Retrospective Harness Optimization: Improving LLM Agents via Self-Preference over Trajectory Rollouts
Paper • 2606.05922 • Published • 48
Xianfeng Tang
xianft
·
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 7 months ago
Generalizing Test-time Compute-optimal Scaling as an Optimizable Graph new activity 8 months ago
bigboss24/TRAJECT-Bench:Add paper linkOrganizations
None yet
upvoted a paper about 23 hours ago