Skip to content

Conversation

@yuchengyue
Copy link
Collaborator

@yuchengyue yuchengyue commented Sep 17, 2025

fix: agent training

  1. Add llm_api_key parameter
  2. Improve handling of trajectories with non-assistant final messages
  3. Update Gaia reward calculation
  4. Correct the generation of response_ids and response_mask

@rainsonGain rainsonGain merged commit 2d8411e into main Sep 17, 2025
1 check passed
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

Successfully merging this pull request may close these issues.

3 participants