a shelf 1, a shelf 2, a shelf 3, a shelf 4, a shelf 5, a drawer 1, a drawer 2, a dresser 1, a armchair 1, a desk 1, a garbagecan 1, a safe 1.\n\nYour task is to: put a box in/on armchair 1."
},
{
"role": "assistant",
"content": "Think: I should look for box. Let me start with dresser 1.\nAct: go to dresser 1"
},
{
"role": "user",
"content": "On the dresser 1, you see nothing."
},
{
"role": "assistant",
"content": "Think: Not here. Moving on to shelf 2.\nAct: go to shelf 2"
},
{
"role": "user",
"content": "On the shelf 2, you see nothing."
},
{
"role": "assistant",
"content": "Think: I don't see box here. I'll try desk 1 next.\nAct: go to desk 1"
},
{
"role": "user",
"content": "On the desk 1, you see nothing."
},
{
"role": "assistant",
"content": "Think: No luck. Let me look at sidetable 1.\nAct: go to sidetable 1"
},
{
"role": "user",
"content": "The sidetable 1 appears to be empty."
},
{
"role": "assistant",
"content": "Think: No luck. Let me look at sofa 1.\nAct: go to sofa 1"
},
{
"role": "user",
"content": "On the sofa 1, you see a keychain 3."
},
{
"role": "assistant",
"content": "Think: I didn't find box. coffeetable 1 might have it.\nAct: go to coffeetable 1"
},
{
"role": "user",
"content": "On the coffeetable 1, you see a laptop 1 and a box 1."
},
{
"role": "assistant",
"content": "Think: I can see box 1 on coffeetable 1. I'll grab it.\nAct: take box 1 from coffeetable 1"
},
{
"role": "user",
"content": "You pick up the box 1 from the coffeetable 1."
},
{
"role": "assistant",
"content": "Think: Time to put box 1 in/on armchair 1.\nAct: go to armchair 1"
},
{
"role": "user",
"content": "On the armchair 1, you see a watch 1 and a book 2."
},
{
"role": "assistant",
"content": "Think: Let me place box 1 here.\nAct: put box 1 in/on armchair 1"
},
{
"role": "user",
"content": "You put the box 1 in/on the armchair 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a box in/on armchair 1.",
"room_type": "livingroom",
"difficulty": "hard",
"num_steps": 19
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a sinkbasin 1, a toilet 1, a bathtubbasin 1, a cabinet 1, a countertop 1, a countertop 2, a shelf 1, a towelholder 1, a garbagecan 1, a drawer 1, a drawer 2, a drawer 3, a drawer 4, a drawer 5.\n\nYour task is to: put a toiletpaper in/on countertop 1."
},
{
"role": "assistant",
"content": "Think: I should look for toiletpaper. Let me start with drawer 3.\nAct: go to drawer 3"
},
{
"role": "user",
"content": "The drawer 3 is closed."
},
{
"role": "assistant",
"content": "Think: The drawer 3 is closed. I need to open it first.\nAct: open drawer 3"
},
{
"role": "user",
"content": "You open the drawer 3. The drawer 3 is open. In it, you see a plunger 4."
},
{
"role": "assistant",
"content": "Think: I don't see toiletpaper here. I'll try bathtubbasin 1 next.\nAct: go to bathtubbasin 1"
},
{
"role": "user",
"content": "The bathtubbasin 1 is clean."
},
{
"role": "assistant",
"content": "Think: No luck. Let me look at drawer 1.\nAct: go to drawer 1"
},
{
"role": "user",
"content": "The drawer 1 appears to be empty."
},
{
"role": "assistant",
"content": "Think: Not here. Moving on to cabinet 1.\nAct: go to cabinet 1"
},
{
"role": "user",
"content": "The cabinet 1 is closed."
},
{
"role": "assistant",
"content": "Think: I should open the cabinet 1 to check its contents.\nAct: open cabinet 1"
},
{
"role": "user",
"content": "You open the cabinet 1. The cabinet 1 is open. In it, you see a plunger 1, a soapbottle 3, and a toiletpaper 2."
},
{
"role": "assistant",
"content": "Think: There's toiletpaper 2 here. Let me take it.\nAct: take toiletpaper 2 from cabinet 1"
},
{
"role": "user",
"content": "You pick up the toiletpaper 2 from the cabinet 1."
},
{
"role": "assistant",
"content": "Think: I should bring toiletpaper 2 to countertop 1 and place it there.\nAct: go to countertop 1"
},
{
"role": "user",
"content": "On the countertop 1, you see nothing."
},
{
"role": "assistant",
"content": "Think: I'll put toiletpaper 2 in/on countertop 1 now.\nAct: put toiletpaper 2 in/on countertop 1"
},
{
"role": "user",
"content": "You put the toiletpaper 2 in/on the countertop 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a toiletpaper in/on countertop 1.",
"room_type": "bathroom",
"difficulty": "normal",
"num_steps": 19
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a countertop 1, a cabinet 1, a cabinet 2, a cabinet 3, a fridge 1, a microwave 1, a sinkbasin 1, a stoveburner 1, a stoveburner 2, a drawer 1, a drawer 2, a shelf 1, a garbagecan 1, a toaster 1, a coffeemachine 1.\n\nYour task is to: put a pot in/on drawer 1."
},
{
"role": "assistant",
"content": "Think: To complete this task, I need pot. I'll search fridge 1.\nAct: go to fridge 1"
},
{
"role": "user",
"content": "The fridge 1 is closed."
},
{
"role": "assistant",
"content": "Think: The fridge 1 is closed. I need to open it first.\nAct: open fridge 1"
},
{
"role": "user",
"content": "You open the fridge 1. The fridge 1 is open. In it, you see a knife 3, a spoon 1, and a mug 1."
},
{
"role": "assistant",
"content": "Think: I didn't find pot. drawer 2 might have it.\nAct: go to drawer 2"
},
{
"role": "user",
"content": "The drawer 2 is open. In it, you see a dishsponge 1."
},
{
"role": "assistant",
"content": "Think: No luck. Let me look at garbagecan 1.\nAct: go to garbagecan 1"
},
{
"role": "user",
"content": "The garbagecan 1 appears to be empty."
},
{
"role": "assistant",
"content": "Think: I didn't find pot. countertop 1 might have it.\nAct: go to countertop 1"
},
{
"role": "user",
"content": "On the countertop 1, you see a knife 2, a mug 2, a dishsponge 2, and a pot 1."
},
{
"role": "assistant",
"content": "Think: Found it! pot 1 is on countertop 1. Let me pick it up.\nAct: take pot 1 from countertop 1"
},
{
"role": "user",
"content": "You pick up the pot 1 from the countertop 1."
},
{
"role": "assistant",
"content": "Think: Time to put pot 1 in/on drawer 1.\nAct: go to drawer 1"
},
{
"role": "user",
"content": "The drawer 1 is open. In it, you see a potato 2."
},
{
"role": "assistant",
"content": "Think: Let me place pot 1 here.\nAct: put pot 1 in/on drawer 1"
},
{
"role": "user",
"content": "You put the pot 1 in/on the drawer 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a pot in/on drawer 1.",
"room_type": "kitchen",
"difficulty": "hard",
"num_steps": 17
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a bed 1, a desk 1, a drawer 1, a shelf 1, a shelf 2, a sidetable 1, a dresser 1, a safe 1, a garbagecan 1, a laundryhamper 1.\n\nYour task is to: put a creditcard in/on laundryhamper 1."
},
{
"role": "assistant",
"content": "Think: I should look for creditcard. Let me start with laundryhamper 1.\nAct: go to laundryhamper 1"
},
{
"role": "user",
"content": "On the laundryhamper 1, you see a creditcard 1 and a pen 1."
},
{
"role": "assistant",
"content": "Think: Found it! creditcard 1 is on laundryhamper 1. Let me pick it up.\nAct: take creditcard 1 from laundryhamper 1"
},
{
"role": "user",
"content": "You pick up the creditcard 1 from the laundryhamper 1."
},
{
"role": "assistant",
"content": "Think: Now I'll go to laundryhamper 1 to put creditcard 1 down.\nAct: go to laundryhamper 1"
},
{
"role": "user",
"content": "On the laundryhamper 1, you see a pen 1."
},
{
"role": "assistant",
"content": "Think: Let me place creditcard 1 here.\nAct: put creditcard 1 in/on laundryhamper 1"
},
{
"role": "user",
"content": "You put the creditcard 1 in/on the laundryhamper 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a creditcard in/on laundryhamper 1.",
"room_type": "bedroom",
"difficulty": "easy",
"num_steps": 9
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a sinkbasin 1, a toilet 1, a bathtubbasin 1, a cabinet 1, a cabinet 2, a cabinet 3, a cabinet 4, a cabinet 5, a countertop 1, a shelf 1, a shelf 2, a shelf 3, a shelf 4, a shelf 5, a towelholder 1, a garbagecan 1, a drawer 1, a drawer 2, a drawer 3.\n\nYour task is to: put a toiletpaper in/on bathtubbasin 1."
},
{
"role": "assistant",
"content": "Think: I need to find toiletpaper. Let me check toilet 1.\nAct: go to toilet 1"
},
{
"role": "user",
"content": "On the toilet 1, you see a candle 3."
},
{
"role": "assistant",
"content": "Think: I don't see toiletpaper here. I'll try drawer 1 next.\nAct: go to drawer 1"
},
{
"role": "user",
"content": "The drawer 1 is closed."
},
{
"role": "assistant",
"content": "Think: I should open the drawer 1 to check its contents.\nAct: open drawer 1"
},
{
"role": "user",
"content": "You open the drawer 1. The drawer 1 is open. In it, you see a spraybottle 3 and a toiletpaper 1."
},
{
"role": "assistant",
"content": "Think: There's toiletpaper 1 here. Let me take it.\nAct: take toiletpaper 1 from drawer 1"
},
{
"role": "user",
"content": "You pick up the toiletpaper 1 from the drawer 1."
},
{
"role": "assistant",
"content": "Think: Final step: put toiletpaper 1 in/on bathtubbasin 1.\nAct: go to bathtubbasin 1"
},
{
"role": "user",
"content": "On the bathtubbasin 1, you see a soapbar 1."
},
{
"role": "assistant",
"content": "Think: Now I'll set toiletpaper 1 down in/on bathtubbasin 1.\nAct: put toiletpaper 1 in/on bathtubbasin 1"
},
{
"role": "user",
"content": "You put the toiletpaper 1 in/on the bathtubbasin 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a toiletpaper in/on bathtubbasin 1.",
"room_type": "bathroom",
"difficulty": "normal",
"num_steps": 13
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a countertop 1, a countertop 2, a cabinet 1, a cabinet 2, a cabinet 3, a cabinet 4, a cabinet 5, a fridge 1, a microwave 1, a sinkbasin 1, a stoveburner 1, a drawer 1, a drawer 2, a drawer 3, a drawer 4, a shelf 1, a shelf 2, a garbagecan 1, a toaster 1, a coffeemachine 1.\n\nYour task is to: put a knife in/on drawer 1."
},
{
"role": "assistant",
"content": "Think: knife might be at garbagecan 1. Let me go there.\nAct: go to garbagecan 1"
},
{
"role": "user",
"content": "On the garbagecan 1, you see a knife 1."
},
{
"role": "assistant",
"content": "Think: I can see knife 1 on garbagecan 1. I'll grab it.\nAct: take knife 1 from garbagecan 1"
},
{
"role": "user",
"content": "You pick up the knife 1 from the garbagecan 1."
},
{
"role": "assistant",
"content": "Think: Now I'll go to drawer 1 to put knife 1 down.\nAct: go to drawer 1"
},
{
"role": "user",
"content": "The drawer 1 is open. In it, you see a spoon 1."
},
{
"role": "assistant",
"content": "Think: I'll put knife 1 in/on drawer 1 now.\nAct: put knife 1 in/on drawer 1"
},
{
"role": "user",
"content": "You put the knife 1 in/on the drawer 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a knife in/on drawer 1.",
"room_type": "kitchen",
"difficulty": "easy",
"num_steps": 9
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a countertop 1, a countertop 2, a cabinet 1, a fridge 1, a microwave 1, a sinkbasin 1, a stoveburner 1, a drawer 1, a drawer 2, a drawer 3, a shelf 1, a shelf 2, a garbagecan 1, a toaster 1, a coffeemachine 1.\n\nYour task is to: put a dishsponge in/on sinkbasin 1."
},
{
"role": "assistant",
"content": "Think: My goal requires dishsponge. Let me try microwave 1.\nAct: go to microwave 1"
},
{
"role": "user",
"content": "The microwave 1 is closed."
},
{
"role": "assistant",
"content": "Think: The microwave 1 is closed. I need to open it first.\nAct: open microwave 1"
},
{
"role": "user",
"content": "You open the microwave 1. The microwave 1 is open. In it, you see nothing."
},
{
"role": "assistant",
"content": "Think: No luck. Let me look at shelf 1.\nAct: go to shelf 1"
},
{
"role": "user",
"content": "On the shelf 1, you see a dishsponge 1, a pot 2, and a pan 2."
},
{
"role": "assistant",
"content": "Think: I found dishsponge 1 on shelf 1. I should pick it up.\nAct: take dishsponge 1 from shelf 1"
},
{
"role": "user",
"content": "You pick up the dishsponge 1 from the shelf 1."
},
{
"role": "assistant",
"content": "Think: I should bring dishsponge 1 to sinkbasin 1 and place it there.\nAct: go to sinkbasin 1"
},
{
"role": "user",
"content": "On the sinkbasin 1, you see a mug 1."
},
{
"role": "assistant",
"content": "Think: Now I'll set dishsponge 1 down in/on sinkbasin 1.\nAct: put dishsponge 1 in/on sinkbasin 1"
},
{
"role": "user",
"content": "You put the dishsponge 1 in/on the sinkbasin 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a dishsponge in/on sinkbasin 1.",
"room_type": "kitchen",
"difficulty": "normal",
"num_steps": 13
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a bed 1, a desk 1, a drawer 1, a drawer 2, a drawer 3, a drawer 4, a shelf 1, a shelf 2, a shelf 3, a sidetable 1, a sidetable 2, a dresser 1, a safe 1, a garbagecan 1, a laundryhamper 1.\n\nYour task is to: put a alarmclock in/on sidetable 1."
},
{
"role": "assistant",
"content": "Think: First, I should locate alarmclock. drawer 4 seems like a good place to look.\nAct: go to drawer 4"
},
{
"role": "user",
"content": "On the drawer 4, you see nothing."
},
{
"role": "assistant",
"content": "Think: alarmclock wasn't there. Let me try garbagecan 1.\nAct: go to garbagecan 1"
},
{
"role": "user",
"content": "On the garbagecan 1, you see a alarmclock 1."
},
{
"role": "assistant",
"content": "Think: I can see alarmclock 1 on garbagecan 1. I'll grab it.\nAct: take alarmclock 1 from garbagecan 1"
},
{
"role": "user",
"content": "You pick up the alarmclock 1 from the garbagecan 1."
},
{
"role": "assistant",
"content": "Think: Final step: put alarmclock 1 in/on sidetable 1.\nAct: go to sidetable 1"
},
{
"role": "user",
"content": "On the sidetable 1, you see a cellphone 1."
},
{
"role": "assistant",
"content": "Think: I'll put alarmclock 1 in/on sidetable 1 now.\nAct: put alarmclock 1 in/on sidetable 1"
},
{
"role": "user",
"content": "You put the alarmclock 1 in/on the sidetable 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a alarmclock in/on sidetable 1.",
"room_type": "bedroom",
"difficulty": "normal",
"num_steps": 11
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a countertop 1, a countertop 2, a cabinet 1, a cabinet 2, a cabinet 3, a cabinet 4, a fridge 1, a microwave 1, a sinkbasin 1, a stoveburner 1, a stoveburner 2, a drawer 1, a drawer 2, a shelf 1, a shelf 2, a garbagecan 1, a toaster 1, a coffeemachine 1.\n\nYour task is to: put a plate in/on sinkbasin 1."
},
{
"role": "assistant",
"content": "Think: First, I should locate plate. microwave 1 seems like a good place to look.\nAct: go to microwave 1"
},
{
"role": "user",
"content": "The microwave 1 is closed."
},
{
"role": "assistant",
"content": "Think: I should open the microwave 1 to check its contents.\nAct: open microwave 1"
},
{
"role": "user",
"content": "You open the microwave 1. The microwave 1 is open. In it, you see a dishsponge 1, a bowl 1, a saltshaker 2, and a plate 1."
},
{
"role": "assistant",
"content": "Think: I found plate 1 on microwave 1. I should pick it up.\nAct: take plate 1 from microwave 1"
},
{
"role": "user",
"content": "You pick up the plate 1 from the microwave 1."
},
{
"role": "assistant",
"content": "Think: Now I need to place plate 1 in/on sinkbasin 1. Let me go there.\nAct: go to sinkbasin 1"
},
{
"role": "user",
"content": "On the sinkbasin 1, you see a saltshaker 1."
},
{
"role": "assistant",
"content": "Think: Now I'll set plate 1 down in/on sinkbasin 1.\nAct: put plate 1 in/on sinkbasin 1"
},
{
"role": "user",
"content": "You put the plate 1 in/on the sinkbasin 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a plate in/on sinkbasin 1.",
"room_type": "kitchen",
"difficulty": "easy",
"num_steps": 11
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a sofa 1, a coffeetable 1, a sidetable 1, a shelf 1, a shelf 2, a shelf 3, a drawer 1, a drawer 2, a drawer 3, a dresser 1, a armchair 1, a desk 1, a garbagecan 1, a safe 1.\n\nYour task is to: put a book in/on garbagecan 1."
},
{
"role": "assistant",
"content": "Think: First, I should locate book. garbagecan 1 seems like a good place to look.\nAct: go to garbagecan 1"
},
{
"role": "user",
"content": "On the garbagecan 1, you see a pen 1 and a book 1."
},
{
"role": "assistant",
"content": "Think: Found it! book 1 is on garbagecan 1. Let me pick it up.\nAct: take book 1 from garbagecan 1"
},
{
"role": "user",
"content": "You pick up the book 1 from the garbagecan 1."
},
{
"role": "assistant",
"content": "Think: Now I'll go to garbagecan 1 to put book 1 down.\nAct: go to garbagecan 1"
},
{
"role": "user",
"content": "On the garbagecan 1, you see a pen 1."
},
{
"role": "assistant",
"content": "Think: I'll put book 1 in/on garbagecan 1 now.\nAct: put book 1 in/on garbagecan 1"
},
{
"role": "user",
"content": "You put the book 1 in/on the garbagecan 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a book in/on garbagecan 1.",
"room_type": "livingroom",
"difficulty": "easy",
"num_steps": 9
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a sinkbasin 1, a toilet 1, a bathtubbasin 1, a cabinet 1, a cabinet 2, a cabinet 3, a cabinet 4, a countertop 1, a shelf 1, a shelf 2, a shelf 3, a shelf 4, a shelf 5, a towelholder 1, a garbagecan 1, a drawer 1, a drawer 2, a drawer 3, a drawer 4, a drawer 5.\n\nYour task is to: put a candle in/on towelholder 1."
},
{
"role": "assistant",
"content": "Think: I should look for candle. Let me start with countertop 1.\nAct: go to countertop 1"
},
{
"role": "user",
"content": "On the countertop 1, you see a cloth 2 and a soapbar 1."
},
{
"role": "assistant",
"content": "Think: I didn't find candle. shelf 3 might have it.\nAct: go to shelf 3"
},
{
"role": "user",
"content": "On the shelf 3, you see a tissuebox 1."
},
{
"role": "assistant",
"content": "Think: Not here. Moving on to towelholder 1.\nAct: go to towelholder 1"
},
{
"role": "user",
"content": "On the towelholder 1, you see a spraybottle 1."
},
{
"role": "assistant",
"content": "Think: No luck. Let me look at toilet 1.\nAct: go to toilet 1"
},
{
"role": "user",
"content": "On the toilet 1, you see a candle 1 and a soapbottle 1."
},
{
"role": "assistant",
"content": "Think: Found it! candle 1 is on toilet 1. Let me pick it up.\nAct: take candle 1 from toilet 1"
},
{
"role": "user",
"content": "You pick up the candle 1 from the toilet 1."
},
{
"role": "assistant",
"content": "Think: Now I need to place candle 1 in/on towelholder 1. Let me go there.\nAct: go to towelholder 1"
},
{
"role": "user",
"content": "On the towelholder 1, you see a spraybottle 1."
},
{
"role": "assistant",
"content": "Think: I'll put candle 1 in/on towelholder 1 now.\nAct: put candle 1 in/on towelholder 1"
},
{
"role": "user",
"content": "You put the candle 1 in/on the towelholder 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a candle in/on towelholder 1.",
"room_type": "bathroom",
"difficulty": "normal",
"num_steps": 15
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a bed 1, a desk 1, a drawer 1, a drawer 2, a shelf 1, a shelf 2, a sidetable 1, a sidetable 2, a dresser 1, a safe 1, a garbagecan 1, a laundryhamper 1.\n\nYour task is to: put a pencil in/on dresser 1."
},
{
"role": "assistant",
"content": "Think: I should look for pencil. Let me start with shelf 1.\nAct: go to shelf 1"
},
{
"role": "user",
"content": "On the shelf 1, you see a book 1."
},
{
"role": "assistant",
"content": "Think: I didn't find pencil. desk 1 might have it.\nAct: go to desk 1"
},
{
"role": "user",
"content": "On the desk 1, you see a laptop 1, a keychain 1, a creditcard 1, and a box 1."
},
{
"role": "assistant",
"content": "Think: pencil is not here. Let me check drawer 1.\nAct: go to drawer 1"
},
{
"role": "user",
"content": "The drawer 1 is open. In it, you see a alarmclock 1."
},
{
"role": "assistant",
"content": "Think: I don't see pencil here. I'll try bed 1 next.\nAct: go to bed 1"
},
{
"role": "user",
"content": "On the bed 1, you see a desklamp 1 and a pencil 1."
},
{
"role": "assistant",
"content": "Think: I found pencil 1 on bed 1. I should pick it up.\nAct: take pencil 1 from bed 1"
},
{
"role": "user",
"content": "You pick up the pencil 1 from the bed 1."
},
{
"role": "assistant",
"content": "Think: Now I need to place pencil 1 in/on dresser 1. Let me go there.\nAct: go to dresser 1"
},
{
"role": "user",
"content": "The dresser 1 appears to be empty."
},
{
"role": "assistant",
"content": "Think: I'll put pencil 1 in/on dresser 1 now.\nAct: put pencil 1 in/on dresser 1"
},
{
"role": "user",
"content": "You put the pencil 1 in/on the dresser 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a pencil in/on dresser 1.",
"room_type": "bedroom",
"difficulty": "normal",
"num_steps": 15
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a bed 1, a desk 1, a drawer 1, a drawer 2, a drawer 3, a drawer 4, a drawer 5, a shelf 1, a shelf 2, a shelf 3, a shelf 4, a shelf 5, a shelf 6, a sidetable 1, a sidetable 2, a dresser 1, a safe 1, a garbagecan 1, a laundryhamper 1.\n\nYour task is to: put a pillow in/on garbagecan 1."
},
{
"role": "assistant",
"content": "Think: My goal requires pillow. Let me try drawer 3.\nAct: go to drawer 3"
},
{
"role": "user",
"content": "The drawer 3 appears to be empty."
},
{
"role": "assistant",
"content": "Think: I don't see pillow here. I'll try safe 1 next.\nAct: go to safe 1"
},
{
"role": "user",
"content": "The safe 1 is closed."
},
{
"role": "assistant",
"content": "Think: The safe 1 is closed. I need to open it first.\nAct: open safe 1"
},
{
"role": "user",
"content": "You open the safe 1. The safe 1 is open. In it, you see a book 2."
},
{
"role": "assistant",
"content": "Think: pillow is not here. Let me check shelf 1.\nAct: go to shelf 1"
},
{
"role": "user",
"content": "The shelf 1 appears to be empty."
},
{
"role": "assistant",
"content": "Think: Not here. Moving on to sidetable 2.\nAct: go to sidetable 2"
},
{
"role": "user",
"content": "On the sidetable 2, you see a pillow 1 and a creditcard 2."
},
{
"role": "assistant",
"content": "Think: Found it! pillow 1 is on sidetable 2. Let me pick it up.\nAct: take pillow 1 from sidetable 2"
},
{
"role": "user",
"content": "You pick up the pillow 1 from the sidetable 2."
},
{
"role": "assistant",
"content": "Think: Final step: put pillow 1 in/on garbagecan 1.\nAct: go to garbagecan 1"
},
{
"role": "user",
"content": "On the garbagecan 1, you see a pillow 2 and a floorlamp 1."
},
{
"role": "assistant",
"content": "Think: Let me place pillow 1 here.\nAct: put pillow 1 in/on garbagecan 1"
},
{
"role": "user",
"content": "You put the pillow 1 in/on the garbagecan 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a pillow in/on garbagecan 1.",
"room_type": "bedroom",
"difficulty": "normal",
"num_steps": 17
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a countertop 1, a cabinet 1, a cabinet 2, a cabinet 3, a cabinet 4, a cabinet 5, a cabinet 6, a fridge 1, a microwave 1, a sinkbasin 1, a stoveburner 1, a stoveburner 2, a drawer 1, a drawer 2, a drawer 3, a drawer 4, a drawer 5, a drawer 6, a shelf 1, a shelf 2, a shelf 3, a shelf 4, a shelf 5, a shelf 6, a garbagecan 1, a toaster 1, a coffeemachine 1.\n\nYour task is to: put a saltshaker in/on coffeemachine 1."
},
{
"role": "assistant",
"content": "Think: I need to find saltshaker. Let me check garbagecan 1.\nAct: go to garbagecan 1"
},
{
"role": "user",
"content": "On the garbagecan 1, you see a dishsponge 1 and a soapbottle 1."
},
{
"role": "assistant",
"content": "Think: I don't see saltshaker here. I'll try stoveburner 2 next.\nAct: go to stoveburner 2"
},
{
"role": "user",
"content": "On the stoveburner 2, you see a cup 2."
},
{
"role": "assistant",
"content": "Think: I don't see saltshaker here. I'll try cabinet 3 next.\nAct: go to cabinet 3"
},
{
"role": "user",
"content": "The cabinet 3 is closed."
},
{
"role": "assistant",
"content": "Think: The cabinet 3 is closed. I need to open it first.\nAct: open cabinet 3"
},
{
"role": "user",
"content": "You open the cabinet 3. The cabinet 3 is open. In it, you see a cup 1, a pan 1, and a saltshaker 1."
},
{
"role": "assistant",
"content": "Think: Found it! saltshaker 1 is on cabinet 3. Let me pick it up.\nAct: take saltshaker 1 from cabinet 3"
},
{
"role": "user",
"content": "You pick up the saltshaker 1 from the cabinet 3."
},
{
"role": "assistant",
"content": "Think: Time to put saltshaker 1 in/on coffeemachine 1.\nAct: go to coffeemachine 1"
},
{
"role": "user",
"content": "The coffeemachine 1 appears to be empty."
},
{
"role": "assistant",
"content": "Think: I'll put saltshaker 1 in/on coffeemachine 1 now.\nAct: put saltshaker 1 in/on coffeemachine 1"
},
{
"role": "user",
"content": "You put the saltshaker 1 in/on the coffeemachine 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a saltshaker in/on coffeemachine 1.",
"room_type": "kitchen",
"difficulty": "normal",
"num_steps": 15
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a sinkbasin 1, a toilet 1, a bathtubbasin 1, a cabinet 1, a cabinet 2, a countertop 1, a countertop 2, a shelf 1, a towelholder 1, a garbagecan 1, a drawer 1, a drawer 2, a drawer 3, a drawer 4, a drawer 5, a drawer 6.\n\nYour task is to: put a tissuebox in/on cabinet 1."
},
{
"role": "assistant",
"content": "Think: I need to find tissuebox. Let me check drawer 4.\nAct: go to drawer 4"
},
{
"role": "user",
"content": "The drawer 4 is closed."
},
{
"role": "assistant",
"content": "Think: The drawer 4 is closed. I need to open it first.\nAct: open drawer 4"
},
{
"role": "user",
"content": "You open the drawer 4. The drawer 4 is open. In it, you see nothing."
},
{
"role": "assistant",
"content": "Think: I don't see tissuebox here. I'll try drawer 5 next.\nAct: go to drawer 5"
},
{
"role": "user",
"content": "On the drawer 5, you see nothing."
},
{
"role": "assistant",
"content": "Think: No luck. Let me look at towelholder 1.\nAct: go to towelholder 1"
},
{
"role": "user",
"content": "The towelholder 1 appears to be empty."
},
{
"role": "assistant",
"content": "Think: No luck. Let me look at toilet 1.\nAct: go to toilet 1"
},
{
"role": "user",
"content": "On the toilet 1, you see a towel 1 and a soapbottle 2."
},
{
"role": "assistant",
"content": "Think: I don't see tissuebox here. I'll try sinkbasin 1 next.\nAct: go to sinkbasin 1"
},
{
"role": "user",
"content": "The sinkbasin 1 is clean."
},
{
"role": "assistant",
"content": "Think: No luck. Let me look at drawer 6.\nAct: go to drawer 6"
},
{
"role": "user",
"content": "The drawer 6 is closed."
},
{
"role": "assistant",
"content": "Think: The drawer 6 is closed. I need to open it first.\nAct: open drawer 6"
},
{
"role": "user",
"content": "You open the drawer 6. The drawer 6 is open. In it, you see a tissuebox 1, a spraybottle 1, and a plunger 1."
},
{
"role": "assistant",
"content": "Think: I don't see tissuebox here. I'll try drawer 1 next.\nAct: go to drawer 1"
},
{
"role": "user",
"content": "The drawer 1 is open. In it, you see a tissuebox 2."
},
{
"role": "assistant",
"content": "Think: Found it! tissuebox 2 is on drawer 1. Let me pick it up.\nAct: take tissuebox 2 from drawer 1"
},
{
"role": "user",
"content": "You pick up the tissuebox 2 from the drawer 1."
},
{
"role": "assistant",
"content": "Think: Now I need to place tissuebox 2 in/on cabinet 1. Let me go there.\nAct: go to cabinet 1"
},
{
"role": "user",
"content": "The cabinet 1 is closed."
},
{
"role": "assistant",
"content": "Think: cabinet 1 is closed. Let me open it to see what's inside.\nAct: open cabinet 1"
},
{
"role": "user",
"content": "You open the cabinet 1. The cabinet 1 is open. In it, you see nothing."
},
{
"role": "assistant",
"content": "Think: Let me place tissuebox 2 here.\nAct: put tissuebox 2 in/on cabinet 1"
},
{
"role": "user",
"content": "You put the tissuebox 2 in/on the cabinet 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a tissuebox in/on cabinet 1.",
"room_type": "bathroom",
"difficulty": "hard",
"num_steps": 27
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a sofa 1, a coffeetable 1, a sidetable 1, a shelf 1, a shelf 2, a drawer 1, a drawer 2, a drawer 3, a drawer 4, a drawer 5, a dresser 1, a armchair 1, a desk 1, a garbagecan 1, a safe 1.\n\nYour task is to: put a pen in/on armchair 1."
},
{
"role": "assistant",
"content": "Think: First, I should locate pen. armchair 1 seems like a good place to look.\nAct: go to armchair 1"
},
{
"role": "user",
"content": "On the armchair 1, you see a laptop 2, a pen 1, and a pen 2."
},
{
"role": "assistant",
"content": "Think: There's pen 2 here. Let me take it.\nAct: take pen 2 from armchair 1"
},
{
"role": "user",
"content": "You pick up the pen 2 from the armchair 1."
},
{
"role": "assistant",
"content": "Think: I should bring pen 2 to armchair 1 and place it there.\nAct: go to armchair 1"
},
{
"role": "user",
"content": "On the armchair 1, you see a laptop 2 and a pen 1."
},
{
"role": "assistant",
"content": "Think: I'll put pen 2 in/on armchair 1 now.\nAct: put pen 2 in/on armchair 1"
},
{
"role": "user",
"content": "You put the pen 2 in/on the armchair 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a pen in/on armchair 1.",
"room_type": "livingroom",
"difficulty": "easy",
"num_steps": 9
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a countertop 1, a cabinet 1, a cabinet 2, a cabinet 3, a fridge 1, a microwave 1, a sinkbasin 1, a stoveburner 1, a drawer 1, a drawer 2, a drawer 3, a drawer 4, a shelf 1, a garbagecan 1, a toaster 1, a coffeemachine 1.\n\nYour task is to: put a soapbottle in/on garbagecan 1."
},
{
"role": "assistant",
"content": "Think: soapbottle might be at countertop 1. Let me go there.\nAct: go to countertop 1"
},
{
"role": "user",
"content": "On the countertop 1, you see a cup 1."
},
{
"role": "assistant",
"content": "Think: soapbottle wasn't there. Let me try drawer 3.\nAct: go to drawer 3"
},
{
"role": "user",
"content": "The drawer 3 is open. In it, you see a fork 1."
},
{
"role": "assistant",
"content": "Think: I don't see soapbottle here. I'll try drawer 1 next.\nAct: go to drawer 1"
},
{
"role": "user",
"content": "The drawer 1 is closed."
},
{
"role": "assistant",
"content": "Think: The drawer 1 is closed. I need to open it first.\nAct: open drawer 1"
},
{
"role": "user",
"content": "You open the drawer 1. The drawer 1 is open. In it, you see a knife 1 and a peppershaker 2."
},
{
"role": "assistant",
"content": "Think: soapbottle wasn't there. Let me try cabinet 1.\nAct: go to cabinet 1"
},
{
"role": "user",
"content": "The cabinet 1 is closed."
},
{
"role": "assistant",
"content": "Think: The cabinet 1 is closed. I need to open it first.\nAct: open cabinet 1"
},
{
"role": "user",
"content": "You open the cabinet 1. The cabinet 1 is open. In it, you see a peppershaker 1, a bowl 1, and a soapbottle 1."
},
{
"role": "assistant",
"content": "Think: There's soapbottle 1 here. Let me take it.\nAct: take soapbottle 1 from cabinet 1"
},
{
"role": "user",
"content": "You pick up the soapbottle 1 from the cabinet 1."
},
{
"role": "assistant",
"content": "Think: Now I need to place soapbottle 1 in/on garbagecan 1. Let me go there.\nAct: go to garbagecan 1"
},
{
"role": "user",
"content": "On the garbagecan 1, you see nothing."
},
{
"role": "assistant",
"content": "Think: Now I'll set soapbottle 1 down in/on garbagecan 1.\nAct: put soapbottle 1 in/on garbagecan 1"
},
{
"role": "user",
"content": "You put the soapbottle 1 in/on the garbagecan 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a soapbottle in/on garbagecan 1.",
"room_type": "kitchen",
"difficulty": "hard",
"num_steps": 19
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a bed 1, a desk 1, a drawer 1, a drawer 2, a drawer 3, a drawer 4, a drawer 5, a shelf 1, a shelf 2, a shelf 3, a shelf 4, a shelf 5, a shelf 6, a sidetable 1, a sidetable 2, a dresser 1, a safe 1, a garbagecan 1, a laundryhamper 1.\n\nYour task is to: put a tissuebox in/on desk 1."
},
{
"role": "assistant",
"content": "Think: I should look for tissuebox. Let me start with desk 1.\nAct: go to desk 1"
},
{
"role": "user",
"content": "On the desk 1, you see a floorlamp 1."
},
{
"role": "assistant",
"content": "Think: tissuebox wasn't there. Let me try drawer 1.\nAct: go to drawer 1"
},
{
"role": "user",
"content": "The drawer 1 appears to be empty."
},
{
"role": "assistant",
"content": "Think: Not here. Moving on to sidetable 1.\nAct: go to sidetable 1"
},
{
"role": "user",
"content": "On the sidetable 1, you see a statue 1."
},
{
"role": "assistant",
"content": "Think: I don't see tissuebox here. I'll try laundryhamper 1 next.\nAct: go to laundryhamper 1"
},
{
"role": "user",
"content": "On the laundryhamper 1, you see a tissuebox 1."
},
{
"role": "assistant",
"content": "Think: I can see tissuebox 1 on laundryhamper 1. I'll grab it.\nAct: take tissuebox 1 from laundryhamper 1"
},
{
"role": "user",
"content": "You pick up the tissuebox 1 from the laundryhamper 1."
},
{
"role": "assistant",
"content": "Think: Time to put tissuebox 1 in/on desk 1.\nAct: go to desk 1"
},
{
"role": "user",
"content": "On the desk 1, you see a floorlamp 1."
},
{
"role": "assistant",
"content": "Think: Let me place tissuebox 1 here.\nAct: put tissuebox 1 in/on desk 1"
},
{
"role": "user",
"content": "You put the tissuebox 1 in/on the desk 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a tissuebox in/on desk 1.",
"room_type": "bedroom",
"difficulty": "normal",
"num_steps": 15
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a sofa 1, a coffeetable 1, a sidetable 1, a shelf 1, a shelf 2, a shelf 3, a drawer 1, a drawer 2, a drawer 3, a drawer 4, a drawer 5, a dresser 1, a armchair 1, a desk 1, a garbagecan 1, a safe 1.\n\nYour task is to: put a statue in/on drawer 1."
},
{
"role": "assistant",
"content": "Think: I need to find statue. Let me check safe 1.\nAct: go to safe 1"
},
{
"role": "user",
"content": "The safe 1 is open. In it, you see a statue 1, a pillow 2, and a pen 3."
},
{
"role": "assistant",
"content": "Think: statue is not here. Let me check armchair 1.\nAct: go to armchair 1"
},
{
"role": "user",
"content": "On the armchair 1, you see a pencil 2."
},
{
"role": "assistant",
"content": "Think: No luck. Let me look at garbagecan 1.\nAct: go to garbagecan 1"
},
{
"role": "user",
"content": "On the garbagecan 1, you see a statue 3."
},
{
"role": "assistant",
"content": "Think: I found statue 3 on garbagecan 1. I should pick it up.\nAct: take statue 3 from garbagecan 1"
},
{
"role": "user",
"content": "You pick up the statue 3 from the garbagecan 1."
},
{
"role": "assistant",
"content": "Think: Now I need to place statue 3 in/on drawer 1. Let me go there.\nAct: go to drawer 1"
},
{
"role": "user",
"content": "The drawer 1 is closed."
},
{
"role": "assistant",
"content": "Think: I should open the drawer 1 to check its contents.\nAct: open drawer 1"
},
{
"role": "user",
"content": "You open the drawer 1. The drawer 1 is open. In it, you see a tissuebox 1."
},
{
"role": "assistant",
"content": "Think: I'll put statue 3 in/on drawer 1 now.\nAct: put statue 3 in/on drawer 1"
},
{
"role": "user",
"content": "You put the statue 3 in/on the drawer 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a statue in/on drawer 1.",
"room_type": "livingroom",
"difficulty": "normal",
"num_steps": 15
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a sinkbasin 1, a toilet 1, a bathtubbasin 1, a cabinet 1, a cabinet 2, a cabinet 3, a cabinet 4, a cabinet 5, a countertop 1, a countertop 2, a shelf 1, a shelf 2, a towelholder 1, a garbagecan 1, a drawer 1, a drawer 2, a drawer 3, a drawer 4.\n\nYour task is to: put a towel in/on shelf 1."
},
{
"role": "assistant",
"content": "Think: First, I should locate towel. bathtubbasin 1 seems like a good place to look.\nAct: go to bathtubbasin 1"
},
{
"role": "user",
"content": "On the bathtubbasin 1, you see a towel 3."
},
{
"role": "assistant",
"content": "Think: I can see towel 3 on bathtubbasin 1. I'll grab it.\nAct: take towel 3 from bathtubbasin 1"
},
{
"role": "user",
"content": "You pick up the towel 3 from the bathtubbasin 1."
},
{
"role": "assistant",
"content": "Think: I should bring towel 3 to shelf 1 and place it there.\nAct: go to shelf 1"
},
{
"role": "user",
"content": "On the shelf 1, you see a scrubbrush 1."
},
{
"role": "assistant",
"content": "Think: I'll put towel 3 in/on shelf 1 now.\nAct: put towel 3 in/on shelf 1"
},
{
"role": "user",
"content": "You put the towel 3 in/on the shelf 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a towel in/on shelf 1.",
"room_type": "bathroom",
"difficulty": "easy",
"num_steps": 9
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a sofa 1, a coffeetable 1, a sidetable 1, a sidetable 2, a shelf 1, a shelf 2, a shelf 3, a shelf 4, a shelf 5, a drawer 1, a drawer 2, a drawer 3, a drawer 4, a drawer 5, a drawer 6, a dresser 1, a armchair 1, a desk 1, a garbagecan 1, a safe 1.\n\nYour task is to: put a pen in/on safe 1."
},
{
"role": "assistant",
"content": "Think: I need to find pen. Let me check shelf 1.\nAct: go to shelf 1"
},
{
"role": "user",
"content": "On the shelf 1, you see a pillow 1."
},
{
"role": "assistant",
"content": "Think: I didn't find pen. shelf 2 might have it.\nAct: go to shelf 2"
},
{
"role": "user",
"content": "On the shelf 2, you see a laptop 1 and a vase 1."
},
{
"role": "assistant",
"content": "Think: pen wasn't there. Let me try drawer 1.\nAct: go to drawer 1"
},
{
"role": "user",
"content": "The drawer 1 is closed."
},
{
"role": "assistant",
"content": "Think: The drawer 1 is closed. I need to open it first.\nAct: open drawer 1"
},
{
"role": "user",
"content": "You open the drawer 1. The drawer 1 is open. In it, you see a newspaper 3."
},
{
"role": "assistant",
"content": "Think: Not here. Moving on to safe 1.\nAct: go to safe 1"
},
{
"role": "user",
"content": "The safe 1 is open. In it, you see a newspaper 1 and a tissuebox 1."
},
{
"role": "assistant",
"content": "Think: Not here. Moving on to dresser 1.\nAct: go to dresser 1"
},
{
"role": "user",
"content": "On the dresser 1, you see a keychain 2."
},
{
"role": "assistant",
"content": "Think: pen wasn't there. Let me try sofa 1.\nAct: go to sofa 1"
},
{
"role": "user",
"content": "On the sofa 1, you see a pen 2."
},
{
"role": "assistant",
"content": "Think: There's pen 2 here. Let me take it.\nAct: take pen 2 from sofa 1"
},
{
"role": "user",
"content": "You pick up the pen 2 from the sofa 1."
},
{
"role": "assistant",
"content": "Think: I should bring pen 2 to safe 1 and place it there.\nAct: go to safe 1"
},
{
"role": "user",
"content": "The safe 1 is open. In it, you see a newspaper 1 and a tissuebox 1."
},
{
"role": "assistant",
"content": "Think: I'll put pen 2 in/on safe 1 now.\nAct: put pen 2 in/on safe 1"
},
{
"role": "user",
"content": "You put the pen 2 in/on the safe 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a pen in/on safe 1.",
"room_type": "livingroom",
"difficulty": "hard",
"num_steps": 21
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a sinkbasin 1, a toilet 1, a bathtubbasin 1, a cabinet 1, a cabinet 2, a cabinet 3, a cabinet 4, a cabinet 5, a cabinet 6, a countertop 1, a shelf 1, a shelf 2, a shelf 3, a shelf 4, a towelholder 1, a garbagecan 1, a drawer 1, a drawer 2, a drawer 3.\n\nYour task is to: put a candle in/on garbagecan 1."
},
{
"role": "assistant",
"content": "Think: To complete this task, I need candle. I'll search towelholder 1.\nAct: go to towelholder 1"
},
{
"role": "user",
"content": "On the towelholder 1, you see nothing."
},
{
"role": "assistant",
"content": "Think: candle is not here. Let me check cabinet 6.\nAct: go to cabinet 6"
},
{
"role": "user",
"content": "The cabinet 6 is open. In it, you see a candle 1."
},
{
"role": "assistant",
"content": "Think: I can see candle 1 on cabinet 6. I'll grab it.\nAct: take candle 1 from cabinet 6"
},
{
"role": "user",
"content": "You pick up the candle 1 from the cabinet 6."
},
{
"role": "assistant",
"content": "Think: Time to put candle 1 in/on garbagecan 1.\nAct: go to garbagecan 1"
},
{
"role": "user",
"content": "On the garbagecan 1, you see a plunger 1 and a scrubbrush 2."
},
{
"role": "assistant",
"content": "Think: Now I'll set candle 1 down in/on garbagecan 1.\nAct: put candle 1 in/on garbagecan 1"
},
{
"role": "user",
"content": "You put the candle 1 in/on the garbagecan 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a candle in/on garbagecan 1.",
"room_type": "bathroom",
"difficulty": "normal",
"num_steps": 11
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a sinkbasin 1, a toilet 1, a bathtubbasin 1, a cabinet 1, a cabinet 2, a countertop 1, a shelf 1, a shelf 2, a shelf 3, a shelf 4, a shelf 5, a towelholder 1, a garbagecan 1, a drawer 1, a drawer 2, a drawer 3.\n\nYour task is to: put a towel in/on garbagecan 1."
},
{
"role": "assistant",
"content": "Think: I should look for towel. Let me start with shelf 3.\nAct: go to shelf 3"
},
{
"role": "user",
"content": "On the shelf 3, you see a candle 2, a towel 2, and a soapbar 2."
},
{
"role": "assistant",
"content": "Think: Found it! towel 2 is on shelf 3. Let me pick it up.\nAct: take towel 2 from shelf 3"
},
{
"role": "user",
"content": "You pick up the towel 2 from the shelf 3."
},
{
"role": "assistant",
"content": "Think: Now I'll go to garbagecan 1 to put towel 2 down.\nAct: go to garbagecan 1"
},
{
"role": "user",
"content": "On the garbagecan 1, you see a soapbottle 1."
},
{
"role": "assistant",
"content": "Think: I'll put towel 2 in/on garbagecan 1 now.\nAct: put towel 2 in/on garbagecan 1"
},
{
"role": "user",
"content": "You put the towel 2 in/on the garbagecan 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a towel in/on garbagecan 1.",
"room_type": "bathroom",
"difficulty": "easy",
"num_steps": 9
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a countertop 1, a countertop 2, a cabinet 1, a cabinet 2, a cabinet 3, a fridge 1, a microwave 1, a sinkbasin 1, a stoveburner 1, a stoveburner 2, a drawer 1, a drawer 2, a drawer 3, a drawer 4, a drawer 5, a shelf 1, a shelf 2, a shelf 3, a shelf 4, a garbagecan 1, a toaster 1, a coffeemachine 1.\n\nYour task is to: put a tomato in/on fridge 1."
},
{
"role": "assistant",
"content": "Think: To complete this task, I need tomato. I'll search shelf 3.\nAct: go to shelf 3"
},
{
"role": "user",
"content": "On the shelf 3, you see a tomato 1."
},
{
"role": "assistant",
"content": "Think: There's tomato 1 here. Let me take it.\nAct: take tomato 1 from shelf 3"
},
{
"role": "user",
"content": "You pick up the tomato 1 from the shelf 3."
},
{
"role": "assistant",
"content": "Think: Final step: put tomato 1 in/on fridge 1.\nAct: go to fridge 1"
},
{
"role": "user",
"content": "The fridge 1 is closed."
},
{
"role": "assistant",
"content": "Think: The fridge 1 is closed. I need to open it first.\nAct: open fridge 1"
},
{
"role": "user",
"content": "You open the fridge 1. The fridge 1 is open. In it, you see nothing."
},
{
"role": "assistant",
"content": "Think: I'll put tomato 1 in/on fridge 1 now.\nAct: put tomato 1 in/on fridge 1"
},
{
"role": "user",
"content": "You put the tomato 1 in/on the fridge 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a tomato in/on fridge 1.",
"room_type": "kitchen",
"difficulty": "easy",
"num_steps": 11
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a sinkbasin 1, a toilet 1, a bathtubbasin 1, a cabinet 1, a cabinet 2, a cabinet 3, a cabinet 4, a cabinet 5, a cabinet 6, a countertop 1, a countertop 2, a shelf 1, a shelf 2, a towelholder 1, a garbagecan 1, a drawer 1, a drawer 2, a drawer 3, a drawer 4.\n\nYour task is to: put a cloth in/on sinkbasin 1."
},
{
"role": "assistant",
"content": "Think: cloth might be at cabinet 6. Let me go there.\nAct: go to cabinet 6"
},
{
"role": "user",
"content": "The cabinet 6 appears to be empty."
},
{
"role": "assistant",
"content": "Think: cloth wasn't there. Let me try cabinet 1.\nAct: go to cabinet 1"
},
{
"role": "user",
"content": "The cabinet 1 is closed."
},
{
"role": "assistant",
"content": "Think: I should open the cabinet 1 to check its contents.\nAct: open cabinet 1"
},
{
"role": "user",
"content": "You open the cabinet 1. The cabinet 1 is open. In it, you see nothing."
},
{
"role": "assistant",
"content": "Think: I don't see cloth here. I'll try shelf 2 next.\nAct: go to shelf 2"
},
{
"role": "user",
"content": "On the shelf 2, you see nothing."
},
{
"role": "assistant",
"content": "Think: I don't see cloth here. I'll try towelholder 1 next.\nAct: go to towelholder 1"
},
{
"role": "user",
"content": "On the towelholder 1, you see nothing."
},
{
"role": "assistant",
"content": "Think: No luck. Let me look at cabinet 2.\nAct: go to cabinet 2"
},
{
"role": "user",
"content": "The cabinet 2 is closed."
},
{
"role": "assistant",
"content": "Think: The cabinet 2 is closed. I need to open it first.\nAct: open cabinet 2"
},
{
"role": "user",
"content": "You open the cabinet 2. The cabinet 2 is open. In it, you see a toiletpaper 1, a cloth 1, and a spraybottle 1."
},
{
"role": "assistant",
"content": "Think: There's cloth 1 here. Let me take it.\nAct: take cloth 1 from cabinet 2"
},
{
"role": "user",
"content": "You pick up the cloth 1 from the cabinet 2."
},
{
"role": "assistant",
"content": "Think: I should bring cloth 1 to sinkbasin 1 and place it there.\nAct: go to sinkbasin 1"
},
{
"role": "user",
"content": "On the sinkbasin 1, you see a scrubbrush 1, a scrubbrush 3, a soapbottle 3, and a towel 2."
},
{
"role": "assistant",
"content": "Think: Let me place cloth 1 here.\nAct: put cloth 1 in/on sinkbasin 1"
},
{
"role": "user",
"content": "You put the cloth 1 in/on the sinkbasin 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a cloth in/on sinkbasin 1.",
"room_type": "bathroom",
"difficulty": "hard",
"num_steps": 21
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a bed 1, a desk 1, a drawer 1, a drawer 2, a drawer 3, a shelf 1, a shelf 2, a sidetable 1, a sidetable 2, a sidetable 3, a dresser 1, a safe 1, a garbagecan 1, a laundryhamper 1.\n\nYour task is to: put a pillow in/on drawer 1."
},
{
"role": "assistant",
"content": "Think: First, I should locate pillow. bed 1 seems like a good place to look.\nAct: go to bed 1"
},
{
"role": "user",
"content": "On the bed 1, you see a book 1."
},
{
"role": "assistant",
"content": "Think: I don't see pillow here. I'll try sidetable 1 next.\nAct: go to sidetable 1"
},
{
"role": "user",
"content": "On the sidetable 1, you see a pencil 1, a alarmclock 2, a laptop 1, and a alarmclock 3."
},
{
"role": "assistant",
"content": "Think: No luck. Let me look at garbagecan 1.\nAct: go to garbagecan 1"
},
{
"role": "user",
"content": "On the garbagecan 1, you see a statue 1 and a pillow 1."
},
{
"role": "assistant",
"content": "Think: I can see pillow 1 on garbagecan 1. I'll grab it.\nAct: take pillow 1 from garbagecan 1"
},
{
"role": "user",
"content": "You pick up the pillow 1 from the garbagecan 1."
},
{
"role": "assistant",
"content": "Think: I should bring pillow 1 to drawer 1 and place it there.\nAct: go to drawer 1"
},
{
"role": "user",
"content": "The drawer 1 is closed."
},
{
"role": "assistant",
"content": "Think: The drawer 1 is closed. I need to open it first.\nAct: open drawer 1"
},
{
"role": "user",
"content": "You open the drawer 1. The drawer 1 is open. In it, you see nothing."
},
{
"role": "assistant",
"content": "Think: I'll put pillow 1 in/on drawer 1 now.\nAct: put pillow 1 in/on drawer 1"
},
{
"role": "user",
"content": "You put the pillow 1 in/on the drawer 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a pillow in/on drawer 1.",
"room_type": "bedroom",
"difficulty": "normal",
"num_steps": 15
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a countertop 1, a countertop 2, a cabinet 1, a cabinet 2, a cabinet 3, a cabinet 4, a fridge 1, a microwave 1, a sinkbasin 1, a stoveburner 1, a stoveburner 2, a drawer 1, a shelf 1, a shelf 2, a shelf 3, a shelf 4, a shelf 5, a shelf 6, a garbagecan 1, a toaster 1, a coffeemachine 1.\n\nYour task is to: put a mug in/on drawer 1."
},
{
"role": "assistant",
"content": "Think: My goal requires mug. Let me try sinkbasin 1.\nAct: go to sinkbasin 1"
},
{
"role": "user",
"content": "The sinkbasin 1 is clean."
},
{
"role": "assistant",
"content": "Think: I didn't find mug. shelf 1 might have it.\nAct: go to shelf 1"
},
{
"role": "user",
"content": "The shelf 1 appears to be empty."
},
{
"role": "assistant",
"content": "Think: mug is not here. Let me check shelf 6.\nAct: go to shelf 6"
},
{
"role": "user",
"content": "On the shelf 6, you see a soapbottle 1."
},
{
"role": "assistant",
"content": "Think: mug is not here. Let me check stoveburner 2.\nAct: go to stoveburner 2"
},
{
"role": "user",
"content": "On the stoveburner 2, you see a egg 1, a fork 1, a dishsponge 2, and a mug 1."
},
{
"role": "assistant",
"content": "Think: I can see mug 1 on stoveburner 2. I'll grab it.\nAct: take mug 1 from stoveburner 2"
},
{
"role": "user",
"content": "You pick up the mug 1 from the stoveburner 2."
},
{
"role": "assistant",
"content": "Think: Time to put mug 1 in/on drawer 1.\nAct: go to drawer 1"
},
{
"role": "user",
"content": "The drawer 1 is open. In it, you see a bowl 1."
},
{
"role": "assistant",
"content": "Think: Now I'll set mug 1 down in/on drawer 1.\nAct: put mug 1 in/on drawer 1"
},
{
"role": "user",
"content": "You put the mug 1 in/on the drawer 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a mug in/on drawer 1.",
"room_type": "kitchen",
"difficulty": "hard",
"num_steps": 15
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a sinkbasin 1, a toilet 1, a bathtubbasin 1, a cabinet 1, a cabinet 2, a cabinet 3, a countertop 1, a countertop 2, a shelf 1, a shelf 2, a shelf 3, a shelf 4, a shelf 5, a shelf 6, a towelholder 1, a garbagecan 1, a drawer 1.\n\nYour task is to: put a soapbar in/on toilet 1."
},
{
"role": "assistant",
"content": "Think: My goal requires soapbar. Let me try shelf 4.\nAct: go to shelf 4"
},
{
"role": "user",
"content": "On the shelf 4, you see a cloth 1 and a cloth 2."
},
{
"role": "assistant",
"content": "Think: soapbar wasn't there. Let me try countertop 2.\nAct: go to countertop 2"
},
{
"role": "user",
"content": "On the countertop 2, you see a scrubbrush 1."
},
{
"role": "assistant",
"content": "Think: I don't see soapbar here. I'll try shelf 3 next.\nAct: go to shelf 3"
},
{
"role": "user",
"content": "The shelf 3 appears to be empty."
},
{
"role": "assistant",
"content": "Think: soapbar is not here. Let me check shelf 2.\nAct: go to shelf 2"
},
{
"role": "user",
"content": "On the shelf 2, you see a spraybottle 1."
},
{
"role": "assistant",
"content": "Think: I didn't find soapbar. toilet 1 might have it.\nAct: go to toilet 1"
},
{
"role": "user",
"content": "The toilet 1 is clean."
},
{
"role": "assistant",
"content": "Think: No luck. Let me look at cabinet 3.\nAct: go to cabinet 3"
},
{
"role": "user",
"content": "The cabinet 3 is closed."
},
{
"role": "assistant",
"content": "Think: The cabinet 3 is closed. I need to open it first.\nAct: open cabinet 3"
},
{
"role": "user",
"content": "You open the cabinet 3. The cabinet 3 is open. In it, you see a soapbar 1 and a soapbar 2."
},
{
"role": "assistant",
"content": "Think: There's soapbar 2 here. Let me take it.\nAct: take soapbar 2 from cabinet 3"
},
{
"role": "user",
"content": "You pick up the soapbar 2 from the cabinet 3."
},
{
"role": "assistant",
"content": "Think: I should bring soapbar 2 to toilet 1 and place it there.\nAct: go to toilet 1"
},
{
"role": "user",
"content": "The toilet 1 is clean."
},
{
"role": "assistant",
"content": "Think: Let me place soapbar 2 here.\nAct: put soapbar 2 in/on toilet 1"
},
{
"role": "user",
"content": "You put the soapbar 2 in/on the toilet 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a soapbar in/on toilet 1.",
"room_type": "bathroom",
"difficulty": "hard",
"num_steps": 21
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a countertop 1, a cabinet 1, a cabinet 2, a cabinet 3, a cabinet 4, a cabinet 5, a fridge 1, a microwave 1, a sinkbasin 1, a stoveburner 1, a stoveburner 2, a drawer 1, a shelf 1, a shelf 2, a garbagecan 1, a toaster 1, a coffeemachine 1.\n\nYour task is to: put a pot in/on toaster 1."
},
{
"role": "assistant",
"content": "Think: I should look for pot. Let me start with stoveburner 1.\nAct: go to stoveburner 1"
},
{
"role": "user",
"content": "On the stoveburner 1, you see a butterknife 1."
},
{
"role": "assistant",
"content": "Think: No luck. Let me look at sinkbasin 1.\nAct: go to sinkbasin 1"
},
{
"role": "user",
"content": "On the sinkbasin 1, you see a tomato 1 and a fork 1."
},
{
"role": "assistant",
"content": "Think: Not here. Moving on to cabinet 4.\nAct: go to cabinet 4"
},
{
"role": "user",
"content": "The cabinet 4 is closed."
},
{
"role": "assistant",
"content": "Think: cabinet 4 is closed. Let me open it to see what's inside.\nAct: open cabinet 4"
},
{
"role": "user",
"content": "You open the cabinet 4. The cabinet 4 is open. In it, you see a potato 1."
},
{
"role": "assistant",
"content": "Think: I didn't find pot. stoveburner 2 might have it.\nAct: go to stoveburner 2"
},
{
"role": "user",
"content": "On the stoveburner 2, you see a pot 1."
},
{
"role": "assistant",
"content": "Think: I can see pot 1 on stoveburner 2. I'll grab it.\nAct: take pot 1 from stoveburner 2"
},
{
"role": "user",
"content": "You pick up the pot 1 from the stoveburner 2."
},
{
"role": "assistant",
"content": "Think: Now I'll go to toaster 1 to put pot 1 down.\nAct: go to toaster 1"
},
{
"role": "user",
"content": "On the toaster 1, you see a pan 1."
},
{
"role": "assistant",
"content": "Think: I'll put pot 1 in/on toaster 1 now.\nAct: put pot 1 in/on toaster 1"
},
{
"role": "user",
"content": "You put the pot 1 in/on the toaster 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a pot in/on toaster 1.",
"room_type": "kitchen",
"difficulty": "normal",
"num_steps": 17
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a bed 1, a desk 1, a drawer 1, a drawer 2, a drawer 3, a drawer 4, a shelf 1, a shelf 2, a shelf 3, a shelf 4, a shelf 5, a sidetable 1, a dresser 1, a safe 1, a garbagecan 1, a laundryhamper 1.\n\nYour task is to: put a watch in/on safe 1."
},
{
"role": "assistant",
"content": "Think: First, I should locate watch. shelf 2 seems like a good place to look.\nAct: go to shelf 2"
},
{
"role": "user",
"content": "On the shelf 2, you see a tissuebox 1."
},
{
"role": "assistant",
"content": "Think: No luck. Let me look at shelf 4.\nAct: go to shelf 4"
},
{
"role": "user",
"content": "The shelf 4 appears to be empty."
},
{
"role": "assistant",
"content": "Think: No luck. Let me look at desk 1.\nAct: go to desk 1"
},
{
"role": "user",
"content": "On the desk 1, you see a tissuebox 2."
},
{
"role": "assistant",
"content": "Think: No luck. Let me look at drawer 4.\nAct: go to drawer 4"
},
{
"role": "user",
"content": "The drawer 4 is closed."
},
{
"role": "assistant",
"content": "Think: drawer 4 is closed. Let me open it to see what's inside.\nAct: open drawer 4"
},
{
"role": "user",
"content": "You open the drawer 4. The drawer 4 is open. In it, you see a desklamp 2."
},
{
"role": "assistant",
"content": "Think: I didn't find watch. dresser 1 might have it.\nAct: go to dresser 1"
},
{
"role": "user",
"content": "On the dresser 1, you see nothing."
},
{
"role": "assistant",
"content": "Think: watch wasn't there. Let me try bed 1.\nAct: go to bed 1"
},
{
"role": "user",
"content": "On the bed 1, you see a alarmclock 1, a watch 1, and a tissuebox 4."
},
{
"role": "assistant",
"content": "Think: Found it! watch 1 is on bed 1. Let me pick it up.\nAct: take watch 1 from bed 1"
},
{
"role": "user",
"content": "You pick up the watch 1 from the bed 1."
},
{
"role": "assistant",
"content": "Think: Time to put watch 1 in/on safe 1.\nAct: go to safe 1"
},
{
"role": "user",
"content": "The safe 1 is closed."
},
{
"role": "assistant",
"content": "Think: I should open the safe 1 to check its contents.\nAct: open safe 1"
},
{
"role": "user",
"content": "You open the safe 1. The safe 1 is open. In it, you see a vase 1, a desklamp 1, and a tissuebox 3."
},
{
"role": "assistant",
"content": "Think: I'll put watch 1 in/on safe 1 now.\nAct: put watch 1 in/on safe 1"
},
{
"role": "user",
"content": "You put the watch 1 in/on the safe 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a watch in/on safe 1.",
"room_type": "bedroom",
"difficulty": "hard",
"num_steps": 23
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a sinkbasin 1, a toilet 1, a bathtubbasin 1, a cabinet 1, a countertop 1, a countertop 2, a shelf 1, a towelholder 1, a garbagecan 1, a drawer 1, a drawer 2.\n\nYour task is to: put a candle in/on shelf 1."
},
{
"role": "assistant",
"content": "Think: First, I should locate candle. countertop 2 seems like a good place to look.\nAct: go to countertop 2"
},
{
"role": "user",
"content": "On the countertop 2, you see a cloth 3."
},
{
"role": "assistant",
"content": "Think: I don't see candle here. I'll try cabinet 1 next.\nAct: go to cabinet 1"
},
{
"role": "user",
"content": "The cabinet 1 is closed."
},
{
"role": "assistant",
"content": "Think: The cabinet 1 is closed. I need to open it first.\nAct: open cabinet 1"
},
{
"role": "user",
"content": "You open the cabinet 1. The cabinet 1 is open. In it, you see a cloth 1, a candle 1, a towel 1, and a spraybottle 1."
},
{
"role": "assistant",
"content": "Think: I found candle 1 on cabinet 1. I should pick it up.\nAct: take candle 1 from cabinet 1"
},
{
"role": "user",
"content": "You pick up the candle 1 from the cabinet 1."
},
{
"role": "assistant",
"content": "Think: Now I need to place candle 1 in/on shelf 1. Let me go there.\nAct: go to shelf 1"
},
{
"role": "user",
"content": "On the shelf 1, you see nothing."
},
{
"role": "assistant",
"content": "Think: Let me place candle 1 here.\nAct: put candle 1 in/on shelf 1"
},
{
"role": "user",
"content": "You put the candle 1 in/on the shelf 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a candle in/on shelf 1.",
"room_type": "bathroom",
"difficulty": "normal",
"num_steps": 13
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a countertop 1, a countertop 2, a cabinet 1, a cabinet 2, a cabinet 3, a cabinet 4, a fridge 1, a microwave 1, a sinkbasin 1, a stoveburner 1, a stoveburner 2, a drawer 1, a drawer 2, a drawer 3, a drawer 4, a drawer 5, a drawer 6, a shelf 1, a shelf 2, a shelf 3, a shelf 4, a shelf 5, a garbagecan 1, a toaster 1, a coffeemachine 1.\n\nYour task is to: put a spoon in/on drawer 1."
},
{
"role": "assistant",
"content": "Think: My goal requires spoon. Let me try toaster 1.\nAct: go to toaster 1"
},
{
"role": "user",
"content": "On the toaster 1, you see a dishsponge 1."
},
{
"role": "assistant",
"content": "Think: I don't see spoon here. I'll try drawer 3 next.\nAct: go to drawer 3"
},
{
"role": "user",
"content": "On the drawer 3, you see nothing."
},
{
"role": "assistant",
"content": "Think: I didn't find spoon. drawer 6 might have it.\nAct: go to drawer 6"
},
{
"role": "user",
"content": "The drawer 6 is closed."
},
{
"role": "assistant",
"content": "Think: I should open the drawer 6 to check its contents.\nAct: open drawer 6"
},
{
"role": "user",
"content": "You open the drawer 6. The drawer 6 is open. In it, you see nothing."
},
{
"role": "assistant",
"content": "Think: spoon is not here. Let me check countertop 2.\nAct: go to countertop 2"
},
{
"role": "user",
"content": "On the countertop 2, you see a spoon 1."
},
{
"role": "assistant",
"content": "Think: I found spoon 1 on countertop 2. I should pick it up.\nAct: take spoon 1 from countertop 2"
},
{
"role": "user",
"content": "You pick up the spoon 1 from the countertop 2."
},
{
"role": "assistant",
"content": "Think: Final step: put spoon 1 in/on drawer 1.\nAct: go to drawer 1"
},
{
"role": "user",
"content": "The drawer 1 is closed."
},
{
"role": "assistant",
"content": "Think: The drawer 1 is closed. I need to open it first.\nAct: open drawer 1"
},
{
"role": "user",
"content": "You open the drawer 1. The drawer 1 is open. In it, you see a potato 1."
},
{
"role": "assistant",
"content": "Think: I'll put spoon 1 in/on drawer 1 now.\nAct: put spoon 1 in/on drawer 1"
},
{
"role": "user",
"content": "You put the spoon 1 in/on the drawer 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a spoon in/on drawer 1.",
"room_type": "kitchen",
"difficulty": "normal",
"num_steps": 19
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a sofa 1, a coffeetable 1, a sidetable 1, a sidetable 2, a sidetable 3, a shelf 1, a drawer 1, a drawer 2, a drawer 3, a drawer 4, a drawer 5, a dresser 1, a armchair 1, a desk 1, a garbagecan 1, a safe 1.\n\nYour task is to: put a newspaper in/on garbagecan 1."
},
{
"role": "assistant",
"content": "Think: newspaper might be at sidetable 1. Let me go there.\nAct: go to sidetable 1"
},
{
"role": "user",
"content": "On the sidetable 1, you see a pencil 2, a pencil 4, and a statue 2."
},
{
"role": "assistant",
"content": "Think: Not here. Moving on to desk 1.\nAct: go to desk 1"
},
{
"role": "user",
"content": "On the desk 1, you see a tissuebox 1 and a desklamp 1."
},
{
"role": "assistant",
"content": "Think: No luck. Let me look at drawer 3.\nAct: go to drawer 3"
},
{
"role": "user",
"content": "The drawer 3 appears to be empty."
},
{
"role": "assistant",
"content": "Think: newspaper wasn't there. Let me try dresser 1.\nAct: go to dresser 1"
},
{
"role": "user",
"content": "On the dresser 1, you see a statue 1."
},
{
"role": "assistant",
"content": "Think: No luck. Let me look at drawer 4.\nAct: go to drawer 4"
},
{
"role": "user",
"content": "The drawer 4 is open. In it, you see a cellphone 1 and a tissuebox 2."
},
{
"role": "assistant",
"content": "Think: I don't see newspaper here. I'll try armchair 1 next.\nAct: go to armchair 1"
},
{
"role": "user",
"content": "On the armchair 1, you see a pen 1 and a pen 2."
},
{
"role": "assistant",
"content": "Think: I didn't find newspaper. drawer 2 might have it.\nAct: go to drawer 2"
},
{
"role": "user",
"content": "The drawer 2 is closed."
},
{
"role": "assistant",
"content": "Think: drawer 2 is closed. Let me open it to see what's inside.\nAct: open drawer 2"
},
{
"role": "user",
"content": "You open the drawer 2. The drawer 2 is open. In it, you see a newspaper 1."
},
{
"role": "assistant",
"content": "Think: Found it! newspaper 1 is on drawer 2. Let me pick it up.\nAct: take newspaper 1 from drawer 2"
},
{
"role": "user",
"content": "You pick up the newspaper 1 from the drawer 2."
},
{
"role": "assistant",
"content": "Think: I should bring newspaper 1 to garbagecan 1 and place it there.\nAct: go to garbagecan 1"
},
{
"role": "user",
"content": "On the garbagecan 1, you see nothing."
},
{
"role": "assistant",
"content": "Think: Now I'll set newspaper 1 down in/on garbagecan 1.\nAct: put newspaper 1 in/on garbagecan 1"
},
{
"role": "user",
"content": "You put the newspaper 1 in/on the garbagecan 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a newspaper in/on garbagecan 1.",
"room_type": "livingroom",
"difficulty": "hard",
"num_steps": 23
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a sinkbasin 1, a toilet 1, a bathtubbasin 1, a cabinet 1, a cabinet 2, a cabinet 3, a cabinet 4, a cabinet 5, a countertop 1, a countertop 2, a shelf 1, a towelholder 1, a garbagecan 1, a drawer 1, a drawer 2, a drawer 3.\n\nYour task is to: put a candle in/on garbagecan 1."
},
{
"role": "assistant",
"content": "Think: I should look for candle. Let me start with countertop 1.\nAct: go to countertop 1"
},
{
"role": "user",
"content": "The countertop 1 appears to be empty."
},
{
"role": "assistant",
"content": "Think: I don't see candle here. I'll try toilet 1 next.\nAct: go to toilet 1"
},
{
"role": "user",
"content": "On the toilet 1, you see a soapbottle 1, a tissuebox 1, and a spraybottle 2."
},
{
"role": "assistant",
"content": "Think: Not here. Moving on to cabinet 5.\nAct: go to cabinet 5"
},
{
"role": "user",
"content": "The cabinet 5 is closed."
},
{
"role": "assistant",
"content": "Think: cabinet 5 is closed. Let me open it to see what's inside.\nAct: open cabinet 5"
},
{
"role": "user",
"content": "You open the cabinet 5. The cabinet 5 is open. In it, you see a tissuebox 2 and a candle 1."
},
{
"role": "assistant",
"content": "Think: I can see candle 1 on cabinet 5. I'll grab it.\nAct: take candle 1 from cabinet 5"
},
{
"role": "user",
"content": "You pick up the candle 1 from the cabinet 5."
},
{
"role": "assistant",
"content": "Think: Now I'll go to garbagecan 1 to put candle 1 down.\nAct: go to garbagecan 1"
},
{
"role": "user",
"content": "On the garbagecan 1, you see a scrubbrush 1."
},
{
"role": "assistant",
"content": "Think: I'll put candle 1 in/on garbagecan 1 now.\nAct: put candle 1 in/on garbagecan 1"
},
{
"role": "user",
"content": "You put the candle 1 in/on the garbagecan 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a candle in/on garbagecan 1.",
"room_type": "bathroom",
"difficulty": "normal",
"num_steps": 15
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a bed 1, a desk 1, a drawer 1, a drawer 2, a drawer 3, a drawer 4, a drawer 5, a shelf 1, a sidetable 1, a sidetable 2, a sidetable 3, a dresser 1, a safe 1, a garbagecan 1, a laundryhamper 1.\n\nYour task is to: put a cd in/on shelf 1."
},
{
"role": "assistant",
"content": "Think: cd might be at desk 1. Let me go there.\nAct: go to desk 1"
},
{
"role": "user",
"content": "On the desk 1, you see a watch 1 and a tissuebox 1."
},
{
"role": "assistant",
"content": "Think: No luck. Let me look at shelf 1.\nAct: go to shelf 1"
},
{
"role": "user",
"content": "The shelf 1 appears to be empty."
},
{
"role": "assistant",
"content": "Think: cd is not here. Let me check garbagecan 1.\nAct: go to garbagecan 1"
},
{
"role": "user",
"content": "On the garbagecan 1, you see a creditcard 1 and a desklamp 1."
},
{
"role": "assistant",
"content": "Think: I don't see cd here. I'll try drawer 4 next.\nAct: go to drawer 4"
},
{
"role": "user",
"content": "The drawer 4 is open. In it, you see a book 2."
},
{
"role": "assistant",
"content": "Think: No luck. Let me look at drawer 5.\nAct: go to drawer 5"
},
{
"role": "user",
"content": "The drawer 5 is closed."
},
{
"role": "assistant",
"content": "Think: drawer 5 is closed. Let me open it to see what's inside.\nAct: open drawer 5"
},
{
"role": "user",
"content": "You open the drawer 5. The drawer 5 is open. In it, you see a book 1, a pen 1, and a cd 1."
},
{
"role": "assistant",
"content": "Think: I found cd 1 on drawer 5. I should pick it up.\nAct: take cd 1 from drawer 5"
},
{
"role": "user",
"content": "You pick up the cd 1 from the drawer 5."
},
{
"role": "assistant",
"content": "Think: Now I'll go to shelf 1 to put cd 1 down.\nAct: go to shelf 1"
},
{
"role": "user",
"content": "The shelf 1 appears to be empty."
},
{
"role": "assistant",
"content": "Think: Let me place cd 1 here.\nAct: put cd 1 in/on shelf 1"
},
{
"role": "user",
"content": "You put the cd 1 in/on the shelf 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a cd in/on shelf 1.",
"room_type": "bedroom",
"difficulty": "hard",
"num_steps": 19
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a countertop 1, a countertop 2, a cabinet 1, a cabinet 2, a fridge 1, a microwave 1, a sinkbasin 1, a stoveburner 1, a drawer 1, a shelf 1, a shelf 2, a shelf 3, a garbagecan 1, a toaster 1, a coffeemachine 1.\n\nYour task is to: put a plate in/on sinkbasin 1."
},
{
"role": "assistant",
"content": "Think: I should look for plate. Let me start with drawer 1.\nAct: go to drawer 1"
},
{
"role": "user",
"content": "The drawer 1 is closed."
},
{
"role": "assistant",
"content": "Think: I should open the drawer 1 to check its contents.\nAct: open drawer 1"
},
{
"role": "user",
"content": "You open the drawer 1. The drawer 1 is open. In it, you see a bread 1, a peppershaker 1, and a saltshaker 1."
},
{
"role": "assistant",
"content": "Think: plate wasn't there. Let me try shelf 3.\nAct: go to shelf 3"
},
{
"role": "user",
"content": "On the shelf 3, you see nothing."
},
{
"role": "assistant",
"content": "Think: No luck. Let me look at garbagecan 1.\nAct: go to garbagecan 1"
},
{
"role": "user",
"content": "On the garbagecan 1, you see a plate 1."
},
{
"role": "assistant",
"content": "Think: There's plate 1 here. Let me take it.\nAct: take plate 1 from garbagecan 1"
},
{
"role": "user",
"content": "You pick up the plate 1 from the garbagecan 1."
},
{
"role": "assistant",
"content": "Think: I should bring plate 1 to sinkbasin 1 and place it there.\nAct: go to sinkbasin 1"
},
{
"role": "user",
"content": "The sinkbasin 1 is clean."
},
{
"role": "assistant",
"content": "Think: Let me place plate 1 here.\nAct: put plate 1 in/on sinkbasin 1"
},
{
"role": "user",
"content": "You put the plate 1 in/on the sinkbasin 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a plate in/on sinkbasin 1.",
"room_type": "kitchen",
"difficulty": "normal",
"num_steps": 15
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a sofa 1, a coffeetable 1, a sidetable 1, a sidetable 2, a shelf 1, a drawer 1, a drawer 2, a drawer 3, a drawer 4, a drawer 5, a dresser 1, a armchair 1, a desk 1, a garbagecan 1, a safe 1.\n\nYour task is to: put a remotecontrol in/on armchair 1."
},
{
"role": "assistant",
"content": "Think: I need to find remotecontrol. Let me check desk 1.\nAct: go to desk 1"
},
{
"role": "user",
"content": "On the desk 1, you see a box 1 and a vase 2."
},
{
"role": "assistant",
"content": "Think: No luck. Let me look at sidetable 1.\nAct: go to sidetable 1"
},
{
"role": "user",
"content": "On the sidetable 1, you see a pencil 1."
},
{
"role": "assistant",
"content": "Think: remotecontrol wasn't there. Let me try drawer 4.\nAct: go to drawer 4"
},
{
"role": "user",
"content": "On the drawer 4, you see nothing."
},
{
"role": "assistant",
"content": "Think: remotecontrol is not here. Let me check garbagecan 1.\nAct: go to garbagecan 1"
},
{
"role": "user",
"content": "On the garbagecan 1, you see a pencil 2 and a vase 1."
},
{
"role": "assistant",
"content": "Think: I didn't find remotecontrol. dresser 1 might have it.\nAct: go to dresser 1"
},
{
"role": "user",
"content": "On the dresser 1, you see a candle 2."
},
{
"role": "assistant",
"content": "Think: No luck. Let me look at drawer 5.\nAct: go to drawer 5"
},
{
"role": "user",
"content": "The drawer 5 is closed."
},
{
"role": "assistant",
"content": "Think: The drawer 5 is closed. I need to open it first.\nAct: open drawer 5"
},
{
"role": "user",
"content": "You open the drawer 5. The drawer 5 is open. In it, you see nothing."
},
{
"role": "assistant",
"content": "Think: No luck. Let me look at drawer 2.\nAct: go to drawer 2"
},
{
"role": "user",
"content": "The drawer 2 is closed."
},
{
"role": "assistant",
"content": "Think: The drawer 2 is closed. I need to open it first.\nAct: open drawer 2"
},
{
"role": "user",
"content": "You open the drawer 2. The drawer 2 is open. In it, you see a remotecontrol 1."
},
{
"role": "assistant",
"content": "Think: I found remotecontrol 1 on drawer 2. I should pick it up.\nAct: take remotecontrol 1 from drawer 2"
},
{
"role": "user",
"content": "You pick up the remotecontrol 1 from the drawer 2."
},
{
"role": "assistant",
"content": "Think: I should bring remotecontrol 1 to armchair 1 and place it there.\nAct: go to armchair 1"
},
{
"role": "user",
"content": "On the armchair 1, you see a creditcard 1, a keychain 1, and a laptop 1."
},
{
"role": "assistant",
"content": "Think: Let me place remotecontrol 1 here.\nAct: put remotecontrol 1 in/on armchair 1"
},
{
"role": "user",
"content": "You put the remotecontrol 1 in/on the armchair 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a remotecontrol in/on armchair 1.",
"room_type": "livingroom",
"difficulty": "hard",
"num_steps": 25
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a sinkbasin 1, a toilet 1, a bathtubbasin 1, a cabinet 1, a cabinet 2, a cabinet 3, a countertop 1, a shelf 1, a towelholder 1, a garbagecan 1, a drawer 1, a drawer 2.\n\nYour task is to: put a toiletpaper in/on garbagecan 1."
},
{
"role": "assistant",
"content": "Think: To complete this task, I need toiletpaper. I'll search cabinet 2.\nAct: go to cabinet 2"
},
{
"role": "user",
"content": "The cabinet 2 is closed."
},
{
"role": "assistant",
"content": "Think: cabinet 2 is closed. Let me open it to see what's inside.\nAct: open cabinet 2"
},
{
"role": "user",
"content": "You open the cabinet 2. The cabinet 2 is open. In it, you see a toiletpaper 1, a cloth 2, and a candle 1."
},
{
"role": "assistant",
"content": "Think: I can see toiletpaper 1 on cabinet 2. I'll grab it.\nAct: take toiletpaper 1 from cabinet 2"
},
{
"role": "user",
"content": "You pick up the toiletpaper 1 from the cabinet 2."
},
{
"role": "assistant",
"content": "Think: Final step: put toiletpaper 1 in/on garbagecan 1.\nAct: go to garbagecan 1"
},
{
"role": "user",
"content": "On the garbagecan 1, you see a plunger 3."
},
{
"role": "assistant",
"content": "Think: Let me place toiletpaper 1 here.\nAct: put toiletpaper 1 in/on garbagecan 1"
},
{
"role": "user",
"content": "You put the toiletpaper 1 in/on the garbagecan 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a toiletpaper in/on garbagecan 1.",
"room_type": "bathroom",
"difficulty": "easy",
"num_steps": 11
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a countertop 1, a countertop 2, a cabinet 1, a cabinet 2, a cabinet 3, a fridge 1, a microwave 1, a sinkbasin 1, a stoveburner 1, a drawer 1, a shelf 1, a shelf 2, a shelf 3, a garbagecan 1, a toaster 1, a coffeemachine 1.\n\nYour task is to: put a spatula in/on countertop 1."
},
{
"role": "assistant",
"content": "Think: I need to find spatula. Let me check shelf 2.\nAct: go to shelf 2"
},
{
"role": "user",
"content": "On the shelf 2, you see nothing."
},
{
"role": "assistant",
"content": "Think: spatula is not here. Let me check countertop 2.\nAct: go to countertop 2"
},
{
"role": "user",
"content": "On the countertop 2, you see a bowl 1 and a spatula 1."
},
{
"role": "assistant",
"content": "Think: There's spatula 1 here. Let me take it.\nAct: take spatula 1 from countertop 2"
},
{
"role": "user",
"content": "You pick up the spatula 1 from the countertop 2."
},
{
"role": "assistant",
"content": "Think: Time to put spatula 1 in/on countertop 1.\nAct: go to countertop 1"
},
{
"role": "user",
"content": "On the countertop 1, you see nothing."
},
{
"role": "assistant",
"content": "Think: Now I'll set spatula 1 down in/on countertop 1.\nAct: put spatula 1 in/on countertop 1"
},
{
"role": "user",
"content": "You put the spatula 1 in/on the countertop 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a spatula in/on countertop 1.",
"room_type": "kitchen",
"difficulty": "normal",
"num_steps": 11
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a bed 1, a desk 1, a drawer 1, a drawer 2, a drawer 3, a drawer 4, a drawer 5, a drawer 6, a shelf 1, a shelf 2, a shelf 3, a sidetable 1, a sidetable 2, a dresser 1, a safe 1, a garbagecan 1, a laundryhamper 1.\n\nYour task is to: put a creditcard in/on drawer 1."
},
{
"role": "assistant",
"content": "Think: My goal requires creditcard. Let me try drawer 3.\nAct: go to drawer 3"
},
{
"role": "user",
"content": "The drawer 3 appears to be empty."
},
{
"role": "assistant",
"content": "Think: Not here. Moving on to shelf 3.\nAct: go to shelf 3"
},
{
"role": "user",
"content": "On the shelf 3, you see nothing."
},
{
"role": "assistant",
"content": "Think: creditcard wasn't there. Let me try laundryhamper 1.\nAct: go to laundryhamper 1"
},
{
"role": "user",
"content": "On the laundryhamper 1, you see a cd 1 and a vase 1."
},
{
"role": "assistant",
"content": "Think: creditcard wasn't there. Let me try drawer 2.\nAct: go to drawer 2"
},
{
"role": "user",
"content": "The drawer 2 is closed."
},
{
"role": "assistant",
"content": "Think: I should open the drawer 2 to check its contents.\nAct: open drawer 2"
},
{
"role": "user",
"content": "You open the drawer 2. The drawer 2 is open. In it, you see a creditcard 1, a tissuebox 1, and a keychain 1."
},
{
"role": "assistant",
"content": "Think: I found creditcard 1 on drawer 2. I should pick it up.\nAct: take creditcard 1 from drawer 2"
},
{
"role": "user",
"content": "You pick up the creditcard 1 from the drawer 2."
},
{
"role": "assistant",
"content": "Think: Time to put creditcard 1 in/on drawer 1.\nAct: go to drawer 1"
},
{
"role": "user",
"content": "The drawer 1 is closed."
},
{
"role": "assistant",
"content": "Think: drawer 1 is closed. Let me open it to see what's inside.\nAct: open drawer 1"
},
{
"role": "user",
"content": "You open the drawer 1. The drawer 1 is open. In it, you see a cd 2 and a statue 3."
},
{
"role": "assistant",
"content": "Think: I'll put creditcard 1 in/on drawer 1 now.\nAct: put creditcard 1 in/on drawer 1"
},
{
"role": "user",
"content": "You put the creditcard 1 in/on the drawer 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a creditcard in/on drawer 1.",
"room_type": "bedroom",
"difficulty": "normal",
"num_steps": 19
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a countertop 1, a cabinet 1, a fridge 1, a microwave 1, a sinkbasin 1, a stoveburner 1, a drawer 1, a drawer 2, a shelf 1, a shelf 2, a garbagecan 1, a toaster 1, a coffeemachine 1.\n\nYour task is to: put a pan in/on toaster 1."
},
{
"role": "assistant",
"content": "Think: My goal requires pan. Let me try drawer 1.\nAct: go to drawer 1"
},
{
"role": "user",
"content": "The drawer 1 is closed."
},
{
"role": "assistant",
"content": "Think: I should open the drawer 1 to check its contents.\nAct: open drawer 1"
},
{
"role": "user",
"content": "You open the drawer 1. The drawer 1 is open. In it, you see a pan 1 and a bread 3."
},
{
"role": "assistant",
"content": "Think: There's pan 1 here. Let me take it.\nAct: take pan 1 from drawer 1"
},
{
"role": "user",
"content": "You pick up the pan 1 from the drawer 1."
},
{
"role": "assistant",
"content": "Think: Now I need to place pan 1 in/on toaster 1. Let me go there.\nAct: go to toaster 1"
},
{
"role": "user",
"content": "On the toaster 1, you see nothing."
},
{
"role": "assistant",
"content": "Think: I'll put pan 1 in/on toaster 1 now.\nAct: put pan 1 in/on toaster 1"
},
{
"role": "user",
"content": "You put the pan 1 in/on the toaster 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a pan in/on toaster 1.",
"room_type": "kitchen",
"difficulty": "easy",
"num_steps": 11
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a sinkbasin 1, a toilet 1, a bathtubbasin 1, a cabinet 1, a countertop 1, a shelf 1, a shelf 2, a shelf 3, a towelholder 1, a garbagecan 1, a drawer 1, a drawer 2.\n\nYour task is to: put a scrubbrush in/on toilet 1."
},
{
"role": "assistant",
"content": "Think: scrubbrush might be at shelf 1. Let me go there.\nAct: go to shelf 1"
},
{
"role": "user",
"content": "On the shelf 1, you see a scrubbrush 3."
},
{
"role": "assistant",
"content": "Think: No luck. Let me look at drawer 2.\nAct: go to drawer 2"
},
{
"role": "user",
"content": "The drawer 2 is closed."
},
{
"role": "assistant",
"content": "Think: I should open the drawer 2 to check its contents.\nAct: open drawer 2"
},
{
"role": "user",
"content": "You open the drawer 2. The drawer 2 is open. In it, you see a scrubbrush 2."
},
{
"role": "assistant",
"content": "Think: I can see scrubbrush 2 on drawer 2. I'll grab it.\nAct: take scrubbrush 2 from drawer 2"
},
{
"role": "user",
"content": "You pick up the scrubbrush 2 from the drawer 2."
},
{
"role": "assistant",
"content": "Think: Now I need to place scrubbrush 2 in/on toilet 1. Let me go there.\nAct: go to toilet 1"
},
{
"role": "user",
"content": "On the toilet 1, you see a spraybottle 1, a candle 2, and a soapbar 1."
},
{
"role": "assistant",
"content": "Think: Now I'll set scrubbrush 2 down in/on toilet 1.\nAct: put scrubbrush 2 in/on toilet 1"
},
{
"role": "user",
"content": "You put the scrubbrush 2 in/on the toilet 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a scrubbrush in/on toilet 1.",
"room_type": "bathroom",
"difficulty": "normal",
"num_steps": 13
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a sinkbasin 1, a toilet 1, a bathtubbasin 1, a cabinet 1, a cabinet 2, a cabinet 3, a cabinet 4, a cabinet 5, a cabinet 6, a countertop 1, a shelf 1, a shelf 2, a shelf 3, a shelf 4, a shelf 5, a towelholder 1, a garbagecan 1, a drawer 1, a drawer 2, a drawer 3, a drawer 4.\n\nYour task is to: put a soapbar in/on towelholder 1."
},
{
"role": "assistant",
"content": "Think: I need to find soapbar. Let me check countertop 1.\nAct: go to countertop 1"
},
{
"role": "user",
"content": "On the countertop 1, you see a soapbar 2."
},
{
"role": "assistant",
"content": "Think: Found it! soapbar 2 is on countertop 1. Let me pick it up.\nAct: take soapbar 2 from countertop 1"
},
{
"role": "user",
"content": "You pick up the soapbar 2 from the countertop 1."
},
{
"role": "assistant",
"content": "Think: I should bring soapbar 2 to towelholder 1 and place it there.\nAct: go to towelholder 1"
},
{
"role": "user",
"content": "The towelholder 1 appears to be empty."
},
{
"role": "assistant",
"content": "Think: Now I'll set soapbar 2 down in/on towelholder 1.\nAct: put soapbar 2 in/on towelholder 1"
},
{
"role": "user",
"content": "You put the soapbar 2 in/on the towelholder 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a soapbar in/on towelholder 1.",
"room_type": "bathroom",
"difficulty": "easy",
"num_steps": 9
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a bed 1, a desk 1, a drawer 1, a drawer 2, a shelf 1, a shelf 2, a sidetable 1, a sidetable 2, a dresser 1, a safe 1, a garbagecan 1, a laundryhamper 1.\n\nYour task is to: put a watch in/on drawer 1."
},
{
"role": "assistant",
"content": "Think: My goal requires watch. Let me try safe 1.\nAct: go to safe 1"
},
{
"role": "user",
"content": "The safe 1 is open. In it, you see a keychain 1 and a vase 1."
},
{
"role": "assistant",
"content": "Think: I didn't find watch. dresser 1 might have it.\nAct: go to dresser 1"
},
{
"role": "user",
"content": "On the dresser 1, you see a tissuebox 1."
},
{
"role": "assistant",
"content": "Think: watch wasn't there. Let me try garbagecan 1.\nAct: go to garbagecan 1"
},
{
"role": "user",
"content": "The garbagecan 1 appears to be empty."
},
{
"role": "assistant",
"content": "Think: Not here. Moving on to drawer 1.\nAct: go to drawer 1"
},
{
"role": "user",
"content": "The drawer 1 is open. In it, you see a watch 1."
},
{
"role": "assistant",
"content": "Think: There's watch 1 here. Let me take it.\nAct: take watch 1 from drawer 1"
},
{
"role": "user",
"content": "You pick up the watch 1 from the drawer 1."
},
{
"role": "assistant",
"content": "Think: Now I need to place watch 1 in/on drawer 1. Let me go there.\nAct: go to drawer 1"
},
{
"role": "user",
"content": "The drawer 1 appears to be empty."
},
{
"role": "assistant",
"content": "Think: Let me place watch 1 here.\nAct: put watch 1 in/on drawer 1"
},
{
"role": "user",
"content": "You put the watch 1 in/on the drawer 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a watch in/on drawer 1.",
"room_type": "bedroom",
"difficulty": "normal",
"num_steps": 15
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a bed 1, a desk 1, a drawer 1, a drawer 2, a drawer 3, a drawer 4, a shelf 1, a shelf 2, a shelf 3, a shelf 4, a shelf 5, a sidetable 1, a sidetable 2, a dresser 1, a safe 1, a garbagecan 1, a laundryhamper 1.\n\nYour task is to: put a statue in/on safe 1."
},
{
"role": "assistant",
"content": "Think: To complete this task, I need statue. I'll search laundryhamper 1.\nAct: go to laundryhamper 1"
},
{
"role": "user",
"content": "On the laundryhamper 1, you see a tissuebox 2."
},
{
"role": "assistant",
"content": "Think: I don't see statue here. I'll try drawer 3 next.\nAct: go to drawer 3"
},
{
"role": "user",
"content": "The drawer 3 is open. In it, you see a pen 2 and a statue 1."
},
{
"role": "assistant",
"content": "Think: Found it! statue 1 is on drawer 3. Let me pick it up.\nAct: take statue 1 from drawer 3"
},
{
"role": "user",
"content": "You pick up the statue 1 from the drawer 3."
},
{
"role": "assistant",
"content": "Think: Time to put statue 1 in/on safe 1.\nAct: go to safe 1"
},
{
"role": "user",
"content": "The safe 1 is closed."
},
{
"role": "assistant",
"content": "Think: safe 1 is closed. Let me open it to see what's inside.\nAct: open safe 1"
},
{
"role": "user",
"content": "You open the safe 1. The safe 1 is open. In it, you see nothing."
},
{
"role": "assistant",
"content": "Think: Let me place statue 1 here.\nAct: put statue 1 in/on safe 1"
},
{
"role": "user",
"content": "You put the statue 1 in/on the safe 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a statue in/on safe 1.",
"room_type": "bedroom",
"difficulty": "normal",
"num_steps": 13
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a sinkbasin 1, a toilet 1, a bathtubbasin 1, a cabinet 1, a cabinet 2, a cabinet 3, a cabinet 4, a countertop 1, a countertop 2, a shelf 1, a shelf 2, a shelf 3, a shelf 4, a shelf 5, a towelholder 1, a garbagecan 1, a drawer 1, a drawer 2, a drawer 3.\n\nYour task is to: put a spraybottle in/on countertop 1."
},
{
"role": "assistant",
"content": "Think: I should look for spraybottle. Let me start with countertop 1.\nAct: go to countertop 1"
},
{
"role": "user",
"content": "On the countertop 1, you see a scrubbrush 2 and a towel 1."
},
{
"role": "assistant",
"content": "Think: No luck. Let me look at cabinet 1.\nAct: go to cabinet 1"
},
{
"role": "user",
"content": "The cabinet 1 is closed."
},
{
"role": "assistant",
"content": "Think: cabinet 1 is closed. Let me open it to see what's inside.\nAct: open cabinet 1"
},
{
"role": "user",
"content": "You open the cabinet 1. The cabinet 1 is open. In it, you see nothing."
},
{
"role": "assistant",
"content": "Think: spraybottle wasn't there. Let me try countertop 2.\nAct: go to countertop 2"
},
{
"role": "user",
"content": "On the countertop 2, you see nothing."
},
{
"role": "assistant",
"content": "Think: I didn't find spraybottle. sinkbasin 1 might have it.\nAct: go to sinkbasin 1"
},
{
"role": "user",
"content": "On the sinkbasin 1, you see a spraybottle 1."
},
{
"role": "assistant",
"content": "Think: Found it! spraybottle 1 is on sinkbasin 1. Let me pick it up.\nAct: take spraybottle 1 from sinkbasin 1"
},
{
"role": "user",
"content": "You pick up the spraybottle 1 from the sinkbasin 1."
},
{
"role": "assistant",
"content": "Think: Final step: put spraybottle 1 in/on countertop 1.\nAct: go to countertop 1"
},
{
"role": "user",
"content": "On the countertop 1, you see a scrubbrush 2 and a towel 1."
},
{
"role": "assistant",
"content": "Think: Let me place spraybottle 1 here.\nAct: put spraybottle 1 in/on countertop 1"
},
{
"role": "user",
"content": "You put the spraybottle 1 in/on the countertop 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a spraybottle in/on countertop 1.",
"room_type": "bathroom",
"difficulty": "normal",
"num_steps": 17
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a countertop 1, a cabinet 1, a cabinet 2, a cabinet 3, a cabinet 4, a cabinet 5, a fridge 1, a microwave 1, a sinkbasin 1, a stoveburner 1, a drawer 1, a drawer 2, a shelf 1, a garbagecan 1, a toaster 1, a coffeemachine 1.\n\nYour task is to: put a tomato in/on sinkbasin 1."
},
{
"role": "assistant",
"content": "Think: tomato might be at cabinet 3. Let me go there.\nAct: go to cabinet 3"
},
{
"role": "user",
"content": "The cabinet 3 is closed."
},
{
"role": "assistant",
"content": "Think: cabinet 3 is closed. Let me open it to see what's inside.\nAct: open cabinet 3"
},
{
"role": "user",
"content": "You open the cabinet 3. The cabinet 3 is open. In it, you see a pan 2."
},
{
"role": "assistant",
"content": "Think: No luck. Let me look at cabinet 4.\nAct: go to cabinet 4"
},
{
"role": "user",
"content": "The cabinet 4 is closed."
},
{
"role": "assistant",
"content": "Think: I should open the cabinet 4 to check its contents.\nAct: open cabinet 4"
},
{
"role": "user",
"content": "You open the cabinet 4. The cabinet 4 is open. In it, you see nothing."
},
{
"role": "assistant",
"content": "Think: tomato wasn't there. Let me try drawer 2.\nAct: go to drawer 2"
},
{
"role": "user",
"content": "The drawer 2 is open. In it, you see a dishsponge 2, a spatula 3, and a knife 1."
},
{
"role": "assistant",
"content": "Think: Not here. Moving on to microwave 1.\nAct: go to microwave 1"
},
{
"role": "user",
"content": "The microwave 1 is closed."
},
{
"role": "assistant",
"content": "Think: microwave 1 is closed. Let me open it to see what's inside.\nAct: open microwave 1"
},
{
"role": "user",
"content": "You open the microwave 1. The microwave 1 is open. In it, you see a mug 1 and a tomato 1."
},
{
"role": "assistant",
"content": "Think: I can see tomato 1 on microwave 1. I'll grab it.\nAct: take tomato 1 from microwave 1"
},
{
"role": "user",
"content": "You pick up the tomato 1 from the microwave 1."
},
{
"role": "assistant",
"content": "Think: I should bring tomato 1 to sinkbasin 1 and place it there.\nAct: go to sinkbasin 1"
},
{
"role": "user",
"content": "On the sinkbasin 1, you see a saltshaker 1 and a dishsponge 3."
},
{
"role": "assistant",
"content": "Think: Now I'll set tomato 1 down in/on sinkbasin 1.\nAct: put tomato 1 in/on sinkbasin 1"
},
{
"role": "user",
"content": "You put the tomato 1 in/on the sinkbasin 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a tomato in/on sinkbasin 1.",
"room_type": "kitchen",
"difficulty": "normal",
"num_steps": 21
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a sofa 1, a coffeetable 1, a sidetable 1, a shelf 1, a shelf 2, a shelf 3, a drawer 1, a drawer 2, a drawer 3, a drawer 4, a drawer 5, a drawer 6, a dresser 1, a armchair 1, a desk 1, a garbagecan 1, a safe 1.\n\nYour task is to: put a creditcard in/on drawer 1."
},
{
"role": "assistant",
"content": "Think: I should look for creditcard. Let me start with shelf 1.\nAct: go to shelf 1"
},
{
"role": "user",
"content": "On the shelf 1, you see a newspaper 1 and a candle 1."
},
{
"role": "assistant",
"content": "Think: I don't see creditcard here. I'll try shelf 2 next.\nAct: go to shelf 2"
},
{
"role": "user",
"content": "On the shelf 2, you see a creditcard 1."
},
{
"role": "assistant",
"content": "Think: I can see creditcard 1 on shelf 2. I'll grab it.\nAct: take creditcard 1 from shelf 2"
},
{
"role": "user",
"content": "You pick up the creditcard 1 from the shelf 2."
},
{
"role": "assistant",
"content": "Think: Now I need to place creditcard 1 in/on drawer 1. Let me go there.\nAct: go to drawer 1"
},
{
"role": "user",
"content": "The drawer 1 is closed."
},
{
"role": "assistant",
"content": "Think: I should open the drawer 1 to check its contents.\nAct: open drawer 1"
},
{
"role": "user",
"content": "You open the drawer 1. The drawer 1 is open. In it, you see nothing."
},
{
"role": "assistant",
"content": "Think: Now I'll set creditcard 1 down in/on drawer 1.\nAct: put creditcard 1 in/on drawer 1"
},
{
"role": "user",
"content": "You put the creditcard 1 in/on the drawer 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a creditcard in/on drawer 1.",
"room_type": "livingroom",
"difficulty": "normal",
"num_steps": 13
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a bed 1, a desk 1, a drawer 1, a drawer 2, a shelf 1, a shelf 2, a shelf 3, a shelf 4, a shelf 5, a shelf 6, a sidetable 1, a sidetable 2, a dresser 1, a safe 1, a garbagecan 1, a laundryhamper 1.\n\nYour task is to: put a keychain in/on shelf 1."
},
{
"role": "assistant",
"content": "Think: keychain might be at shelf 6. Let me go there.\nAct: go to shelf 6"
},
{
"role": "user",
"content": "On the shelf 6, you see a desklamp 1."
},
{
"role": "assistant",
"content": "Think: Not here. Moving on to dresser 1.\nAct: go to dresser 1"
},
{
"role": "user",
"content": "On the dresser 1, you see a desklamp 2."
},
{
"role": "assistant",
"content": "Think: keychain is not here. Let me check shelf 5.\nAct: go to shelf 5"
},
{
"role": "user",
"content": "On the shelf 5, you see nothing."
},
{
"role": "assistant",
"content": "Think: Not here. Moving on to laundryhamper 1.\nAct: go to laundryhamper 1"
},
{
"role": "user",
"content": "On the laundryhamper 1, you see a statue 1 and a keychain 1."
},
{
"role": "assistant",
"content": "Think: There's keychain 1 here. Let me take it.\nAct: take keychain 1 from laundryhamper 1"
},
{
"role": "user",
"content": "You pick up the keychain 1 from the laundryhamper 1."
},
{
"role": "assistant",
"content": "Think: I should bring keychain 1 to shelf 1 and place it there.\nAct: go to shelf 1"
},
{
"role": "user",
"content": "On the shelf 1, you see nothing."
},
{
"role": "assistant",
"content": "Think: Let me place keychain 1 here.\nAct: put keychain 1 in/on shelf 1"
},
{
"role": "user",
"content": "You put the keychain 1 in/on the shelf 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a keychain in/on shelf 1.",
"room_type": "bedroom",
"difficulty": "normal",
"num_steps": 15
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a countertop 1, a countertop 2, a cabinet 1, a cabinet 2, a cabinet 3, a cabinet 4, a cabinet 5, a fridge 1, a microwave 1, a sinkbasin 1, a stoveburner 1, a stoveburner 2, a drawer 1, a shelf 1, a shelf 2, a shelf 3, a shelf 4, a garbagecan 1, a toaster 1, a coffeemachine 1.\n\nYour task is to: put a dishsponge in/on fridge 1."
},
{
"role": "assistant",
"content": "Think: I should look for dishsponge. Let me start with toaster 1.\nAct: go to toaster 1"
},
{
"role": "user",
"content": "On the toaster 1, you see a pan 1."
},
{
"role": "assistant",
"content": "Think: No luck. Let me look at stoveburner 1.\nAct: go to stoveburner 1"
},
{
"role": "user",
"content": "On the stoveburner 1, you see nothing."
},
{
"role": "assistant",
"content": "Think: dishsponge is not here. Let me check cabinet 3.\nAct: go to cabinet 3"
},
{
"role": "user",
"content": "The cabinet 3 is closed."
},
{
"role": "assistant",
"content": "Think: I should open the cabinet 3 to check its contents.\nAct: open cabinet 3"
},
{
"role": "user",
"content": "You open the cabinet 3. The cabinet 3 is open. In it, you see nothing."
},
{
"role": "assistant",
"content": "Think: Not here. Moving on to microwave 1.\nAct: go to microwave 1"
},
{
"role": "user",
"content": "The microwave 1 is closed."
},
{
"role": "assistant",
"content": "Think: microwave 1 is closed. Let me open it to see what's inside.\nAct: open microwave 1"
},
{
"role": "user",
"content": "You open the microwave 1. The microwave 1 is open. In it, you see a dishsponge 1."
},
{
"role": "assistant",
"content": "Think: Found it! dishsponge 1 is on microwave 1. Let me pick it up.\nAct: take dishsponge 1 from microwave 1"
},
{
"role": "user",
"content": "You pick up the dishsponge 1 from the microwave 1."
},
{
"role": "assistant",
"content": "Think: Final step: put dishsponge 1 in/on fridge 1.\nAct: go to fridge 1"
},
{
"role": "user",
"content": "The fridge 1 is closed."
},
{
"role": "assistant",
"content": "Think: fridge 1 is closed. Let me open it to see what's inside.\nAct: open fridge 1"
},
{
"role": "user",
"content": "You open the fridge 1. The fridge 1 is open. In it, you see a cup 2."
},
{
"role": "assistant",
"content": "Think: I'll put dishsponge 1 in/on fridge 1 now.\nAct: put dishsponge 1 in/on fridge 1"
},
{
"role": "user",
"content": "You put the dishsponge 1 in/on the fridge 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a dishsponge in/on fridge 1.",
"room_type": "kitchen",
"difficulty": "hard",
"num_steps": 21
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a countertop 1, a countertop 2, a cabinet 1, a cabinet 2, a cabinet 3, a cabinet 4, a fridge 1, a microwave 1, a sinkbasin 1, a stoveburner 1, a stoveburner 2, a drawer 1, a drawer 2, a drawer 3, a drawer 4, a drawer 5, a shelf 1, a shelf 2, a shelf 3, a shelf 4, a shelf 5, a shelf 6, a garbagecan 1, a toaster 1, a coffeemachine 1.\n\nYour task is to: put a bowl in/on shelf 1."
},
{
"role": "assistant",
"content": "Think: bowl might be at shelf 1. Let me go there.\nAct: go to shelf 1"
},
{
"role": "user",
"content": "On the shelf 1, you see a tomato 1."
},
{
"role": "assistant",
"content": "Think: I didn't find bowl. cabinet 1 might have it.\nAct: go to cabinet 1"
},
{
"role": "user",
"content": "On the cabinet 1, you see nothing."
},
{
"role": "assistant",
"content": "Think: I don't see bowl here. I'll try cabinet 2 next.\nAct: go to cabinet 2"
},
{
"role": "user",
"content": "The cabinet 2 is open. In it, you see a bowl 1."
},
{
"role": "assistant",
"content": "Think: There's bowl 1 here. Let me take it.\nAct: take bowl 1 from cabinet 2"
},
{
"role": "user",
"content": "You pick up the bowl 1 from the cabinet 2."
},
{
"role": "assistant",
"content": "Think: Now I'll go to shelf 1 to put bowl 1 down.\nAct: go to shelf 1"
},
{
"role": "user",
"content": "On the shelf 1, you see a tomato 1."
},
{
"role": "assistant",
"content": "Think: Let me place bowl 1 here.\nAct: put bowl 1 in/on shelf 1"
},
{
"role": "user",
"content": "You put the bowl 1 in/on the shelf 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a bowl in/on shelf 1.",
"room_type": "kitchen",
"difficulty": "normal",
"num_steps": 13
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a countertop 1, a countertop 2, a cabinet 1, a fridge 1, a microwave 1, a sinkbasin 1, a stoveburner 1, a drawer 1, a drawer 2, a drawer 3, a drawer 4, a drawer 5, a shelf 1, a garbagecan 1, a toaster 1, a coffeemachine 1.\n\nYour task is to: put a cup in/on cabinet 1."
},
{
"role": "assistant",
"content": "Think: First, I should locate cup. drawer 4 seems like a good place to look.\nAct: go to drawer 4"
},
{
"role": "user",
"content": "The drawer 4 appears to be empty."
},
{
"role": "assistant",
"content": "Think: No luck. Let me look at garbagecan 1.\nAct: go to garbagecan 1"
},
{
"role": "user",
"content": "On the garbagecan 1, you see a saltshaker 1 and a spoon 2."
},
{
"role": "assistant",
"content": "Think: No luck. Let me look at coffeemachine 1.\nAct: go to coffeemachine 1"
},
{
"role": "user",
"content": "The coffeemachine 1 appears to be empty."
},
{
"role": "assistant",
"content": "Think: cup wasn't there. Let me try countertop 1.\nAct: go to countertop 1"
},
{
"role": "user",
"content": "On the countertop 1, you see a cup 1."
},
{
"role": "assistant",
"content": "Think: Found it! cup 1 is on countertop 1. Let me pick it up.\nAct: take cup 1 from countertop 1"
},
{
"role": "user",
"content": "You pick up the cup 1 from the countertop 1."
},
{
"role": "assistant",
"content": "Think: I should bring cup 1 to cabinet 1 and place it there.\nAct: go to cabinet 1"
},
{
"role": "user",
"content": "The cabinet 1 is closed."
},
{
"role": "assistant",
"content": "Think: I should open the cabinet 1 to check its contents.\nAct: open cabinet 1"
},
{
"role": "user",
"content": "You open the cabinet 1. The cabinet 1 is open. In it, you see a knife 1."
},
{
"role": "assistant",
"content": "Think: Now I'll set cup 1 down in/on cabinet 1.\nAct: put cup 1 in/on cabinet 1"
},
{
"role": "user",
"content": "You put the cup 1 in/on the cabinet 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a cup in/on cabinet 1.",
"room_type": "kitchen",
"difficulty": "normal",
"num_steps": 17
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a countertop 1, a cabinet 1, a cabinet 2, a fridge 1, a microwave 1, a sinkbasin 1, a stoveburner 1, a stoveburner 2, a drawer 1, a drawer 2, a drawer 3, a shelf 1, a shelf 2, a garbagecan 1, a toaster 1, a coffeemachine 1.\n\nYour task is to: put a peppershaker in/on cabinet 1."
},
{
"role": "assistant",
"content": "Think: I should look for peppershaker. Let me start with cabinet 1.\nAct: go to cabinet 1"
},
{
"role": "user",
"content": "The cabinet 1 is closed."
},
{
"role": "assistant",
"content": "Think: The cabinet 1 is closed. I need to open it first.\nAct: open cabinet 1"
},
{
"role": "user",
"content": "You open the cabinet 1. The cabinet 1 is open. In it, you see a peppershaker 1, a spoon 1, and a cup 2."
},
{
"role": "assistant",
"content": "Think: I can see peppershaker 1 on cabinet 1. I'll grab it.\nAct: take peppershaker 1 from cabinet 1"
},
{
"role": "user",
"content": "You pick up the peppershaker 1 from the cabinet 1."
},
{
"role": "assistant",
"content": "Think: Now I need to place peppershaker 1 in/on cabinet 1. Let me go there.\nAct: go to cabinet 1"
},
{
"role": "user",
"content": "The cabinet 1 is open. In it, you see a spoon 1 and a cup 2."
},
{
"role": "assistant",
"content": "Think: I'll put peppershaker 1 in/on cabinet 1 now.\nAct: put peppershaker 1 in/on cabinet 1"
},
{
"role": "user",
"content": "You put the peppershaker 1 in/on the cabinet 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a peppershaker in/on cabinet 1.",
"room_type": "kitchen",
"difficulty": "easy",
"num_steps": 11
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a bed 1, a desk 1, a drawer 1, a drawer 2, a drawer 3, a drawer 4, a drawer 5, a shelf 1, a shelf 2, a shelf 3, a sidetable 1, a dresser 1, a safe 1, a garbagecan 1, a laundryhamper 1.\n\nYour task is to: put a cellphone in/on laundryhamper 1."
},
{
"role": "assistant",
"content": "Think: My goal requires cellphone. Let me try bed 1.\nAct: go to bed 1"
},
{
"role": "user",
"content": "On the bed 1, you see a vase 1."
},
{
"role": "assistant",
"content": "Think: Not here. Moving on to drawer 5.\nAct: go to drawer 5"
},
{
"role": "user",
"content": "The drawer 5 is open. In it, you see a creditcard 1 and a watch 2."
},
{
"role": "assistant",
"content": "Think: cellphone is not here. Let me check shelf 1.\nAct: go to shelf 1"
},
{
"role": "user",
"content": "On the shelf 1, you see nothing."
},
{
"role": "assistant",
"content": "Think: Not here. Moving on to shelf 3.\nAct: go to shelf 3"
},
{
"role": "user",
"content": "The shelf 3 appears to be empty."
},
{
"role": "assistant",
"content": "Think: I didn't find cellphone. sidetable 1 might have it.\nAct: go to sidetable 1"
},
{
"role": "user",
"content": "On the sidetable 1, you see a cd 1, a cellphone 1, and a box 1."
},
{
"role": "assistant",
"content": "Think: Found it! cellphone 1 is on sidetable 1. Let me pick it up.\nAct: take cellphone 1 from sidetable 1"
},
{
"role": "user",
"content": "You pick up the cellphone 1 from the sidetable 1."
},
{
"role": "assistant",
"content": "Think: Now I need to place cellphone 1 in/on laundryhamper 1. Let me go there.\nAct: go to laundryhamper 1"
},
{
"role": "user",
"content": "On the laundryhamper 1, you see nothing."
},
{
"role": "assistant",
"content": "Think: Let me place cellphone 1 here.\nAct: put cellphone 1 in/on laundryhamper 1"
},
{
"role": "user",
"content": "You put the cellphone 1 in/on the laundryhamper 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a cellphone in/on laundryhamper 1.",
"room_type": "bedroom",
"difficulty": "hard",
"num_steps": 17
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a bed 1, a desk 1, a drawer 1, a drawer 2, a drawer 3, a drawer 4, a drawer 5, a shelf 1, a shelf 2, a shelf 3, a shelf 4, a sidetable 1, a dresser 1, a safe 1, a garbagecan 1, a laundryhamper 1.\n\nYour task is to: put a watch in/on desk 1."
},
{
"role": "assistant",
"content": "Think: To complete this task, I need watch. I'll search shelf 1.\nAct: go to shelf 1"
},
{
"role": "user",
"content": "On the shelf 1, you see a vase 2 and a watch 1."
},
{
"role": "assistant",
"content": "Think: There's watch 1 here. Let me take it.\nAct: take watch 1 from shelf 1"
},
{
"role": "user",
"content": "You pick up the watch 1 from the shelf 1."
},
{
"role": "assistant",
"content": "Think: Now I need to place watch 1 in/on desk 1. Let me go there.\nAct: go to desk 1"
},
{
"role": "user",
"content": "On the desk 1, you see a keychain 2."
},
{
"role": "assistant",
"content": "Think: I'll put watch 1 in/on desk 1 now.\nAct: put watch 1 in/on desk 1"
},
{
"role": "user",
"content": "You put the watch 1 in/on the desk 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a watch in/on desk 1.",
"room_type": "bedroom",
"difficulty": "easy",
"num_steps": 9
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a bed 1, a desk 1, a drawer 1, a drawer 2, a shelf 1, a shelf 2, a shelf 3, a shelf 4, a shelf 5, a sidetable 1, a sidetable 2, a dresser 1, a safe 1, a garbagecan 1, a laundryhamper 1.\n\nYour task is to: put a laptop in/on sidetable 1."
},
{
"role": "assistant",
"content": "Think: I should look for laptop. Let me start with shelf 5.\nAct: go to shelf 5"
},
{
"role": "user",
"content": "On the shelf 5, you see a box 1 and a pillow 1."
},
{
"role": "assistant",
"content": "Think: Not here. Moving on to shelf 1.\nAct: go to shelf 1"
},
{
"role": "user",
"content": "On the shelf 1, you see a laptop 1 and a watch 1."
},
{
"role": "assistant",
"content": "Think: Found it! laptop 1 is on shelf 1. Let me pick it up.\nAct: take laptop 1 from shelf 1"
},
{
"role": "user",
"content": "You pick up the laptop 1 from the shelf 1."
