activity
20242026
most citedThe N+ Implementation Details of RLHF with PPO: A Case Study on TL;DR Summarization

2 citations · 4 across the 24 of their papers we have counts for

collaborators
Showing cs.LGShow all

8 papers · 1 filter

cs.LG2026

Staleness-Learning Rate Scaling Laws for Asynchronous RLHF

Jingwei Song, Haofeng Xu, Jie Xiao +8

High-throughput RLHF systems often decouple rollout generation from policy optimization, leading to the use of stale rollouts during learner updates. In this work, we study the eff…

cs.LG2026

The Mirage of Optimizing Training Policies: Monotonic Inference Policies as the Real Objective for LLM Reinforcement Learning

Jing Liang, Hongyao Tang, Yi Ma +9

Reinforcement learning (RL) has gained growing attention in large language model (LLM) post-training, yet RL training remains fragile and can suffer from instability or collapse. O…

cs.LG2026

How Does Reasoning Flow? Tracing Attention-Induced Information Flow for Targeted RL in LLMs

Zhichen Dong, Yang Li, Yuhan Sun +9

Token-level credit assignment remains a key obstacle for reinforcement learning (RL) in large language models (LLMs), where RL recipes typically treat all tokens equally, failing t…

cs.LG2026

One Sample to Rule Them All: Extreme Data Efficiency in Multidiscipline Reasoning with Reinforcement Learning

Yiyuan Li, Zhen Huang, Yanan Wu +6

The reasoning ability of large language models (LLMs) can be unleashed with reinforcement learning (RL) (OpenAI, 2024; DeepSeek-AI et al., 2025a; Zeng et al., 2025). The success of…

cs.LG2025

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…

cs.LG2025

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…