Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
Can We Trust the Teacher? Decoupled Credit Direction-Magnitude for Self-Distillation
Yugu Li, Zehong Cao, Peizhen Li +3
RLVR provides reliable trajectory-level credit, while OPSD offers dense supervision for token-level credit. This exposes a fundamental coupling when updating step-level credit dire…
cs.AI2026
RTPO: Reverse-Turn Policy Optimization for Stabilizing Agentic RL Training
Yugu Li, Zehong Cao, Jianglin Qiao +1
Training multi-turn agentic workflows with reinforcement learning (RL) enables large language models to perform complex reasoning, use external tools, and conduct iterative search…