Skip to content

Fix minor benchmark script bugs #1822

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 6 commits into from
Oct 18, 2025
Merged

Fix minor benchmark script bugs #1822

Changes from 2 commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
59eb951
Fix 'ChatMessage' object is not iterable
suryabdev Oct 15, 2025
c9f7068
Remove additional_authorized_imports from ToolCallingAgent
suryabdev Oct 15, 2025
9387a66
Remove default InferenceClient provider
suryabdev Oct 15, 2025
fddf812
Fix datetime import error
suryabdev Oct 15, 2025
7c59cee
Add authorized_imports to ToolCallingAgent's PythonInterpreterTool
suryabdev Oct 16, 2025
54b3e4d
Merge branch 'main' into fix-benchmark-dict
suryabdev Oct 16, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 1 addition & 2 deletions examples/smolagents_benchmark/run.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -137,7 +137,6 @@ def answer_single_question(example, model, answers_file, action_type):
agent = ToolCallingAgent(
tools=[GoogleSearchTool(provider="serper"), VisitWebpageTool(), PythonInterpreterTool()],
Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Should the default tools be changed so that there is an apples-apples comparison between the ToolCallingAgent and CodeAgent?
Maybe pass the bellow additional_authorized_imports to the PythonInterpreterTool initialization

Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Yes indeed, we should pass the same additional_authorized_imports to PythonInterpreterTool to make it really an even comparison!

Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I'll let ou do the change before merging

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Done

model=model,
additional_authorized_imports=["numpy", "sympy"],
max_steps=10,
)

Expand All @@ -158,7 +157,7 @@ def answer_single_question(example, model, answers_file, action_type):
# Run agent 🚀
answer = str(agent.run(augmented_question))
token_counts = agent.monitor.get_total_token_counts()
intermediate_steps = [dict(message) for message in agent.write_memory_to_messages()]
intermediate_steps = [message.dict() for message in agent.write_memory_to_messages()]

end_time = time.time()
except Exception as e:
Expand Down