Retrospective Harness Optimization: Improving LLM Agents via Self-Preference over Trajectory Rollouts
Paper • 2606.05922 • Published • 67
Zhiwei
Arlene4869
·
AI & ML interests
Multimodality Interaction, Embodied AI
Recent Activity
new activity 7 days ago
BAAI-Agents/SWITCH:Add SWITCH MCQ public test 1500 upvoted a paper 12 months ago
DualTHOR: A Dual-Arm Humanoid Simulation Platform for Contingency-Aware
PlanningOrganizations
