Retrospective Harness Optimization: Improving LLM Agents via Self-Preference over Trajectory Rollouts
Paper • 2606.05922 • Published • 48
Shujie Liu
j4ckl1u
AI & ML interests
None yet
Recent Activity
upvoted a paper about 23 hours ago
Retrospective Harness Optimization: Improving LLM Agents via Self-Preference over Trajectory Rollouts upvoted a paper 17 days ago
Lens: Rethinking Training Efficiency for Foundational Text-to-Image Models liked a model 5 months ago
microsoft/VibeVoice-ASROrganizations
None yet