4 papers
REOPD: Reliability-Adaptive Reward Extrapolation for On-Policy Distillation
Yang Sun, Lichao Ma, Houyuan Qin +5
On-policy distillation (OPD) trains a student on its own trajectories under dense token-level supervision from a teacher. Reward-extrapolation methods such as ExOPD amplify the tea…
Attention Illuminates LLM Reasoning: The Preplan-and-Anchor Rhythm Enables Fine-Grained Policy Optimization
Yang Li, Zhichen Dong, Yuhan Sun +9
The reasoning pattern of Large language models (LLMs) remains opaque, and reinforcement learning (RL) typically applies uniform credit across an entire generation, blurring the dis…
Asymmetric Proximal Policy Optimization: mini-critics boost LLM reasoning
Jiashun Liu, Johan Obando-Ceron, Han Lu +7
Most recent RL for LLMs (RL4LLM) methods avoid explicit critics, replacing them with average advantage baselines. This shift is largely pragmatic: conventional value functions are…
Part II: ROLL Flash -- Accelerating RLVR and Agentic Training with Asynchrony
Han Lu, Zichen Liu, Shaopan Xiong +19
Synchronous Reinforcement Learning (RL) post-training has emerged as a crucial step for enhancing Large Language Models (LLMs) with diverse capabilities. However, many systems desi…