Hugging Face's logo

Datasets:
AgentSuite
/
tau2-bench-trajectories

Tags:
agent
function-calling
tool-use
llm-trajectories
Dataset card Data Studio Files
xet
 Community
Dataset Preview
Duplicate
The full dataset viewer is not available (click to read why). Only showing a preview of the rows.
The dataset generation failed
Error code:   DatasetGenerationError
Exception:    TypeError
Message:      Couldn't cast array of type int64 to null
Traceback:    Traceback (most recent call last):
                File "/usr/local/lib/python3.12/site-packages/datasets/builder.py", line 1816, in _prepare_split_single
                  for key, table in generator:
                                    ^^^^^^^^^
                File "/usr/local/lib/python3.12/site-packages/datasets/packaged_modules/json/json.py", line 310, in _generate_tables
                  self._cast_table(pa_table, json_field_paths=json_field_paths),
                  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
                File "/usr/local/lib/python3.12/site-packages/datasets/packaged_modules/json/json.py", line 130, in _cast_table
                  pa_table = table_cast(pa_table, self.info.features.arrow_schema)
                             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
                File "/usr/local/lib/python3.12/site-packages/datasets/table.py", line 2369, in table_cast
                  return cast_table_to_schema(table, schema)
                         ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
                File "/usr/local/lib/python3.12/site-packages/datasets/table.py", line 2303, in cast_table_to_schema
                  cast_array_to_feature(
                File "/usr/local/lib/python3.12/site-packages/datasets/table.py", line 1852, in wrapper
                  return pa.chunked_array([func(chunk, *args, **kwargs) for chunk in array.chunks])
                                           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
                File "/usr/local/lib/python3.12/site-packages/datasets/table.py", line 2059, in cast_array_to_feature
                  _c(array.field(name) if name in array_fields else null_array, subfeature)
                File "/usr/local/lib/python3.12/site-packages/datasets/table.py", line 1854, in wrapper
                  return func(array, *args, **kwargs)
                         ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
                File "/usr/local/lib/python3.12/site-packages/datasets/table.py", line 2143, in cast_array_to_feature
                  return array_cast(
                         ^^^^^^^^^^^
                File "/usr/local/lib/python3.12/site-packages/datasets/table.py", line 1854, in wrapper
                  return func(array, *args, **kwargs)
                         ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
                File "/usr/local/lib/python3.12/site-packages/datasets/table.py", line 2005, in array_cast
                  raise TypeError(f"Couldn't cast array of type {_short_str(array.type)} to {_short_str(pa_type)}")
              TypeError: Couldn't cast array of type int64 to null
              
              The above exception was the direct cause of the following exception:
              
              Traceback (most recent call last):
                File "/src/services/worker/src/worker/job_runners/config/parquet_and_info.py", line 1348, in compute_config_parquet_and_info_response
                  parquet_operations = convert_to_parquet(builder)
                                       ^^^^^^^^^^^^^^^^^^^^^^^^^^^
                File "/src/services/worker/src/worker/job_runners/config/parquet_and_info.py", line 980, in convert_to_parquet
                  builder.download_and_prepare(
                File "/usr/local/lib/python3.12/site-packages/datasets/builder.py", line 890, in download_and_prepare
                  self._download_and_prepare(
                File "/usr/local/lib/python3.12/site-packages/datasets/builder.py", line 951, in _download_and_prepare
                  self._prepare_split(split_generator, **prepare_split_kwargs)
                File "/usr/local/lib/python3.12/site-packages/datasets/builder.py", line 1683, in _prepare_split
                  for job_id, done, content in self._prepare_split_single(
                                               ^^^^^^^^^^^^^^^^^^^^^^^^^^^
                File "/usr/local/lib/python3.12/site-packages/datasets/builder.py", line 1869, in _prepare_split_single
                  raise DatasetGenerationError("An error occurred while generating the dataset") from e
              datasets.exceptions.DatasetGenerationError: An error occurred while generating the dataset

Need help to make the dataset viewer work? Make sure to review how to configure the dataset viewer, and open a discussion for direct support.

model_path
string
user_model_path
string
benchmark_name
string
task_name
string
sampling_params
dict
user_sampling_params
dict
messages
list
eval_result
dict
meta
dict
deepseek-ai/DeepSeek-R1-0528
openai/gpt-4o-20240806
tau2-bench
telecom
{ "max_tokens": null, "temperature": 0 }
{ "temperature": 0 }
[ { "role": "system", "content": "<main_policy>\n# Telecom Agent Policy\n\nThe current time is 2025-02-25 12:08:00 EST.\n\nAs a telecom agent, you can help users with **technical support**, **overdue bill payment**, **line suspension**, and **plan options**.\n\nYou should not provide any information, knowled...
{ "score": 1, "db_match": true }
{ "id": "telecom_[mobile_data_issue]airplane_mode_on|data_mode_off[PERSONA:None]", "is_correct": true, "finish_reason": "user_stop", "run_timestamp": "2025-08-13T12:44:03.933450", "simulation_start_time": "2025-08-13T12:44:04.351791", "simulation_end_time": "2025-08-13T12:50:16.781687", "duration_seconds"...
deepseek-ai/DeepSeek-R1-0528
openai/gpt-4o-20240806
tau2-bench
telecom
{ "max_tokens": null, "temperature": 0 }
{ "temperature": 0 }
[ { "role": "system", "content": "<main_policy>\n# Telecom Agent Policy\n\nThe current time is 2025-02-25 12:08:00 EST.\n\nAs a telecom agent, you can help users with **technical support**, **overdue bill payment**, **line suspension**, and **plan options**.\n\nYou should not provide any information, knowled...
{ "score": 1, "db_match": true }
{ "id": "telecom_[mobile_data_issue]airplane_mode_on|bad_network_preference[PERSONA:Hard]", "is_correct": true, "finish_reason": "user_stop", "run_timestamp": "2025-08-13T12:44:03.933450", "simulation_start_time": "2025-08-13T12:44:07.150601", "simulation_end_time": "2025-08-13T12:52:51.566843", "duration...
deepseek-ai/DeepSeek-R1-0528
openai/gpt-4o-20240806
tau2-bench
telecom
{ "max_tokens": null, "temperature": 0 }
{ "temperature": 0 }
[ { "role": "system", "content": "<main_policy>\n# Telecom Agent Policy\n\nThe current time is 2025-02-25 12:08:00 EST.\n\nAs a telecom agent, you can help users with **technical support**, **overdue bill payment**, **line suspension**, and **plan options**.\n\nYou should not provide any information, knowled...
{ "score": 0, "db_match": false }
{ "id": "telecom_[mobile_data_issue]airplane_mode_on|data_saver_mode_on|user_abroad_roaming_disabled_on[PERSONA:None]", "is_correct": false, "finish_reason": "user_stop", "run_timestamp": "2025-08-13T12:44:03.933450", "simulation_start_time": "2025-08-13T12:44:07.370063", "simulation_end_time": "2025-08-13T...
deepseek-ai/DeepSeek-R1-0528
openai/gpt-4o-20240806
tau2-bench
telecom
{ "max_tokens": null, "temperature": 0 }
{ "temperature": 0 }
[ { "role": "system", "content": "<main_policy>\n# Telecom Agent Policy\n\nThe current time is 2025-02-25 12:08:00 EST.\n\nAs a telecom agent, you can help users with **technical support**, **overdue bill payment**, **line suspension**, and **plan options**.\n\nYou should not provide any information, knowled...
{ "score": 1, "db_match": true }
{ "id": "telecom_[mobile_data_issue]airplane_mode_on|bad_network_preference|user_abroad_roaming_enabled_off[PERSONA:Easy]", "is_correct": true, "finish_reason": "user_stop", "run_timestamp": "2025-08-13T12:44:03.933450", "simulation_start_time": "2025-08-13T12:44:07.407584", "simulation_end_time": "2025-08-...
deepseek-ai/DeepSeek-R1-0528
openai/gpt-4o-20240806
tau2-bench
telecom
{ "max_tokens": null, "temperature": 0 }
{ "temperature": 0 }
[ { "role": "system", "content": "<main_policy>\n# Telecom Agent Policy\n\nThe current time is 2025-02-25 12:08:00 EST.\n\nAs a telecom agent, you can help users with **technical support**, **overdue bill payment**, **line suspension**, and **plan options**.\n\nYou should not provide any information, knowled...
{ "score": 1, "db_match": false }
{ "id": "telecom_[mobile_data_issue]airplane_mode_on|bad_network_preference|bad_vpn|data_saver_mode_on|user_abroad_roaming_disabled_on[PERSONA:Easy]", "is_correct": false, "finish_reason": "user_stop", "run_timestamp": "2025-08-13T12:44:03.933450", "simulation_start_time": "2025-08-13T12:44:07.609010", "sim...
deepseek-ai/DeepSeek-R1-0528
openai/gpt-4o-20240806
tau2-bench
telecom
{ "max_tokens": null, "temperature": 0 }
{ "temperature": 0 }
[{"role":"system","content":"<main_policy>\n# Telecom Agent Policy\n\nThe current time is 2025-02-25(...TRUNCATED)
{ "score": 0, "db_match": false }
{"id":"telecom_[mobile_data_issue]airplane_mode_on|bad_network_preference|data_mode_off|data_saver_m(...TRUNCATED)
deepseek-ai/DeepSeek-R1-0528
openai/gpt-4o-20240806
tau2-bench
telecom
{ "max_tokens": null, "temperature": 0 }
{ "temperature": 0 }
[{"role":"system","content":"<main_policy>\n# Telecom Agent Policy\n\nThe current time is 2025-02-25(...TRUNCATED)
{ "score": 1, "db_match": false }
{"id":"telecom_[mobile_data_issue]data_mode_off|data_usage_exceeded[PERSONA:None]","is_correct":fals(...TRUNCATED)
deepseek-ai/DeepSeek-R1-0528
openai/gpt-4o-20240806
tau2-bench
telecom
{ "max_tokens": null, "temperature": 0 }
{ "temperature": 0 }
[{"role":"system","content":"<main_policy>\n# Telecom Agent Policy\n\nThe current time is 2025-02-25(...TRUNCATED)
{ "score": 1, "db_match": false }
{"id":"telecom_[mobile_data_issue]bad_network_preference|data_saver_mode_on|data_usage_exceeded[PERS(...TRUNCATED)
deepseek-ai/DeepSeek-R1-0528
openai/gpt-4o-20240806
tau2-bench
telecom
{ "max_tokens": null, "temperature": 0 }
{ "temperature": 0 }
[{"role":"system","content":"<main_policy>\n# Telecom Agent Policy\n\nThe current time is 2025-02-25(...TRUNCATED)
{ "score": 0, "db_match": false }
{"id":"telecom_[mobile_data_issue]bad_network_preference|bad_vpn|user_abroad_roaming_enabled_off[PER(...TRUNCATED)
deepseek-ai/DeepSeek-R1-0528
openai/gpt-4o-20240806
tau2-bench
telecom
{ "max_tokens": null, "temperature": 0 }
{ "temperature": 0 }
[{"role":"system","content":"<main_policy>\n# Telecom Agent Policy\n\nThe current time is 2025-02-25(...TRUNCATED)
{ "score": 1, "db_match": false }
{"id":"telecom_[mobile_data_issue]bad_network_preference|bad_vpn|data_usage_exceeded|user_abroad_roa(...TRUNCATED)
End of preview.

AgentSuite/tau2-bench-trajectories

Per-model agent trajectory data for tau2-bench (public release).

  • Models: 30
  • Tasks per model: 278
  • One file per model: {model}.jsonl, one JSON object per line.
  • Fields: model_path, user_model_path, benchmark_name, task_name, sampling_params, user_sampling_params, messages, eval_result, meta.
  • sampling_params reflect each benchmark's own implementation; values the benchmark leaves unset are recorded as null (provider default).

Models

  • DeepSeek-R1-0528
  • DeepSeek-V3-0324
  • DeepSeek-V3.2-Exp-thinking-off
  • DeepSeek-V3.2-Exp-thinking-on
  • Kimi-K2-Instruct
  • Kimi-K2-Instruct-0905
  • Qwen3-235B-A22B-FP8
  • Qwen3-235B-A22B-Instruct-2507-FP8
  • Qwen3-235B-A22B-Thinking-2507-FP8
  • Qwen3-Coder-480B-A35B-Instruct-FP8
  • claude-4-opus-thinking-off
  • claude-4-opus-thinking-on-10k
  • claude-4-sonnet-thinking-off
  • claude-4-sonnet-thinking-on-10k
  • claude-4.5-sonnet-thinking-off
  • claude-4.5-sonnet-thinking-on-10k
  • gemini-2.5-flash-thinking-off
  • gemini-2.5-flash-thinking-on
  • gemini-2.5-pro-thinking-on
  • gpt-4.1
  • gpt-4.1-mini
  • gpt-4.1-nano
  • gpt-4o-20240806
  • gpt-4o-mini
  • gpt-5
  • gpt-5-nano
  • gpt-oss-120b
  • gpt-oss-20b
  • o3-high
  • o4-mini-high
Downloads last month
199
Total file size:
290 MB