Skip to content
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.

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

Example demonstrating multi-agent system using smolagents #13

Open
haesleinhuepf opened this issue Dec 30, 2024 · 1 comment
Open

Example demonstrating multi-agent system using smolagents #13

haesleinhuepf opened this issue Dec 30, 2024 · 1 comment

Comments

@haesleinhuepf
Copy link
Contributor

haesleinhuepf commented Dec 30, 2024

Hi again @aymeric-roucher ,

I just wrote an example notebook about how to let multiple smolagents write a manuscript together and I'm curious about two things:

  • Would this example notebook be in scope for your repository as example? I could clean it a bit up (depending in your feedback) and send a PR if this makes sense.
  • Is there room for improvement? I'm in particular curious if the implementation of the scheduler agent makes sense.

Feedback welcome!

Best,
Robert

@rishabhmehrotra
Copy link

rishabhmehrotra commented Jan 1, 2025

@haesleinhuepf great notebook, thanks for sharing -- it was quite helpful to see multiple agents interacting via the scheduler. the prompt_scadsai_llm function in the notebook makes the setup less self-contained to run independently. I'm guessing prompt calls to the function in the Scientific writer and reviewer agents can easily be replaced by an LLM call reusing smolagents components? This might make the notebook self-contained.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants