Retrospective Harness Optimization: Improving LLM Agents via Self-Preference over Trajectory Rollouts
Paper • 2606.05922 • Published • 36
Qianhui WU
qianhuiwu
AI & ML interests
None yet
Recent Activity
upvoted a paper about 5 hours ago
Retrospective Harness Optimization: Improving LLM Agents via Self-Preference over Trajectory Rollouts updated a dataset 8 days ago
OpenWebRL/OpenWebRL-RL-Tasks updated a dataset 9 days ago
OpenWebRL/OpenWebRL-SFT-TrajectoriesOrganizations
upvoted a paper about 5 hours ago
updated a
dataset 8 days ago
updated a
dataset 9 days ago
published a
dataset 15 days ago
upvoted an article 19 days ago
Article
A Guide to Reinforcement Learning Post-Training for LLMs: PPO, DPO, GRPO, and Beyond
karina-zadorozhny
• • 26 upvoted a paper 26 days ago
submitted a
paper to Daily Papers 26 days ago
upvoted a paper about 1 month ago
liked a
dataset 2 months ago
authored 7
papers 3 months ago
Mitigate Position Bias in Large Language Models via Scaling a Single Dimension
Paper • 2406.02536 • Published
Multi-Level Knowledge Distillation for Out-of-Distribution Detection in Text
Paper • 2211.11300 • Published • 1
On Memory Construction and Retrieval for Personalized Conversational Agents
Paper • 2502.05589 • Published
Dyna-Mind: Learning to Simulate from Experience for Better AI Agents
Paper • 2510.09577 • Published • 8
GUI-360: A Comprehensive Dataset and Benchmark for Computer-Using Agents
Paper • 2511.04307 • Published • 16
Adapting Web Agents with Synthetic Supervision
Paper • 2511.06101 • Published • 7
GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL
Paper • 2602.22190 • Published • 17
liked a
model 3 months ago
upvoted a paper 3 months ago
upvoted 2
papers 7 months ago