OpenHands icon indicating copy to clipboard operation
OpenHands copied to clipboard
verified publisher icon All-Hands-AI

Ketan simplified co act workflow

Open ketan1741 opened this issue 1 year ago • 3 comments

Short description of the problem this fixes or functionality that this introduces. This may be used for the CHANGELOG

  • This PR implements a simplified multi-agent workflow inspired by the CoAct paper.
  • Currently, in swe-bench eval, there are complex instances that OpenHands fails, especially ones that single CodeActAgent overlooks the buggy location. If we have a grounding test case for the issue, this workflow seems to help.
  • An overkill-ish successful trajectory with replanning can be found here.
  • A task which CoActPlannerAgent finished but CodeActAgent failed (I expected both to be able to complete it): CoAct traj CodeAct traj

Give a summary of what the PR does, explaining any non-trivial design decisions

  • Modify CodeAct to make it accept delegated task.
  • Implement 2 new agents, planner and executor with the same abilities as CodeAct, different system prompts, additional action parsers.

Link of any specific issues this addresses

ketan1741 avatar Sep 09 '24 20:09 ketan1741

Hey @ketan1741 , I'm confused. How does this relate to https://github.com/All-Hands-AI/OpenHands/pull/3770 ?

neubig avatar Sep 10 '24 00:09 neubig

Hey @ketan1741 , I'm confused. How does this relate to #3770 ?

Hey, Prof. @neubig! Hoang wanted me to have a different branch if I were to make updates to our workflow implementation to make it more reliable/improve it.

ketan1741 avatar Sep 10 '24 00:09 ketan1741

Ah, I see. We can figure this out.

neubig avatar Sep 10 '24 01:09 neubig

This PR is stale because it has been open for 30 days with no activity. Remove stale label or comment or this will be closed in 7 days.

github-actions[bot] avatar Oct 27 '24 02:10 github-actions[bot]

Hi @ketan1741 this PR was marked as stale because it hasn't had any activity in 30 days. Did you want to close it and reopen if it became ready again? Or is it being actively worked on?

mamoodi avatar Nov 01 '24 15:11 mamoodi

Hi @ketan1741 this PR was marked as stale because it hasn't had any activity in 30 days. Did you want to close it and reopen if it became ready again? Or is it being actively worked on?

Hey! Thanks for checking in. Yes, sorry I forgot to close this PR. I am working on it on a different branch after the latest refactoring. I will open a new one once I feel it is ready.

cc: @srishti-chouhan @bhaavanaa

ketan1741 avatar Nov 01 '24 17:11 ketan1741