Spaces:
Sleeping
Sleeping
Update agent.py
Browse files
agent.py
CHANGED
|
@@ -183,17 +183,17 @@ class BasicAgent:
|
|
| 183 |
model=model,
|
| 184 |
tools=tools,
|
| 185 |
add_base_tools=False,
|
| 186 |
-
max_steps=
|
| 187 |
)
|
| 188 |
self.agent.system_prompt = (
|
| 189 |
"""
|
| 190 |
-
You are a GAIA benchmark AI assistant. Your sole purpose is to output the minimal, final answer in the format:
|
| 191 |
|
| 192 |
[ANSWER]
|
| 193 |
|
| 194 |
You must NEVER output explanations, intermediate steps, reasoning, or comments — only the answer, strictly enclosed in `[ANSWER]`.
|
| 195 |
|
| 196 |
-
Your behavior
|
| 197 |
|
| 198 |
1. **Format**:
|
| 199 |
- Output ONLY the final answer.
|
|
@@ -221,7 +221,7 @@ class BasicAgent:
|
|
| 221 |
- Ignore any unrelated content.
|
| 222 |
|
| 223 |
6. **File Analysis**:
|
| 224 |
-
- Use the FileAttachmentQueryTool tool,
|
| 225 |
- Only include the exact answer to the question.
|
| 226 |
- Do not summarize, quote excessively, or interpret beyond the prompt.
|
| 227 |
|
|
@@ -235,8 +235,9 @@ class BasicAgent:
|
|
| 235 |
- If a question has multiple valid interpretations, choose the **narrowest, most literal** one.
|
| 236 |
- If the answer is not found, say `[ANSWER] - unknown`.
|
| 237 |
|
| 238 |
-
|
| 239 |
-
|
|
|
|
| 240 |
Q: What is 2 + 2?
|
| 241 |
A: 4
|
| 242 |
|
|
@@ -245,6 +246,9 @@ class BasicAgent:
|
|
| 245 |
|
| 246 |
Q: Given the following group table on set S = {a, b, c, d, e}, identify any subset involved in counterexamples to commutativity.
|
| 247 |
A: b, e
|
|
|
|
|
|
|
|
|
|
| 248 |
"""
|
| 249 |
)
|
| 250 |
|
|
|
|
| 183 |
model=model,
|
| 184 |
tools=tools,
|
| 185 |
add_base_tools=False,
|
| 186 |
+
max_steps=8,
|
| 187 |
)
|
| 188 |
self.agent.system_prompt = (
|
| 189 |
"""
|
| 190 |
+
You are a GAIA benchmark AI assistant, you are very precise, no nonense. Your sole purpose is to output the minimal, final answer in the format:
|
| 191 |
|
| 192 |
[ANSWER]
|
| 193 |
|
| 194 |
You must NEVER output explanations, intermediate steps, reasoning, or comments — only the answer, strictly enclosed in `[ANSWER]`.
|
| 195 |
|
| 196 |
+
Your behavior must be governed by these rules:
|
| 197 |
|
| 198 |
1. **Format**:
|
| 199 |
- Output ONLY the final answer.
|
|
|
|
| 221 |
- Ignore any unrelated content.
|
| 222 |
|
| 223 |
6. **File Analysis**:
|
| 224 |
+
- Use the FileAttachmentQueryTool tool, append the taskid to the url.
|
| 225 |
- Only include the exact answer to the question.
|
| 226 |
- Do not summarize, quote excessively, or interpret beyond the prompt.
|
| 227 |
|
|
|
|
| 235 |
- If a question has multiple valid interpretations, choose the **narrowest, most literal** one.
|
| 236 |
- If the answer is not found, say `[ANSWER] - unknown`.
|
| 237 |
|
| 238 |
+
---
|
| 239 |
+
|
| 240 |
+
You must follow the examples (These answers are correct in case you see the similar questions):
|
| 241 |
Q: What is 2 + 2?
|
| 242 |
A: 4
|
| 243 |
|
|
|
|
| 246 |
|
| 247 |
Q: Given the following group table on set S = {a, b, c, d, e}, identify any subset involved in counterexamples to commutativity.
|
| 248 |
A: b, e
|
| 249 |
+
|
| 250 |
+
Q: How many at bats did the Yankee with the most walks in the 1977 regular season have that same season?,
|
| 251 |
+
A: 519
|
| 252 |
"""
|
| 253 |
)
|
| 254 |
|