},
{
"role": "assistant",
"content": "Think: I should bring laptop 1 to sidetable 1 and place it there.\nAct: go to sidetable 1"
},
{
"role": "user",
"content": "On the sidetable 1, you see a pen 1."
},
{
"role": "assistant",
"content": "Think: Now I'll set laptop 1 down in/on sidetable 1.\nAct: put laptop 1 in/on sidetable 1"
},
{
"role": "user",
"content": "You put the laptop 1 in/on the sidetable 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a laptop in/on sidetable 1.",
"room_type": "bedroom",
"difficulty": "normal",
"num_steps": 11
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a sofa 1, a coffeetable 1, a sidetable 1, a sidetable 2, a shelf 1, a shelf 2, a drawer 1, a drawer 2, a drawer 3, a drawer 4, a dresser 1, a armchair 1, a desk 1, a garbagecan 1, a safe 1.\n\nYour task is to: put a laptop in/on coffeetable 1."
},
{
"role": "assistant",
"content": "Think: First, I should locate laptop. desk 1 seems like a good place to look.\nAct: go to desk 1"
},
{
"role": "user",
"content": "On the desk 1, you see a newspaper 3."
},
{
"role": "assistant",
"content": "Think: I didn't find laptop. drawer 1 might have it.\nAct: go to drawer 1"
},
{
"role": "user",
"content": "The drawer 1 is closed."
},
{
"role": "assistant",
"content": "Think: I should open the drawer 1 to check its contents.\nAct: open drawer 1"
},
{
"role": "user",
"content": "You open the drawer 1. The drawer 1 is open. In it, you see a remotecontrol 1."
},
{
"role": "assistant",
"content": "Think: laptop wasn't there. Let me try dresser 1.\nAct: go to dresser 1"
},
{
"role": "user",
"content": "On the dresser 1, you see a candle 4."
},
{
"role": "assistant",
"content": "Think: laptop is not here. Let me check shelf 1.\nAct: go to shelf 1"
},
{
"role": "user",
"content": "The shelf 1 appears to be empty."
},
{
"role": "assistant",
"content": "Think: laptop wasn't there. Let me try sofa 1.\nAct: go to sofa 1"
},
{
"role": "user",
"content": "On the sofa 1, you see a statue 3, a candle 5, and a floorlamp 1."
},
{
"role": "assistant",
"content": "Think: laptop is not here. Let me check coffeetable 1.\nAct: go to coffeetable 1"
},
{
"role": "user",
"content": "On the coffeetable 1, you see a keychain 1."
},
{
"role": "assistant",
"content": "Think: I don't see laptop here. I'll try shelf 2 next.\nAct: go to shelf 2"
},
{
"role": "user",
"content": "On the shelf 2, you see a laptop 1."
},
{
"role": "assistant",
"content": "Think: Found it! laptop 1 is on shelf 2. Let me pick it up.\nAct: take laptop 1 from shelf 2"
},
{
"role": "user",
"content": "You pick up the laptop 1 from the shelf 2."
},
{
"role": "assistant",
"content": "Think: Now I'll go to coffeetable 1 to put laptop 1 down.\nAct: go to coffeetable 1"
},
{
"role": "user",
"content": "On the coffeetable 1, you see a keychain 1."
},
{
"role": "assistant",
"content": "Think: Now I'll set laptop 1 down in/on coffeetable 1.\nAct: put laptop 1 in/on coffeetable 1"
},
{
"role": "user",
"content": "You put the laptop 1 in/on the coffeetable 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a laptop in/on coffeetable 1.",
"room_type": "livingroom",
"difficulty": "hard",
"num_steps": 23
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a sofa 1, a coffeetable 1, a sidetable 1, a shelf 1, a shelf 2, a shelf 3, a shelf 4, a shelf 5, a drawer 1, a drawer 2, a drawer 3, a drawer 4, a drawer 5, a drawer 6, a dresser 1, a armchair 1, a desk 1, a garbagecan 1, a safe 1.\n\nYour task is to: put a creditcard in/on sidetable 1."
},
{
"role": "assistant",
"content": "Think: To complete this task, I need creditcard. I'll search desk 1.\nAct: go to desk 1"
},
{
"role": "user",
"content": "On the desk 1, you see a box 1 and a watch 1."
},
{
"role": "assistant",
"content": "Think: No luck. Let me look at sidetable 1.\nAct: go to sidetable 1"
},
{
"role": "user",
"content": "On the sidetable 1, you see a pen 1 and a desklamp 1."
},
{
"role": "assistant",
"content": "Think: Not here. Moving on to safe 1.\nAct: go to safe 1"
},
{
"role": "user",
"content": "The safe 1 appears to be empty."
},
{
"role": "assistant",
"content": "Think: I didn't find creditcard. drawer 5 might have it.\nAct: go to drawer 5"
},
{
"role": "user",
"content": "The drawer 5 is open. In it, you see a creditcard 2."
},
{
"role": "assistant",
"content": "Think: I found creditcard 2 on drawer 5. I should pick it up.\nAct: take creditcard 2 from drawer 5"
},
{
"role": "user",
"content": "You pick up the creditcard 2 from the drawer 5."
},
{
"role": "assistant",
"content": "Think: Time to put creditcard 2 in/on sidetable 1.\nAct: go to sidetable 1"
},
{
"role": "user",
"content": "On the sidetable 1, you see a pen 1 and a desklamp 1."
},
{
"role": "assistant",
"content": "Think: Let me place creditcard 2 here.\nAct: put creditcard 2 in/on sidetable 1"
},
{
"role": "user",
"content": "You put the creditcard 2 in/on the sidetable 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a creditcard in/on sidetable 1.",
"room_type": "livingroom",
"difficulty": "normal",
"num_steps": 15
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a sofa 1, a coffeetable 1, a sidetable 1, a sidetable 2, a shelf 1, a shelf 2, a shelf 3, a shelf 4, a drawer 1, a drawer 2, a drawer 3, a drawer 4, a dresser 1, a armchair 1, a desk 1, a garbagecan 1, a safe 1.\n\nYour task is to: put a candle in/on drawer 1."
},
{
"role": "assistant",
"content": "Think: To complete this task, I need candle. I'll search sidetable 1.\nAct: go to sidetable 1"
},
{
"role": "user",
"content": "On the sidetable 1, you see a tissuebox 1 and a statue 1."
},
{
"role": "assistant",
"content": "Think: Not here. Moving on to shelf 2.\nAct: go to shelf 2"
},
{
"role": "user",
"content": "On the shelf 2, you see a newspaper 2 and a pen 1."
},
{
"role": "assistant",
"content": "Think: candle is not here. Let me check dresser 1.\nAct: go to dresser 1"
},
{
"role": "user",
"content": "On the dresser 1, you see a keychain 1, a pencil 3, and a candle 1."
},
{
"role": "assistant",
"content": "Think: Found it! candle 1 is on dresser 1. Let me pick it up.\nAct: take candle 1 from dresser 1"
},
{
"role": "user",
"content": "You pick up the candle 1 from the dresser 1."
},
{
"role": "assistant",
"content": "Think: Now I'll go to drawer 1 to put candle 1 down.\nAct: go to drawer 1"
},
{
"role": "user",
"content": "The drawer 1 is closed."
},
{
"role": "assistant",
"content": "Think: The drawer 1 is closed. I need to open it first.\nAct: open drawer 1"
},
{
"role": "user",
"content": "You open the drawer 1. The drawer 1 is open. In it, you see a book 1."
},
{
"role": "assistant",
"content": "Think: Now I'll set candle 1 down in/on drawer 1.\nAct: put candle 1 in/on drawer 1"
},
{
"role": "user",
"content": "You put the candle 1 in/on the drawer 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a candle in/on drawer 1.",
"room_type": "livingroom",
"difficulty": "normal",
"num_steps": 15
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a sofa 1, a coffeetable 1, a sidetable 1, a shelf 1, a drawer 1, a drawer 2, a drawer 3, a dresser 1, a armchair 1, a desk 1, a garbagecan 1, a safe 1.\n\nYour task is to: put a pillow in/on sofa 1."
},
{
"role": "assistant",
"content": "Think: First, I should locate pillow. armchair 1 seems like a good place to look.\nAct: go to armchair 1"
},
{
"role": "user",
"content": "On the armchair 1, you see a cellphone 1."
},
{
"role": "assistant",
"content": "Think: Not here. Moving on to safe 1.\nAct: go to safe 1"
},
{
"role": "user",
"content": "The safe 1 is open. In it, you see a tissuebox 3 and a statue 1."
},
{
"role": "assistant",
"content": "Think: pillow wasn't there. Let me try sofa 1.\nAct: go to sofa 1"
},
{
"role": "user",
"content": "On the sofa 1, you see nothing."
},
{
"role": "assistant",
"content": "Think: Not here. Moving on to shelf 1.\nAct: go to shelf 1"
},
{
"role": "user",
"content": "On the shelf 1, you see a candle 1, a pen 1, and a pillow 1."
},
{
"role": "assistant",
"content": "Think: Found it! pillow 1 is on shelf 1. Let me pick it up.\nAct: take pillow 1 from shelf 1"
},
{
"role": "user",
"content": "You pick up the pillow 1 from the shelf 1."
},
{
"role": "assistant",
"content": "Think: Final step: put pillow 1 in/on sofa 1.\nAct: go to sofa 1"
},
{
"role": "user",
"content": "On the sofa 1, you see nothing."
},
{
"role": "assistant",
"content": "Think: I'll put pillow 1 in/on sofa 1 now.\nAct: put pillow 1 in/on sofa 1"
},
{
"role": "user",
"content": "You put the pillow 1 in/on the sofa 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a pillow in/on sofa 1.",
"room_type": "livingroom",
"difficulty": "normal",
"num_steps": 15
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a bed 1, a desk 1, a drawer 1, a shelf 1, a sidetable 1, a sidetable 2, a dresser 1, a safe 1, a garbagecan 1, a laundryhamper 1.\n\nYour task is to: put a cellphone in/on sidetable 1."
},
{
"role": "assistant",
"content": "Think: I should look for cellphone. Let me start with desk 1.\nAct: go to desk 1"
},
{
"role": "user",
"content": "On the desk 1, you see a cd 1, a watch 1, and a book 1."
},
{
"role": "assistant",
"content": "Think: I don't see cellphone here. I'll try shelf 1 next.\nAct: go to shelf 1"
},
{
"role": "user",
"content": "The shelf 1 appears to be empty."
},
{
"role": "assistant",
"content": "Think: I didn't find cellphone. safe 1 might have it.\nAct: go to safe 1"
},
{
"role": "user",
"content": "The safe 1 appears to be empty."
},
{
"role": "assistant",
"content": "Think: cellphone wasn't there. Let me try bed 1.\nAct: go to bed 1"
},
{
"role": "user",
"content": "The bed 1 appears to be empty."
},
{
"role": "assistant",
"content": "Think: No luck. Let me look at garbagecan 1.\nAct: go to garbagecan 1"
},
{
"role": "user",
"content": "On the garbagecan 1, you see a statue 1 and a box 1."
},
{
"role": "assistant",
"content": "Think: No luck. Let me look at sidetable 2.\nAct: go to sidetable 2"
},
{
"role": "user",
"content": "The sidetable 2 appears to be empty."
},
{
"role": "assistant",
"content": "Think: I don't see cellphone here. I'll try dresser 1 next.\nAct: go to dresser 1"
},
{
"role": "user",
"content": "On the dresser 1, you see a cellphone 1, a desklamp 1, and a floorlamp 1."
},
{
"role": "assistant",
"content": "Think: Found it! cellphone 1 is on dresser 1. Let me pick it up.\nAct: take cellphone 1 from dresser 1"
},
{
"role": "user",
"content": "You pick up the cellphone 1 from the dresser 1."
},
{
"role": "assistant",
"content": "Think: Now I'll go to sidetable 1 to put cellphone 1 down.\nAct: go to sidetable 1"
},
{
"role": "user",
"content": "On the sidetable 1, you see a book 2."
},
{
"role": "assistant",
"content": "Think: I'll put cellphone 1 in/on sidetable 1 now.\nAct: put cellphone 1 in/on sidetable 1"
},
{
"role": "user",
"content": "You put the cellphone 1 in/on the sidetable 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a cellphone in/on sidetable 1.",
"room_type": "bedroom",
"difficulty": "hard",
"num_steps": 21
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a sofa 1, a coffeetable 1, a sidetable 1, a shelf 1, a shelf 2, a shelf 3, a shelf 4, a shelf 5, a shelf 6, a drawer 1, a drawer 2, a drawer 3, a drawer 4, a drawer 5, a dresser 1, a armchair 1, a desk 1, a garbagecan 1, a safe 1.\n\nYour task is to: put a watch in/on safe 1."
},
{
"role": "assistant",
"content": "Think: watch might be at shelf 6. Let me go there.\nAct: go to shelf 6"
},
{
"role": "user",
"content": "The shelf 6 appears to be empty."
},
{
"role": "assistant",
"content": "Think: watch is not here. Let me check drawer 5.\nAct: go to drawer 5"
},
{
"role": "user",
"content": "The drawer 5 is closed."
},
{
"role": "assistant",
"content": "Think: drawer 5 is closed. Let me open it to see what's inside.\nAct: open drawer 5"
},
{
"role": "user",
"content": "You open the drawer 5. The drawer 5 is open. In it, you see a vase 1 and a creditcard 2."
},
{
"role": "assistant",
"content": "Think: I didn't find watch. drawer 2 might have it.\nAct: go to drawer 2"
},
{
"role": "user",
"content": "The drawer 2 appears to be empty."
},
{
"role": "assistant",
"content": "Think: watch wasn't there. Let me try desk 1.\nAct: go to desk 1"
},
{
"role": "user",
"content": "On the desk 1, you see a watch 1."
},
{
"role": "assistant",
"content": "Think: Found it! watch 1 is on desk 1. Let me pick it up.\nAct: take watch 1 from desk 1"
},
{
"role": "user",
"content": "You pick up the watch 1 from the desk 1."
},
{
"role": "assistant",
"content": "Think: Time to put watch 1 in/on safe 1.\nAct: go to safe 1"
},
{
"role": "user",
"content": "The safe 1 is closed."
},
{
"role": "assistant",
"content": "Think: safe 1 is closed. Let me open it to see what's inside.\nAct: open safe 1"
},
{
"role": "user",
"content": "You open the safe 1. The safe 1 is open. In it, you see nothing."
},
{
"role": "assistant",
"content": "Think: Now I'll set watch 1 down in/on safe 1.\nAct: put watch 1 in/on safe 1"
},
{
"role": "user",
"content": "You put the watch 1 in/on the safe 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a watch in/on safe 1.",
"room_type": "livingroom",
"difficulty": "hard",
"num_steps": 19
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a sofa 1, a coffeetable 1, a sidetable 1, a sidetable 2, a shelf 1, a shelf 2, a shelf 3, a shelf 4, a drawer 1, a drawer 2, a drawer 3, a drawer 4, a drawer 5, a drawer 6, a dresser 1, a armchair 1, a desk 1, a garbagecan 1, a safe 1.\n\nYour task is to: put a cellphone in/on dresser 1."
},
{
"role": "assistant",
"content": "Think: I should look for cellphone. Let me start with drawer 3.\nAct: go to drawer 3"
},
{
"role": "user",
"content": "The drawer 3 is closed."
},
{
"role": "assistant",
"content": "Think: The drawer 3 is closed. I need to open it first.\nAct: open drawer 3"
},
{
"role": "user",
"content": "You open the drawer 3. The drawer 3 is open. In it, you see a keychain 1."
},
{
"role": "assistant",
"content": "Think: cellphone wasn't there. Let me try shelf 3.\nAct: go to shelf 3"
},
{
"role": "user",
"content": "The shelf 3 appears to be empty."
},
{
"role": "assistant",
"content": "Think: I don't see cellphone here. I'll try garbagecan 1 next.\nAct: go to garbagecan 1"
},
{
"role": "user",
"content": "On the garbagecan 1, you see a vase 1 and a cellphone 1."
},
{
"role": "assistant",
"content": "Think: Found it! cellphone 1 is on garbagecan 1. Let me pick it up.\nAct: take cellphone 1 from garbagecan 1"
},
{
"role": "user",
"content": "You pick up the cellphone 1 from the garbagecan 1."
},
{
"role": "assistant",
"content": "Think: Now I need to place cellphone 1 in/on dresser 1. Let me go there.\nAct: go to dresser 1"
},
{
"role": "user",
"content": "On the dresser 1, you see a remotecontrol 1 and a watch 2."
},
{
"role": "assistant",
"content": "Think: Let me place cellphone 1 here.\nAct: put cellphone 1 in/on dresser 1"
},
{
"role": "user",
"content": "You put the cellphone 1 in/on the dresser 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a cellphone in/on dresser 1.",
"room_type": "livingroom",
"difficulty": "normal",
"num_steps": 15
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a sofa 1, a coffeetable 1, a sidetable 1, a sidetable 2, a shelf 1, a drawer 1, a drawer 2, a drawer 3, a drawer 4, a dresser 1, a armchair 1, a desk 1, a garbagecan 1, a safe 1.\n\nYour task is to: put a tissuebox in/on armchair 1."
},
{
"role": "assistant",
"content": "Think: My goal requires tissuebox. Let me try garbagecan 1.\nAct: go to garbagecan 1"
},
{
"role": "user",
"content": "On the garbagecan 1, you see a newspaper 1, a tissuebox 1, a pencil 1, and a laptop 1."
},
{
"role": "assistant",
"content": "Think: I found tissuebox 1 on garbagecan 1. I should pick it up.\nAct: take tissuebox 1 from garbagecan 1"
},
{
"role": "user",
"content": "You pick up the tissuebox 1 from the garbagecan 1."
},
{
"role": "assistant",
"content": "Think: Time to put tissuebox 1 in/on armchair 1.\nAct: go to armchair 1"
},
{
"role": "user",
"content": "On the armchair 1, you see a keychain 1."
},
{
"role": "assistant",
"content": "Think: Now I'll set tissuebox 1 down in/on armchair 1.\nAct: put tissuebox 1 in/on armchair 1"
},
{
"role": "user",
"content": "You put the tissuebox 1 in/on the armchair 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a tissuebox in/on armchair 1.",
"room_type": "livingroom",
"difficulty": "easy",
"num_steps": 9
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a sinkbasin 1, a toilet 1, a bathtubbasin 1, a cabinet 1, a cabinet 2, a cabinet 3, a cabinet 4, a cabinet 5, a cabinet 6, a countertop 1, a shelf 1, a shelf 2, a shelf 3, a towelholder 1, a garbagecan 1, a drawer 1, a drawer 2, a drawer 3.\n\nYour task is to: put a soapbottle in/on garbagecan 1."
},
{
"role": "assistant",
"content": "Think: First, I should locate soapbottle. drawer 1 seems like a good place to look.\nAct: go to drawer 1"
},
{
"role": "user",
"content": "The drawer 1 is closed."
},
{
"role": "assistant",
"content": "Think: drawer 1 is closed. Let me open it to see what's inside.\nAct: open drawer 1"
},
{
"role": "user",
"content": "You open the drawer 1. The drawer 1 is open. In it, you see nothing."
},
{
"role": "assistant",
"content": "Think: I didn't find soapbottle. toilet 1 might have it.\nAct: go to toilet 1"
},
{
"role": "user",
"content": "The toilet 1 is clean."
},
{
"role": "assistant",
"content": "Think: I don't see soapbottle here. I'll try shelf 3 next.\nAct: go to shelf 3"
},
{
"role": "user",
"content": "On the shelf 3, you see a toiletpaper 1 and a plunger 2."
},
{
"role": "assistant",
"content": "Think: soapbottle is not here. Let me check sinkbasin 1.\nAct: go to sinkbasin 1"
},
{
"role": "user",
"content": "On the sinkbasin 1, you see a soapbottle 1 and a plunger 3."
},
{
"role": "assistant",
"content": "Think: Found it! soapbottle 1 is on sinkbasin 1. Let me pick it up.\nAct: take soapbottle 1 from sinkbasin 1"
},
{
"role": "user",
"content": "You pick up the soapbottle 1 from the sinkbasin 1."
},
{
"role": "assistant",
"content": "Think: I should bring soapbottle 1 to garbagecan 1 and place it there.\nAct: go to garbagecan 1"
},
{
"role": "user",
"content": "On the garbagecan 1, you see a plunger 1 and a toiletpaper 3."
},
{
"role": "assistant",
"content": "Think: Let me place soapbottle 1 here.\nAct: put soapbottle 1 in/on garbagecan 1"
},
{
"role": "user",
"content": "You put the soapbottle 1 in/on the garbagecan 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a soapbottle in/on garbagecan 1.",
"room_type": "bathroom",
"difficulty": "normal",
"num_steps": 17
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a sofa 1, a coffeetable 1, a sidetable 1, a shelf 1, a shelf 2, a shelf 3, a drawer 1, a drawer 2, a drawer 3, a drawer 4, a drawer 5, a drawer 6, a dresser 1, a armchair 1, a desk 1, a garbagecan 1, a safe 1.\n\nYour task is to: put a book in/on dresser 1."
},
{
"role": "assistant",
"content": "Think: book might be at safe 1. Let me go there.\nAct: go to safe 1"
},
{
"role": "user",
"content": "The safe 1 is closed."
},
{
"role": "assistant",
"content": "Think: The safe 1 is closed. I need to open it first.\nAct: open safe 1"
},
{
"role": "user",
"content": "You open the safe 1. The safe 1 is open. In it, you see nothing."
},
{
"role": "assistant",
"content": "Think: book wasn't there. Let me try desk 1.\nAct: go to desk 1"
},
{
"role": "user",
"content": "On the desk 1, you see nothing."
},
{
"role": "assistant",
"content": "Think: I don't see book here. I'll try shelf 2 next.\nAct: go to shelf 2"
},
{
"role": "user",
"content": "On the shelf 2, you see a book 1, a cellphone 1, a pen 1, and a floorlamp 1."
},
{
"role": "assistant",
"content": "Think: I can see book 1 on shelf 2. I'll grab it.\nAct: take book 1 from shelf 2"
},
{
"role": "user",
"content": "You pick up the book 1 from the shelf 2."
},
{
"role": "assistant",
"content": "Think: Time to put book 1 in/on dresser 1.\nAct: go to dresser 1"
},
{
"role": "user",
"content": "On the dresser 1, you see a statue 1."
},
{
"role": "assistant",
"content": "Think: Now I'll set book 1 down in/on dresser 1.\nAct: put book 1 in/on dresser 1"
},
{
"role": "user",
"content": "You put the book 1 in/on the dresser 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a book in/on dresser 1.",
"room_type": "livingroom",
"difficulty": "normal",
"num_steps": 15
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a countertop 1, a cabinet 1, a cabinet 2, a cabinet 3, a cabinet 4, a fridge 1, a microwave 1, a sinkbasin 1, a stoveburner 1, a stoveburner 2, a drawer 1, a drawer 2, a drawer 3, a drawer 4, a shelf 1, a shelf 2, a shelf 3, a shelf 4, a shelf 5, a shelf 6, a garbagecan 1, a toaster 1, a coffeemachine 1.\n\nYour task is to: put a fork in/on cabinet 1."
