[Question] Inquiry About text_webbrowser_agent Implementation in open_deep_search

[callanwu]

I recently came across the implementation of the text_webbrowser_agent within the open_deep_search project.

smolagents/examples/open_deep_research/run.py

Lines 111 to 128 in 9498094

	text_webbrowser_agent = ToolCallingAgent(
	model=model,
	tools=WEB_TOOLS,
	max_steps=20,
	verbosity_level=2,
	planning_interval=4,
	name="search_agent",
	description="""A team member that will search the internet to answer your question.
	Ask him for all your questions that require browsing the web.
	Provide him as much context as possible, in particular if you need to search on a specific timeframe!
	And don't hesitate to provide him with a complex search task, like finding a difference between two webpages.
	Your request must be a real sentence, not a google search! Like "Find me this information (...)" rather than a few keywords.
	""",
	provide_run_summary=True,
	)
	text_webbrowser_agent.prompt_templates["managed_agent"]["task"] += """You can navigate to .txt online files.
	If a non-html page is in another format, especially .pdf or a Youtube video, use tool 'inspect_file_as_text' to inspect it.
	Additionally, if after some searching you find out that you need more information to answer the question, you can use `final_answer` with your request for clarification as argument to request for more information."""

I noticed that the text_webbrowser_agent is implemented using ToolCallingAgent. Could you please clarify the rationale behind using ToolCallingAgent for the text_webbrowser_agent instead of CodeAgent? I recall that your blog highlighted several advantages of CodeAgent in blog.

[albertvillanova]

Thanks for your question, @callanwu. Maybe @aymeric-roucher can give more information about the rationale for that choice.