SMOPD: Multi-Reward Reinforcement Learning via Specialize-and-Merge Online Policy Distillation
Paper • 2608.03092 • Published • 10
chenjiangwang
jwchen2001
AI & ML interests
None yet
Recent Activity
upvoted a paper 8 days ago
CoRT: Counterfactual Replay for Token-Level Rubric-Guided Policy OptimizationOrganizations
None yet
upvoted a paper 2 days ago
upvoted 2
papers 8 days ago
submitted a
paper to Daily Papers 8 days ago
authored 4
papers 9 days ago
DecoEvo: Score-Decoupled Co-Evolution of Solver and Rubric-Generator Skills in Text Space
Paper • 2607.25675 • Published • 65
From Proprietary to Open-Source: Bridging the Distribution Gap via Multi-Agent Protocol Distillation in Agentic Search
Paper • 2607.24280 • Published • 82
OnePred: Next-Query Prediction via Recursive Intent Memory in Multi-Turn Conversations
Paper • 2605.23668 • Published • 1
Co-ReAct: Rubrics as Step-Level Collaborators for ReAct Agents
Paper • 2605.23590 • Published • 2
upvoted a paper 10 days ago