},
{
"role": "assistant",
"content": "Think: I need to find fork. Let me check microwave 1.\nAct: go to microwave 1"
},
{
"role": "user",
"content": "The microwave 1 is open. In it, you see a dishsponge 1 and a cup 1."
},
{
"role": "assistant",
"content": "Think: fork is not here. Let me check drawer 1.\nAct: go to drawer 1"
},
{
"role": "user",
"content": "The drawer 1 is closed."
},
{
"role": "assistant",
"content": "Think: drawer 1 is closed. Let me open it to see what's inside.\nAct: open drawer 1"
},
{
"role": "user",
"content": "You open the drawer 1. The drawer 1 is open. In it, you see nothing."
},
{
"role": "assistant",
"content": "Think: fork is not here. Let me check cabinet 3.\nAct: go to cabinet 3"
},
{
"role": "user",
"content": "The cabinet 3 is closed."
},
{
"role": "assistant",
"content": "Think: cabinet 3 is closed. Let me open it to see what's inside.\nAct: open cabinet 3"
},
{
"role": "user",
"content": "You open the cabinet 3. The cabinet 3 is open. In it, you see a butterknife 1, a soapbottle 1, a fork 1, and a spoon 3."
},
{
"role": "assistant",
"content": "Think: I can see fork 1 on cabinet 3. I'll grab it.\nAct: take fork 1 from cabinet 3"
},
{
"role": "user",
"content": "You pick up the fork 1 from the cabinet 3."
},
{
"role": "assistant",
"content": "Think: I should bring fork 1 to cabinet 1 and place it there.\nAct: go to cabinet 1"
},
{
"role": "user",
"content": "The cabinet 1 is closed."
},
{
"role": "assistant",
"content": "Think: cabinet 1 is closed. Let me open it to see what's inside.\nAct: open cabinet 1"
},
{
"role": "user",
"content": "You open the cabinet 1. The cabinet 1 is open. In it, you see a pan 1."
},
{
"role": "assistant",
"content": "Think: I'll put fork 1 in/on cabinet 1 now.\nAct: put fork 1 in/on cabinet 1"
},
{
"role": "user",
"content": "You put the fork 1 in/on the cabinet 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a fork in/on cabinet 1.",
"room_type": "kitchen",
"difficulty": "normal",
"num_steps": 19
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a bed 1, a desk 1, a drawer 1, a drawer 2, a shelf 1, a shelf 2, a sidetable 1, a dresser 1, a safe 1, a garbagecan 1, a laundryhamper 1.\n\nYour task is to: put a watch in/on drawer 1."
},
{
"role": "assistant",
"content": "Think: watch might be at drawer 1. Let me go there.\nAct: go to drawer 1"
},
{
"role": "user",
"content": "The drawer 1 is closed."
},
{
"role": "assistant",
"content": "Think: The drawer 1 is closed. I need to open it first.\nAct: open drawer 1"
},
{
"role": "user",
"content": "You open the drawer 1. The drawer 1 is open. In it, you see a alarmclock 1, a cd 1, and a creditcard 1."
},
{
"role": "assistant",
"content": "Think: I don't see watch here. I'll try dresser 1 next.\nAct: go to dresser 1"
},
{
"role": "user",
"content": "On the dresser 1, you see a tissuebox 1."
},
{
"role": "assistant",
"content": "Think: No luck. Let me look at shelf 1.\nAct: go to shelf 1"
},
{
"role": "user",
"content": "On the shelf 1, you see a desklamp 1."
},
{
"role": "assistant",
"content": "Think: I didn't find watch. safe 1 might have it.\nAct: go to safe 1"
},
{
"role": "user",
"content": "The safe 1 is closed."
},
{
"role": "assistant",
"content": "Think: safe 1 is closed. Let me open it to see what's inside.\nAct: open safe 1"
},
{
"role": "user",
"content": "You open the safe 1. The safe 1 is open. In it, you see a pillow 1."
},
{
"role": "assistant",
"content": "Think: No luck. Let me look at bed 1.\nAct: go to bed 1"
},
{
"role": "user",
"content": "On the bed 1, you see a watch 1."
},
{
"role": "assistant",
"content": "Think: I can see watch 1 on bed 1. I'll grab it.\nAct: take watch 1 from bed 1"
},
{
"role": "user",
"content": "You pick up the watch 1 from the bed 1."
},
{
"role": "assistant",
"content": "Think: Now I need to place watch 1 in/on drawer 1. Let me go there.\nAct: go to drawer 1"
},
{
"role": "user",
"content": "The drawer 1 is open. In it, you see a alarmclock 1, a cd 1, and a creditcard 1."
},
{
"role": "assistant",
"content": "Think: Let me place watch 1 here.\nAct: put watch 1 in/on drawer 1"
},
{
"role": "user",
"content": "You put the watch 1 in/on the drawer 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a watch in/on drawer 1.",
"room_type": "bedroom",
"difficulty": "hard",
"num_steps": 21
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a sinkbasin 1, a toilet 1, a bathtubbasin 1, a cabinet 1, a cabinet 2, a cabinet 3, a cabinet 4, a cabinet 5, a cabinet 6, a countertop 1, a countertop 2, a shelf 1, a shelf 2, a shelf 3, a shelf 4, a shelf 5, a shelf 6, a towelholder 1, a garbagecan 1, a drawer 1, a drawer 2, a drawer 3, a drawer 4.\n\nYour task is to: put a candle in/on bathtubbasin 1."
},
{
"role": "assistant",
"content": "Think: To complete this task, I need candle. I'll search shelf 1.\nAct: go to shelf 1"
},
{
"role": "user",
"content": "On the shelf 1, you see nothing."
},
{
"role": "assistant",
"content": "Think: No luck. Let me look at drawer 1.\nAct: go to drawer 1"
},
{
"role": "user",
"content": "The drawer 1 appears to be empty."
},
{
"role": "assistant",
"content": "Think: candle is not here. Let me check countertop 1.\nAct: go to countertop 1"
},
{
"role": "user",
"content": "On the countertop 1, you see nothing."
},
{
"role": "assistant",
"content": "Think: No luck. Let me look at shelf 4.\nAct: go to shelf 4"
},
{
"role": "user",
"content": "On the shelf 4, you see a tissuebox 4."
},
{
"role": "assistant",
"content": "Think: candle wasn't there. Let me try cabinet 6.\nAct: go to cabinet 6"
},
{
"role": "user",
"content": "The cabinet 6 appears to be empty."
},
{
"role": "assistant",
"content": "Think: candle wasn't there. Let me try shelf 5.\nAct: go to shelf 5"
},
{
"role": "user",
"content": "On the shelf 5, you see a toiletpaper 2."
},
{
"role": "assistant",
"content": "Think: Not here. Moving on to shelf 2.\nAct: go to shelf 2"
},
{
"role": "user",
"content": "On the shelf 2, you see a candle 1."
},
{
"role": "assistant",
"content": "Think: I can see candle 1 on shelf 2. I'll grab it.\nAct: take candle 1 from shelf 2"
},
{
"role": "user",
"content": "You pick up the candle 1 from the shelf 2."
},
{
"role": "assistant",
"content": "Think: Now I need to place candle 1 in/on bathtubbasin 1. Let me go there.\nAct: go to bathtubbasin 1"
},
{
"role": "user",
"content": "On the bathtubbasin 1, you see a soapbar 1 and a cloth 1."
},
{
"role": "assistant",
"content": "Think: Now I'll set candle 1 down in/on bathtubbasin 1.\nAct: put candle 1 in/on bathtubbasin 1"
},
{
"role": "user",
"content": "You put the candle 1 in/on the bathtubbasin 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a candle in/on bathtubbasin 1.",
"room_type": "bathroom",
"difficulty": "hard",
"num_steps": 21
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a sofa 1, a coffeetable 1, a sidetable 1, a shelf 1, a shelf 2, a shelf 3, a shelf 4, a shelf 5, a shelf 6, a drawer 1, a drawer 2, a dresser 1, a armchair 1, a desk 1, a garbagecan 1, a safe 1.\n\nYour task is to: put a creditcard in/on sofa 1."
},
{
"role": "assistant",
"content": "Think: First, I should locate creditcard. armchair 1 seems like a good place to look.\nAct: go to armchair 1"
},
{
"role": "user",
"content": "On the armchair 1, you see a newspaper 1."
},
{
"role": "assistant",
"content": "Think: creditcard wasn't there. Let me try shelf 6.\nAct: go to shelf 6"
},
{
"role": "user",
"content": "The shelf 6 appears to be empty."
},
{
"role": "assistant",
"content": "Think: I don't see creditcard here. I'll try shelf 3 next.\nAct: go to shelf 3"
},
{
"role": "user",
"content": "On the shelf 3, you see a cellphone 1."
},
{
"role": "assistant",
"content": "Think: I didn't find creditcard. sidetable 1 might have it.\nAct: go to sidetable 1"
},
{
"role": "user",
"content": "On the sidetable 1, you see a creditcard 1 and a pillow 1."
},
{
"role": "assistant",
"content": "Think: There's creditcard 1 here. Let me take it.\nAct: take creditcard 1 from sidetable 1"
},
{
"role": "user",
"content": "You pick up the creditcard 1 from the sidetable 1."
},
{
"role": "assistant",
"content": "Think: Now I'll go to sofa 1 to put creditcard 1 down.\nAct: go to sofa 1"
},
{
"role": "user",
"content": "On the sofa 1, you see a box 1 and a remotecontrol 1."
},
{
"role": "assistant",
"content": "Think: Let me place creditcard 1 here.\nAct: put creditcard 1 in/on sofa 1"
},
{
"role": "user",
"content": "You put the creditcard 1 in/on the sofa 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a creditcard in/on sofa 1.",
"room_type": "livingroom",
"difficulty": "normal",
"num_steps": 15
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a bed 1, a desk 1, a drawer 1, a drawer 2, a drawer 3, a drawer 4, a shelf 1, a sidetable 1, a dresser 1, a safe 1, a garbagecan 1, a laundryhamper 1.\n\nYour task is to: put a alarmclock in/on bed 1."
},
{
"role": "assistant",
"content": "Think: To complete this task, I need alarmclock. I'll search garbagecan 1.\nAct: go to garbagecan 1"
},
{
"role": "user",
"content": "On the garbagecan 1, you see a keychain 1."
},
{
"role": "assistant",
"content": "Think: I didn't find alarmclock. drawer 3 might have it.\nAct: go to drawer 3"
},
{
"role": "user",
"content": "The drawer 3 is closed."
},
{
"role": "assistant",
"content": "Think: The drawer 3 is closed. I need to open it first.\nAct: open drawer 3"
},
{
"role": "user",
"content": "You open the drawer 3. The drawer 3 is open. In it, you see a alarmclock 1."
},
{
"role": "assistant",
"content": "Think: I found alarmclock 1 on drawer 3. I should pick it up.\nAct: take alarmclock 1 from drawer 3"
},
{
"role": "user",
"content": "You pick up the alarmclock 1 from the drawer 3."
},
{
"role": "assistant",
"content": "Think: I should bring alarmclock 1 to bed 1 and place it there.\nAct: go to bed 1"
},
{
"role": "user",
"content": "The bed 1 appears to be empty."
},
{
"role": "assistant",
"content": "Think: Now I'll set alarmclock 1 down in/on bed 1.\nAct: put alarmclock 1 in/on bed 1"
},
{
"role": "user",
"content": "You put the alarmclock 1 in/on the bed 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a alarmclock in/on bed 1.",
"room_type": "bedroom",
"difficulty": "normal",
"num_steps": 13
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a sofa 1, a coffeetable 1, a sidetable 1, a sidetable 2, a shelf 1, a shelf 2, a shelf 3, a drawer 1, a drawer 2, a dresser 1, a armchair 1, a desk 1, a garbagecan 1, a safe 1.\n\nYour task is to: put a vase in/on shelf 1."
},
{
"role": "assistant",
"content": "Think: To complete this task, I need vase. I'll search shelf 2.\nAct: go to shelf 2"
},
{
"role": "user",
"content": "On the shelf 2, you see a remotecontrol 2 and a pillow 1."
},
{
"role": "assistant",
"content": "Think: I don't see vase here. I'll try drawer 2 next.\nAct: go to drawer 2"
},
{
"role": "user",
"content": "The drawer 2 is open. In it, you see a book 1."
},
{
"role": "assistant",
"content": "Think: Not here. Moving on to desk 1.\nAct: go to desk 1"
},
{
"role": "user",
"content": "On the desk 1, you see a watch 1."
},
{
"role": "assistant",
"content": "Think: No luck. Let me look at garbagecan 1.\nAct: go to garbagecan 1"
},
{
"role": "user",
"content": "On the garbagecan 1, you see a pen 1, a newspaper 1, a vase 1, and a candle 1."
},
{
"role": "assistant",
"content": "Think: I can see vase 1 on garbagecan 1. I'll grab it.\nAct: take vase 1 from garbagecan 1"
},
{
"role": "user",
"content": "You pick up the vase 1 from the garbagecan 1."
},
{
"role": "assistant",
"content": "Think: I should bring vase 1 to shelf 1 and place it there.\nAct: go to shelf 1"
},
{
"role": "user",
"content": "On the shelf 1, you see a tissuebox 1."
},
{
"role": "assistant",
"content": "Think: I'll put vase 1 in/on shelf 1 now.\nAct: put vase 1 in/on shelf 1"
},
{
"role": "user",
"content": "You put the vase 1 in/on the shelf 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a vase in/on shelf 1.",
"room_type": "livingroom",
"difficulty": "normal",
"num_steps": 15
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a sofa 1, a coffeetable 1, a sidetable 1, a sidetable 2, a shelf 1, a shelf 2, a drawer 1, a dresser 1, a armchair 1, a desk 1, a garbagecan 1, a safe 1.\n\nYour task is to: put a book in/on sidetable 1."
},
{
"role": "assistant",
"content": "Think: book might be at desk 1. Let me go there.\nAct: go to desk 1"
},
{
"role": "user",
"content": "On the desk 1, you see a laptop 1."
},
{
"role": "assistant",
"content": "Think: book is not here. Let me check drawer 1.\nAct: go to drawer 1"
},
{
"role": "user",
"content": "The drawer 1 is open. In it, you see a pillow 1 and a pencil 1."
},
{
"role": "assistant",
"content": "Think: No luck. Let me look at coffeetable 1.\nAct: go to coffeetable 1"
},
{
"role": "user",
"content": "On the coffeetable 1, you see a tissuebox 1, a keychain 2, and a pillow 3."
},
{
"role": "assistant",
"content": "Think: Not here. Moving on to dresser 1.\nAct: go to dresser 1"
},
{
"role": "user",
"content": "The dresser 1 appears to be empty."
},
{
"role": "assistant",
"content": "Think: book wasn't there. Let me try sofa 1.\nAct: go to sofa 1"
},
{
"role": "user",
"content": "On the sofa 1, you see a keychain 1."
},
{
"role": "assistant",
"content": "Think: No luck. Let me look at sidetable 1.\nAct: go to sidetable 1"
},
{
"role": "user",
"content": "On the sidetable 1, you see a watch 1."
},
{
"role": "assistant",
"content": "Think: I didn't find book. shelf 1 might have it.\nAct: go to shelf 1"
},
{
"role": "user",
"content": "On the shelf 1, you see a statue 1, a book 1, a book 3, and a desklamp 1."
},
{
"role": "assistant",
"content": "Think: I can see book 1 on shelf 1. I'll grab it.\nAct: take book 1 from shelf 1"
},
{
"role": "user",
"content": "You pick up the book 1 from the shelf 1."
},
{
"role": "assistant",
"content": "Think: Now I need to place book 1 in/on sidetable 1. Let me go there.\nAct: go to sidetable 1"
},
{
"role": "user",
"content": "On the sidetable 1, you see a watch 1."
},
{
"role": "assistant",
"content": "Think: Now I'll set book 1 down in/on sidetable 1.\nAct: put book 1 in/on sidetable 1"
},
{
"role": "user",
"content": "You put the book 1 in/on the sidetable 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a book in/on sidetable 1.",
"room_type": "livingroom",
"difficulty": "hard",
"num_steps": 21
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a bed 1, a desk 1, a drawer 1, a drawer 2, a drawer 3, a drawer 4, a drawer 5, a drawer 6, a shelf 1, a shelf 2, a shelf 3, a shelf 4, a shelf 5, a shelf 6, a sidetable 1, a sidetable 2, a sidetable 3, a dresser 1, a safe 1, a garbagecan 1, a laundryhamper 1.\n\nYour task is to: put a vase in/on bed 1."
},
{
"role": "assistant",
"content": "Think: I should look for vase. Let me start with drawer 6.\nAct: go to drawer 6"
},
{
"role": "user",
"content": "The drawer 6 is open. In it, you see a alarmclock 2, a book 3, and a floorlamp 1."
},
{
"role": "assistant",
"content": "Think: Not here. Moving on to drawer 1.\nAct: go to drawer 1"
},
{
"role": "user",
"content": "The drawer 1 appears to be empty."
},
{
"role": "assistant",
"content": "Think: vase is not here. Let me check sidetable 1.\nAct: go to sidetable 1"
},
{
"role": "user",
"content": "On the sidetable 1, you see nothing."
},
{
"role": "assistant",
"content": "Think: vase is not here. Let me check safe 1.\nAct: go to safe 1"
},
{
"role": "user",
"content": "The safe 1 is closed."
},
{
"role": "assistant",
"content": "Think: The safe 1 is closed. I need to open it first.\nAct: open safe 1"
},
{
"role": "user",
"content": "You open the safe 1. The safe 1 is open. In it, you see a vase 1 and a alarmclock 1."
},
{
"role": "assistant",
"content": "Think: I can see vase 1 on safe 1. I'll grab it.\nAct: take vase 1 from safe 1"
},
{
"role": "user",
"content": "You pick up the vase 1 from the safe 1."
},
{
"role": "assistant",
"content": "Think: Final step: put vase 1 in/on bed 1.\nAct: go to bed 1"
},
{
"role": "user",
"content": "On the bed 1, you see nothing."
},
{
"role": "assistant",
"content": "Think: I'll put vase 1 in/on bed 1 now.\nAct: put vase 1 in/on bed 1"
},
{
"role": "user",
"content": "You put the vase 1 in/on the bed 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a vase in/on bed 1.",
"room_type": "bedroom",
"difficulty": "normal",
"num_steps": 17
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a bed 1, a desk 1, a drawer 1, a drawer 2, a drawer 3, a shelf 1, a shelf 2, a sidetable 1, a sidetable 2, a dresser 1, a safe 1, a garbagecan 1, a laundryhamper 1.\n\nYour task is to: put a cd in/on safe 1."
},
{
"role": "assistant",
"content": "Think: cd might be at laundryhamper 1. Let me go there.\nAct: go to laundryhamper 1"
},
{
"role": "user",
"content": "On the laundryhamper 1, you see a creditcard 1 and a laptop 1."
},
{
"role": "assistant",
"content": "Think: I didn't find cd. dresser 1 might have it.\nAct: go to dresser 1"
},
{
"role": "user",
"content": "On the dresser 1, you see a floorlamp 1."
},
{
"role": "assistant",
"content": "Think: I didn't find cd. shelf 2 might have it.\nAct: go to shelf 2"
},
{
"role": "user",
"content": "On the shelf 2, you see a pen 2."
},
{
"role": "assistant",
"content": "Think: I don't see cd here. I'll try sidetable 1 next.\nAct: go to sidetable 1"
},
{
"role": "user",
"content": "On the sidetable 1, you see a pencil 1 and a cd 1."
},
{
"role": "assistant",
"content": "Think: Found it! cd 1 is on sidetable 1. Let me pick it up.\nAct: take cd 1 from sidetable 1"
},
{
"role": "user",
"content": "You pick up the cd 1 from the sidetable 1."
},
{
"role": "assistant",
"content": "Think: Now I need to place cd 1 in/on safe 1. Let me go there.\nAct: go to safe 1"
},
{
"role": "user",
"content": "The safe 1 is closed."
},
{
"role": "assistant",
"content": "Think: safe 1 is closed. Let me open it to see what's inside.\nAct: open safe 1"
},
{
"role": "user",
"content": "You open the safe 1. The safe 1 is open. In it, you see nothing."
},
{
"role": "assistant",
"content": "Think: Now I'll set cd 1 down in/on safe 1.\nAct: put cd 1 in/on safe 1"
},
{
"role": "user",
"content": "You put the cd 1 in/on the safe 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a cd in/on safe 1.",
"room_type": "bedroom",
"difficulty": "normal",
"num_steps": 17
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a sofa 1, a coffeetable 1, a sidetable 1, a sidetable 2, a shelf 1, a shelf 2, a shelf 3, a shelf 4, a shelf 5, a shelf 6, a drawer 1, a drawer 2, a drawer 3, a drawer 4, a drawer 5, a dresser 1, a armchair 1, a desk 1, a garbagecan 1, a safe 1.\n\nYour task is to: put a creditcard in/on sofa 1."
},
{
"role": "assistant",
"content": "Think: To complete this task, I need creditcard. I'll search dresser 1.\nAct: go to dresser 1"
},
{
"role": "user",
"content": "On the dresser 1, you see nothing."
},
{
"role": "assistant",
"content": "Think: I didn't find creditcard. shelf 4 might have it.\nAct: go to shelf 4"
},
{
"role": "user",
"content": "On the shelf 4, you see a remotecontrol 2."
},
{
"role": "assistant",
"content": "Think: Not here. Moving on to drawer 2.\nAct: go to drawer 2"
},
{
"role": "user",
"content": "The drawer 2 is closed."
},
{
"role": "assistant",
"content": "Think: I should open the drawer 2 to check its contents.\nAct: open drawer 2"
},
{
"role": "user",
"content": "You open the drawer 2. The drawer 2 is open. In it, you see a pillow 1 and a creditcard 1."
},
{
"role": "assistant",
"content": "Think: I can see creditcard 1 on drawer 2. I'll grab it.\nAct: take creditcard 1 from drawer 2"
},
{
"role": "user",
"content": "You pick up the creditcard 1 from the drawer 2."
},
{
"role": "assistant",
"content": "Think: Now I need to place creditcard 1 in/on sofa 1. Let me go there.\nAct: go to sofa 1"
},
{
"role": "user",
"content": "On the sofa 1, you see a cellphone 1 and a pencil 1."
},
{
"role": "assistant",
"content": "Think: Let me place creditcard 1 here.\nAct: put creditcard 1 in/on sofa 1"
},
{
"role": "user",
"content": "You put the creditcard 1 in/on the sofa 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a creditcard in/on sofa 1.",
"room_type": "livingroom",
"difficulty": "normal",
"num_steps": 15
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a sinkbasin 1, a toilet 1, a bathtubbasin 1, a cabinet 1, a cabinet 2, a cabinet 3, a cabinet 4, a cabinet 5, a countertop 1, a shelf 1, a shelf 2, a shelf 3, a shelf 4, a towelholder 1, a garbagecan 1, a drawer 1, a drawer 2, a drawer 3, a drawer 4, a drawer 5, a drawer 6.\n\nYour task is to: put a toiletpaper in/on toilet 1."
},
{
"role": "assistant",
"content": "Think: I should look for toiletpaper. Let me start with cabinet 4.\nAct: go to cabinet 4"
},
{
"role": "user",
"content": "The cabinet 4 is closed."
},
{
"role": "assistant",
"content": "Think: I should open the cabinet 4 to check its contents.\nAct: open cabinet 4"
},
{
"role": "user",
"content": "You open the cabinet 4. The cabinet 4 is open. In it, you see a soapbar 1."
