Skip to content

Puppeteer seems to always produce identical selection and highly simlar workflow #640

@OOGZleo

Description

@OOGZleo

Thanks for your excellent work on Puppeteer! I do believe this is the correct direction for future multi-agent systems.
However, I found that after training the orchestrator for the MMLU-pro task using the provided configuration, it always produces the same topology with the same agent choice: arxiv -> concluder -> terminator. It seems to overfit to the same selection regardless of the intermediate output state, even when I explicitly change it. I think maybe the task is too simple for the agents, and the training does not really consider a complex scenario (e.g, where the intermediate agent needs help from another agent).
I really like the idea of puppeteer, and I think it is one of the only studies that considers a dynamic workflow design based on task state. Please let me know if you observed a similar pattern when you trained the model, and if so, do you have any plan to improve the orchestrator?

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type
    No fields configured for issues without a type.

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions