Grouped interleave for multi-agent systems #1532
Draft
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Collaborator
Author
|
@cursoragent please review |
|
Unable to authenticate your request. Please make sure to connect your GitHub account to Cursor. Go to Cursor |
Collaborator
Author
|
@cursoragent please review! |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
In multi-agent systems like the RLM, there are several independent, multi-turn trajectories. We want to interleave the TrajectorySteps within each such multi-turn trajectory for efficiency, but keep the trajectories of the different sub-agents separate.
verifiers PR#675 introduces the
trajectory_idfield as a first-class field inTrajectoryStep. This enables us to perform grouped interleaving of trajectory steps, implemented by this PR.