3 papers
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…
cs.MA2025
Nucleolus Credit Assignment for Effective Coalitions in Multi-agent Reinforcement Learning
Yugu Li, Zehong Cao, Jianglin Qiao +1
In cooperative multi-agent reinforcement learning (MARL), agents typically form a single grand coalition based on credit assignment to tackle a composite task, often resulting in s…