3 papers
cs.AI2026
Solving Without Stopping: On-Policy Distillation at Small Scale
Hongyang Li, Yiming Zhu, Xiao Li +3
On-policy distillation, where a student learns from a stronger teacher's feedback on its own outputs, is a common way to pass reasoning to smaller models. We analyze what it transf…
cs.LG2026
Unlocking the Critic: Reward-Free Policy Optimization for LLM Post-Training
Hongyang Li, Xiao Li, Caesar Wu +3
Recent approaches to reinforcement learning (RL) post-training for large language models increasingly remove the critic to reduce training instability and memory overhead. Even whe…
cs.LG2026
Beyond Compression: Diagnosing How Post-Training Changes Mathematical Reasoning
Hongyang Li, Yiming Zhu, Xiao Li +3
Post-training is central to mathematical reasoning in modern large language models (LLMs), but endpoint pass@1 alone underidentifies what has changed. Gains may reflect newly reach…