Not Every Token Is Worth Distilling: Selective Supervision for Direct-OPD
Paper • 2609.29142 • Published • 1
Zixuan Yang
Luli3220
AI & ML interests
Post Training、RL
Recent Activity
upvoted a paper about 1 hour ago
Not Every Token Is Worth Distilling: Selective Supervision for Direct-OPD submitted a paper about 2 hours ago
Not Every Token Is Worth Distilling: Selective Supervision for Direct-OPD upvoted a paper 4 months ago
When Tools Fail: Benchmarking Dynamic Replanning and Anomaly Recovery in LLM AgentsOrganizations
None yet
upvoted a paper about 1 hour ago
upvoted 4
papers 4 months ago
When Tools Fail: Benchmarking Dynamic Replanning and Anomaly Recovery in LLM Agents
Paper • 2606.05806 • Published • 24
MERIT: Matching Expertise via Rubric-Informed Training for Reviewer Assignment
Paper • 2605.27865 • Published • 1
Retrieval, Reward, and Training Protocols: What Matters in Training Search Agents?
Paper • 2605.27881 • Published • 10
Skill0.5: Joint Skill Internalization and Utilization for Out-of-Distribution Generalization in Agentic Reinforcement Learning
Paper • 2605.28424 • Published • 28