Badge
#483 of 3355 in Artificial Intelligence (All Time)
Retrospective Harness Optimization: Improving LLM Agents via Self-Preference over Trajectory Rollouts
arXiv
Paper details·Week 23, 2026 leaderboard·All Time leaderboard

Share your achievement

Are you one of the authors? Share this badge on social media.

Download image

Congratulate the authors

Know the authors? Send them a congratulation.