most citedYour Group-Relative Advantage Is Biased

1 citations · 1 across the 6 of their papers we have counts for

collaborators
Showing cs.LGShow all

6 papers · 1 filter

cs.LG2026

Toward Plasticity-Preserving KL Regularization for Capability Retention in LLM Reinforcement Learning

Li Wang, Xiaodong Lu, Xiaohan Wang +4

Reinforcement learning (RL) has become a central paradigm for large language model (LLM) post-training, but optimization toward new objectives can degrade capabilities already pres…

cs.LG2026

When Self-Belief Misleads: Active Label Acquisition for Reinforcement Learning with Verifiable Rewards

Li Wang, Xiaodong Lu, Xiaohan Wang +5

Large Language Models (LLMs) have achieved remarkable advancements in reasoning capabilities empowered by Reinforcement Learning with Verifiable Rewards (RLVR). Nonetheless, RLVR i…

cs.LG2026

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning

Zihan Lin, Xiaohan Wang, Jie Cao +6

Reinforcement Learning with Verifiable Rewards (RLVR) enhances reasoning of Large Language Models (LLMs) but usually exhibits limited generation diversity due to the over-incentivi…

cs.LG2026

Policy Improvement Reinforcement Learning

Huaiyang Wang, Xiaojie Li, Xiaohan Wang +10

Reinforcement learning has become a central post-training paradigm for improving LLM and agent capabilities. Yet existing RL post-training methods share a common blind spot: they c…

cs.LG20261 cited

Contextual Rollout Bandits for Reinforcement Learning with Verifiable Rewards

Xiaodong Lu, Xiaohan Wang, Jiajun Chai +7

Reinforcement Learning with Verifiable Rewards (RLVR) is an effective paradigm for improving the reasoning capabilities of large language models. However, existing RLVR methods uti…

cs.LG20261 cited

Your Group-Relative Advantage Is Biased

Fengkai Yang, Zherui Chen, Xiaohan Wang +10

Reinforcement Learning from Verifier Rewards (RLVR) has emerged as a widely used approach for post-training large language models on reasoning tasks, with group-based methods such…