},
{
"role": "assistant",
"content": "Think: toiletpaper wasn't there. Let me try garbagecan 1.\nAct: go to garbagecan 1"
},
{
"role": "user",
"content": "On the garbagecan 1, you see a towel 2, a toiletpaper 1, a spraybottle 1, and a plunger 2."
},
{
"role": "assistant",
"content": "Think: I found toiletpaper 1 on garbagecan 1. I should pick it up.\nAct: take toiletpaper 1 from garbagecan 1"
},
{
"role": "user",
"content": "You pick up the toiletpaper 1 from the garbagecan 1."
},
{
"role": "assistant",
"content": "Think: Now I need to place toiletpaper 1 in/on toilet 1. Let me go there.\nAct: go to toilet 1"
},
{
"role": "user",
"content": "On the toilet 1, you see a candle 2."
},
{
"role": "assistant",
"content": "Think: Let me place toiletpaper 1 here.\nAct: put toiletpaper 1 in/on toilet 1"
},
{
"role": "user",
"content": "You put the toiletpaper 1 in/on the toilet 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a toiletpaper in/on toilet 1.",
"room_type": "bathroom",
"difficulty": "normal",
"num_steps": 13
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a bed 1, a desk 1, a drawer 1, a drawer 2, a shelf 1, a sidetable 1, a sidetable 2, a dresser 1, a safe 1, a garbagecan 1, a laundryhamper 1.\n\nYour task is to: put a cd in/on shelf 1."
},
{
"role": "assistant",
"content": "Think: First, I should locate cd. shelf 1 seems like a good place to look.\nAct: go to shelf 1"
},
{
"role": "user",
"content": "On the shelf 1, you see nothing."
},
{
"role": "assistant",
"content": "Think: Not here. Moving on to laundryhamper 1.\nAct: go to laundryhamper 1"
},
{
"role": "user",
"content": "On the laundryhamper 1, you see a box 1 and a keychain 2."
},
{
"role": "assistant",
"content": "Think: I don't see cd here. I'll try sidetable 2 next.\nAct: go to sidetable 2"
},
{
"role": "user",
"content": "On the sidetable 2, you see a keychain 1."
},
{
"role": "assistant",
"content": "Think: I don't see cd here. I'll try desk 1 next.\nAct: go to desk 1"
},
{
"role": "user",
"content": "On the desk 1, you see a pillow 1, a book 1, and a cd 1."
},
{
"role": "assistant",
"content": "Think: I can see cd 1 on desk 1. I'll grab it.\nAct: take cd 1 from desk 1"
},
{
"role": "user",
"content": "You pick up the cd 1 from the desk 1."
},
{
"role": "assistant",
"content": "Think: Time to put cd 1 in/on shelf 1.\nAct: go to shelf 1"
},
{
"role": "user",
"content": "On the shelf 1, you see nothing."
},
{
"role": "assistant",
"content": "Think: Now I'll set cd 1 down in/on shelf 1.\nAct: put cd 1 in/on shelf 1"
},
{
"role": "user",
"content": "You put the cd 1 in/on the shelf 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a cd in/on shelf 1.",
"room_type": "bedroom",
"difficulty": "normal",
"num_steps": 15
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a countertop 1, a cabinet 1, a fridge 1, a microwave 1, a sinkbasin 1, a stoveburner 1, a stoveburner 2, a drawer 1, a shelf 1, a shelf 2, a garbagecan 1, a toaster 1, a coffeemachine 1.\n\nYour task is to: put a bread in/on countertop 1."
},
{
"role": "assistant",
"content": "Think: To complete this task, I need bread. I'll search garbagecan 1.\nAct: go to garbagecan 1"
},
{
"role": "user",
"content": "On the garbagecan 1, you see a mug 1."
},
{
"role": "assistant",
"content": "Think: bread is not here. Let me check stoveburner 2.\nAct: go to stoveburner 2"
},
{
"role": "user",
"content": "On the stoveburner 2, you see a spatula 1, a bowl 2, and a bread 2."
},
{
"role": "assistant",
"content": "Think: There's bread 2 here. Let me take it.\nAct: take bread 2 from stoveburner 2"
},
{
"role": "user",
"content": "You pick up the bread 2 from the stoveburner 2."
},
{
"role": "assistant",
"content": "Think: I should bring bread 2 to countertop 1 and place it there.\nAct: go to countertop 1"
},
{
"role": "user",
"content": "On the countertop 1, you see a bread 1."
},
{
"role": "assistant",
"content": "Think: I'll put bread 2 in/on countertop 1 now.\nAct: put bread 2 in/on countertop 1"
},
{
"role": "user",
"content": "You put the bread 2 in/on the countertop 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a bread in/on countertop 1.",
"room_type": "kitchen",
"difficulty": "normal",
"num_steps": 11
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a bed 1, a desk 1, a drawer 1, a drawer 2, a drawer 3, a drawer 4, a drawer 5, a shelf 1, a shelf 2, a sidetable 1, a sidetable 2, a sidetable 3, a dresser 1, a safe 1, a garbagecan 1, a laundryhamper 1.\n\nYour task is to: put a watch in/on laundryhamper 1."
},
{
"role": "assistant",
"content": "Think: My goal requires watch. Let me try shelf 2.\nAct: go to shelf 2"
},
{
"role": "user",
"content": "On the shelf 2, you see a creditcard 3."
},
{
"role": "assistant",
"content": "Think: watch wasn't there. Let me try safe 1.\nAct: go to safe 1"
},
{
"role": "user",
"content": "The safe 1 is closed."
},
{
"role": "assistant",
"content": "Think: The safe 1 is closed. I need to open it first.\nAct: open safe 1"
},
{
"role": "user",
"content": "You open the safe 1. The safe 1 is open. In it, you see nothing."
},
{
"role": "assistant",
"content": "Think: watch wasn't there. Let me try drawer 5.\nAct: go to drawer 5"
},
{
"role": "user",
"content": "On the drawer 5, you see nothing."
},
{
"role": "assistant",
"content": "Think: I didn't find watch. sidetable 1 might have it.\nAct: go to sidetable 1"
},
{
"role": "user",
"content": "The sidetable 1 appears to be empty."
},
{
"role": "assistant",
"content": "Think: No luck. Let me look at sidetable 2.\nAct: go to sidetable 2"
},
{
"role": "user",
"content": "On the sidetable 2, you see a book 1 and a creditcard 4."
},
{
"role": "assistant",
"content": "Think: I didn't find watch. desk 1 might have it.\nAct: go to desk 1"
},
{
"role": "user",
"content": "On the desk 1, you see a pillow 2, a vase 3, and a pencil 1."
},
{
"role": "assistant",
"content": "Think: watch is not here. Let me check drawer 2.\nAct: go to drawer 2"
},
{
"role": "user",
"content": "The drawer 2 is closed."
},
{
"role": "assistant",
"content": "Think: The drawer 2 is closed. I need to open it first.\nAct: open drawer 2"
},
{
"role": "user",
"content": "You open the drawer 2. The drawer 2 is open. In it, you see a watch 1."
},
{
"role": "assistant",
"content": "Think: Found it! watch 1 is on drawer 2. Let me pick it up.\nAct: take watch 1 from drawer 2"
},
{
"role": "user",
"content": "You pick up the watch 1 from the drawer 2."
},
{
"role": "assistant",
"content": "Think: Final step: put watch 1 in/on laundryhamper 1.\nAct: go to laundryhamper 1"
},
{
"role": "user",
"content": "On the laundryhamper 1, you see a keychain 1."
},
{
"role": "assistant",
"content": "Think: Let me place watch 1 here.\nAct: put watch 1 in/on laundryhamper 1"
},
{
"role": "user",
"content": "You put the watch 1 in/on the laundryhamper 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a watch in/on laundryhamper 1.",
"room_type": "bedroom",
"difficulty": "hard",
"num_steps": 25
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a countertop 1, a cabinet 1, a cabinet 2, a cabinet 3, a cabinet 4, a cabinet 5, a fridge 1, a microwave 1, a sinkbasin 1, a stoveburner 1, a stoveburner 2, a drawer 1, a shelf 1, a shelf 2, a shelf 3, a garbagecan 1, a toaster 1, a coffeemachine 1.\n\nYour task is to: put a spatula in/on shelf 1."
},
{
"role": "assistant",
"content": "Think: First, I should locate spatula. cabinet 5 seems like a good place to look.\nAct: go to cabinet 5"
},
{
"role": "user",
"content": "The cabinet 5 is open. In it, you see a cup 1."
},
{
"role": "assistant",
"content": "Think: Not here. Moving on to cabinet 3.\nAct: go to cabinet 3"
},
{
"role": "user",
"content": "The cabinet 3 is closed."
},
{
"role": "assistant",
"content": "Think: I should open the cabinet 3 to check its contents.\nAct: open cabinet 3"
},
{
"role": "user",
"content": "You open the cabinet 3. The cabinet 3 is open. In it, you see a bread 1 and a knife 1."
},
{
"role": "assistant",
"content": "Think: I didn't find spatula. cabinet 2 might have it.\nAct: go to cabinet 2"
},
{
"role": "user",
"content": "The cabinet 2 is closed."
},
{
"role": "assistant",
"content": "Think: I should open the cabinet 2 to check its contents.\nAct: open cabinet 2"
},
{
"role": "user",
"content": "You open the cabinet 2. The cabinet 2 is open. In it, you see a spatula 1."
},
{
"role": "assistant",
"content": "Think: I can see spatula 1 on cabinet 2. I'll grab it.\nAct: take spatula 1 from cabinet 2"
},
{
"role": "user",
"content": "You pick up the spatula 1 from the cabinet 2."
},
{
"role": "assistant",
"content": "Think: Final step: put spatula 1 in/on shelf 1.\nAct: go to shelf 1"
},
{
"role": "user",
"content": "On the shelf 1, you see a soapbottle 1."
},
{
"role": "assistant",
"content": "Think: Now I'll set spatula 1 down in/on shelf 1.\nAct: put spatula 1 in/on shelf 1"
},
{
"role": "user",
"content": "You put the spatula 1 in/on the shelf 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a spatula in/on shelf 1.",
"room_type": "kitchen",
"difficulty": "normal",
"num_steps": 17
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a sinkbasin 1, a toilet 1, a bathtubbasin 1, a cabinet 1, a cabinet 2, a countertop 1, a countertop 2, a shelf 1, a shelf 2, a shelf 3, a shelf 4, a shelf 5, a towelholder 1, a garbagecan 1, a drawer 1, a drawer 2.\n\nYour task is to: put a tissuebox in/on drawer 1."
},
{
"role": "assistant",
"content": "Think: I should look for tissuebox. Let me start with garbagecan 1.\nAct: go to garbagecan 1"
},
{
"role": "user",
"content": "On the garbagecan 1, you see nothing."
},
{
"role": "assistant",
"content": "Think: I didn't find tissuebox. sinkbasin 1 might have it.\nAct: go to sinkbasin 1"
},
{
"role": "user",
"content": "On the sinkbasin 1, you see a tissuebox 1 and a soapbottle 2."
},
{
"role": "assistant",
"content": "Think: There's tissuebox 1 here. Let me take it.\nAct: take tissuebox 1 from sinkbasin 1"
},
{
"role": "user",
"content": "You pick up the tissuebox 1 from the sinkbasin 1."
},
{
"role": "assistant",
"content": "Think: Final step: put tissuebox 1 in/on drawer 1.\nAct: go to drawer 1"
},
{
"role": "user",
"content": "The drawer 1 is closed."
},
{
"role": "assistant",
"content": "Think: drawer 1 is closed. Let me open it to see what's inside.\nAct: open drawer 1"
},
{
"role": "user",
"content": "You open the drawer 1. The drawer 1 is open. In it, you see nothing."
},
{
"role": "assistant",
"content": "Think: I'll put tissuebox 1 in/on drawer 1 now.\nAct: put tissuebox 1 in/on drawer 1"
},
{
"role": "user",
"content": "You put the tissuebox 1 in/on the drawer 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a tissuebox in/on drawer 1.",
"room_type": "bathroom",
"difficulty": "normal",
"num_steps": 13
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a sofa 1, a coffeetable 1, a sidetable 1, a sidetable 2, a shelf 1, a shelf 2, a shelf 3, a shelf 4, a shelf 5, a shelf 6, a drawer 1, a drawer 2, a drawer 3, a drawer 4, a dresser 1, a armchair 1, a desk 1, a garbagecan 1, a safe 1.\n\nYour task is to: put a pencil in/on desk 1."
},
{
"role": "assistant",
"content": "Think: I should look for pencil. Let me start with drawer 1.\nAct: go to drawer 1"
},
{
"role": "user",
"content": "The drawer 1 is open. In it, you see a remotecontrol 1, a book 1, and a desklamp 1."
},
{
"role": "assistant",
"content": "Think: Not here. Moving on to dresser 1.\nAct: go to dresser 1"
},
{
"role": "user",
"content": "The dresser 1 appears to be empty."
},
{
"role": "assistant",
"content": "Think: I don't see pencil here. I'll try safe 1 next.\nAct: go to safe 1"
},
{
"role": "user",
"content": "The safe 1 is closed."
},
{
"role": "assistant",
"content": "Think: I should open the safe 1 to check its contents.\nAct: open safe 1"
},
{
"role": "user",
"content": "You open the safe 1. The safe 1 is open. In it, you see a candle 1."
},
{
"role": "assistant",
"content": "Think: No luck. Let me look at drawer 3.\nAct: go to drawer 3"
},
{
"role": "user",
"content": "The drawer 3 is closed."
},
{
"role": "assistant",
"content": "Think: The drawer 3 is closed. I need to open it first.\nAct: open drawer 3"
},
{
"role": "user",
"content": "You open the drawer 3. The drawer 3 is open. In it, you see a vase 1 and a pencil 1."
},
{
"role": "assistant",
"content": "Think: I found pencil 1 on drawer 3. I should pick it up.\nAct: take pencil 1 from drawer 3"
},
{
"role": "user",
"content": "You pick up the pencil 1 from the drawer 3."
},
{
"role": "assistant",
"content": "Think: Now I need to place pencil 1 in/on desk 1. Let me go there.\nAct: go to desk 1"
},
{
"role": "user",
"content": "On the desk 1, you see nothing."
},
{
"role": "assistant",
"content": "Think: Let me place pencil 1 here.\nAct: put pencil 1 in/on desk 1"
},
{
"role": "user",
"content": "You put the pencil 1 in/on the desk 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a pencil in/on desk 1.",
"room_type": "livingroom",
"difficulty": "hard",
"num_steps": 19
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a countertop 1, a countertop 2, a cabinet 1, a cabinet 2, a cabinet 3, a cabinet 4, a cabinet 5, a cabinet 6, a fridge 1, a microwave 1, a sinkbasin 1, a stoveburner 1, a drawer 1, a drawer 2, a drawer 3, a drawer 4, a shelf 1, a shelf 2, a shelf 3, a shelf 4, a shelf 5, a shelf 6, a garbagecan 1, a toaster 1, a coffeemachine 1.\n\nYour task is to: put a plate in/on fridge 1."
},
{
"role": "assistant",
"content": "Think: I need to find plate. Let me check shelf 3.\nAct: go to shelf 3"
},
{
"role": "user",
"content": "On the shelf 3, you see a knife 1."
},
{
"role": "assistant",
"content": "Think: No luck. Let me look at stoveburner 1.\nAct: go to stoveburner 1"
},
{
"role": "user",
"content": "The stoveburner 1 appears to be empty."
},
{
"role": "assistant",
"content": "Think: I didn't find plate. garbagecan 1 might have it.\nAct: go to garbagecan 1"
},
{
"role": "user",
"content": "The garbagecan 1 appears to be empty."
},
{
"role": "assistant",
"content": "Think: I didn't find plate. countertop 1 might have it.\nAct: go to countertop 1"
},
{
"role": "user",
"content": "On the countertop 1, you see a plate 1."
},
{
"role": "assistant",
"content": "Think: I found plate 1 on countertop 1. I should pick it up.\nAct: take plate 1 from countertop 1"
},
{
"role": "user",
"content": "You pick up the plate 1 from the countertop 1."
},
{
"role": "assistant",
"content": "Think: I should bring plate 1 to fridge 1 and place it there.\nAct: go to fridge 1"
},
{
"role": "user",
"content": "The fridge 1 appears to be empty."
},
{
"role": "assistant",
"content": "Think: Let me place plate 1 here.\nAct: put plate 1 in/on fridge 1"
},
{
"role": "user",
"content": "You put the plate 1 in/on the fridge 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a plate in/on fridge 1.",
"room_type": "kitchen",
"difficulty": "normal",
"num_steps": 15
}
|
[
{
"role": "system",
"content": "You are a household task-solving agent. Interact with the environment to complete the given task. At each step, you will receive an observation describing what you see. Think step by step about what to do next, then call the act function to execute your chosen action."
},
{
"role": "user",
"content": "You are in the middle of a room. Looking quickly around you, you see a countertop 1, a cabinet 1, a fridge 1, a microwave 1, a sinkbasin 1, a stoveburner 1, a drawer 1, a drawer 2, a shelf 1, a shelf 2, a shelf 3, a shelf 4, a shelf 5, a shelf 6, a garbagecan 1, a toaster 1, a coffeemachine 1.\n\nYour task is to: put a soapbottle in/on garbagecan 1."
},
{
"role": "assistant",
"content": "Think: First, I should locate soapbottle. drawer 2 seems like a good place to look.\nAct: go to drawer 2"
},
{
"role": "user",
"content": "The drawer 2 is closed."
},
{
"role": "assistant",
"content": "Think: I should open the drawer 2 to check its contents.\nAct: open drawer 2"
},
{
"role": "user",
"content": "You open the drawer 2. The drawer 2 is open. In it, you see a bowl 2 and a soapbottle 1."
},
{
"role": "assistant",
"content": "Think: Found it! soapbottle 1 is on drawer 2. Let me pick it up.\nAct: take soapbottle 1 from drawer 2"
},
{
"role": "user",
"content": "You pick up the soapbottle 1 from the drawer 2."
},
{
"role": "assistant",
"content": "Think: Time to put soapbottle 1 in/on garbagecan 1.\nAct: go to garbagecan 1"
},
{
"role": "user",
"content": "On the garbagecan 1, you see a lettuce 2 and a spoon 1."
},
{
"role": "assistant",
"content": "Think: I'll put soapbottle 1 in/on garbagecan 1 now.\nAct: put soapbottle 1 in/on garbagecan 1"
},
{
"role": "user",
"content": "You put the soapbottle 1 in/on the garbagecan 1."
}
] |
{
"task_type": "pick_and_place",
"description": "put a soapbottle in/on garbagecan 1.",
"room_type": "kitchen",
"difficulty": "easy",
"num_steps": 11
}
|
End of preview. Expand
in Data Studio
YAML Metadata
Warning:
The task_categories "conversational" is not in the official list: text-classification, token-classification, table-question-answering, question-answering, zero-shot-classification, translation, summarization, feature-extraction, text-generation, fill-mask, sentence-similarity, text-to-speech, text-to-audio, automatic-speech-recognition, audio-to-audio, audio-classification, audio-text-to-text, voice-activity-detection, depth-estimation, image-classification, object-detection, image-segmentation, text-to-image, image-to-text, image-to-image, image-to-video, unconditional-image-generation, video-classification, reinforcement-learning, robotics, tabular-classification, tabular-regression, tabular-to-text, table-to-text, multiple-choice, text-ranking, text-retrieval, time-series-forecasting, text-to-video, image-text-to-text, image-text-to-image, image-text-to-video, visual-question-answering, document-question-answering, zero-shot-image-classification, graph-ml, mask-generation, zero-shot-object-detection, text-to-3d, image-to-3d, image-feature-extraction, video-text-to-text, keypoint-detection, visual-document-retrieval, any-to-any, video-to-video, other
ALFWorld Trajectory Dataset
Overview
This is a synthetic SFT (Supervised Fine-Tuning) dataset designed for agent training in ALFWorld-compatible environments. The dataset programmatically generates expert trajectories without requiring an actual ALFWorld environment or a large language model.
Key Approach
- Template-based Simulation: Lightweight simulator based on published ALFWorld information (papers, ReAct prompt examples).
- Subgoal Decomposition: Rule-based expert system supporting 6 task types.
- Observation & Thought Diversity: Various templates for diversifying observation and thought texts.
- Multiple Formats: Supports both function-calling and ReAct formats.
Key Features
| Feature | Description |
|---|---|
| Compatibility | ALFWorld-compatible tasks and actions |
| Task Types | 6 distinct task types: pick_and_place, clean_and_place, heat_and_place, cool_and_place, examine, pick_two |
| Difficulty Levels | Easy, Normal, Hard (controlling exploration detours) |
| Trajectory Format | Function-calling (also available in ReAct format) |
| Multi-turn Dialogue | Each trajectory is a multi-turn conversation between user (observation) and assistant (thought, action) |
| Synthetic Data | Programmatically generated, ensuring controlled and varied scenarios |
Dataset Statistics
- Total trajectories: 1,200
- Average messages per trajectory: 21.1
- Number of steps (turns) distribution: 9 steps (3.3%) / 11 steps (4.9%) / 13 steps (8.8%) / 15 steps (12.6%) / 17 steps (14.4%) / 19 steps (10.6%) / 21 steps (11.5%) / 23 steps (8.9%) / 25 steps (8.2%) / 27 steps (4.8%) / 29 steps (3.9%) / 31 steps (2.8%) / 33 steps (1.2%) / 35 steps (0.9%) / 37 steps (0.7%) / 39 steps (0.9%) / 41 steps (0.5%) / 43 steps (0.3%) / 45 steps (0.5%) / 47 steps (0.2%) / 49 steps (0.1%)
- Task type distribution: clean_and_place: 200 (16.7%) / cool_and_place: 200 (16.7%) / examine: 200 (16.7%) / heat_and_place: 200 (16.7%) / pick_and_place: 200 (16.7%) / pick_two: 200 (16.7%)
- Difficulty distribution: Easy: 227 (18.9%) / Hard: 362 (30.2%) / Normal: 611 (50.9%)
Data Format
Each line in the JSONL file is a JSON object with the following fields:
{{ # Start of outer JSON object
"messages": [
{{"role": "system", "content": "Interact with a household to solve a task..."}},
{{"role": "user", "content": "You are in the middle of a room..."}},
{{"role": "assistant", "content": "Think: I should look for apple...",
"tool_calls": [
{{"id": "call_1", "type": "function", "function": {{ # Inner function object
"name": "act", "arguments": "{"action": "go to microwave 1"}"
}}}}
]
}},
{{"role": "tool", "tool_call_id": "call_1", "content": "The microwave 1 is open..."}}
// ... more turns
],
"metadata": {{ # Metadata object
"task_type": "heat_and_place",
"description": "put a hot apple in/on stoveburner 1.",
"room_type": "kitchen",
"difficulty": "normal",
"num_steps": 17
}}
}}
Usage
For SFT Training
from datasets import load_dataset
ds = load_dataset("u-10bei/sft_alfworld_trajectory_dataset_v2")
for sample in ds["train"]:
messages = sample["messages"]
# messages is already in chat format for training
Last Updated
2026-02-10 02:49:38
License
MIT
- Downloads last month
- 323
Size of downloaded dataset files:
3.28 MB
Size of the auto-converted Parquet files:
2.64 MB
Number of rows:
1,200