activity
20242026
collaborators
Showing cs.LGShow all

6 papers · 1 filter

cs.LG2026

Leveraging Error Diversity in Group Rollouts for Reinforcement Learning

Wenpu Liu, Yuqi Xu, Weichu Xie +8

Reinforcement Learning from Verifiable Rewards (RLVR) typically samples multiple responses per prompt and assigns binary rewards based on individual correctness, yet the collective…

cs.LG2026

Right Makes Might: Aligning Verified Hidden States Empowers RL Reasoning

Ziyue Wang, Aomufei Yuan, Yongfu Zhu +10

Reinforcement Learning from Verifiable Rewards (RLVR) has become the dominant approach for improving mathematical reasoning in large language models, yet current methods reduce eac…

cs.LG2026

Step-wise Rubric Rewards for LLM Reasoning

Weichu Xie, Haozhe Zhao, Wenpu Liu +15

Reinforcement Learning with Verifiable Rewards (RLVR) is widely used to improve reasoning in large language models, but rewards only final-answer correctness with no supervision ov…

cs.LG2026

Co-Evolving Policy Distillation

Naibin Gu, Chenxu Yang, Qingyi Si +7

RLVR and OPD have become standard paradigms for post-training. We provide a unified analysis of these two paradigms in consolidating multiple expert capabilities into a single mode…

cs.LG2026

Near-Future Policy Optimization

Chuanyu Qin, Chenxu Yang, Qingyi Si +6

Reinforcement learning with verifiable rewards (RLVR) has become a core post-training recipe. Introducing suitable off-policy trajectories into on-policy exploration accelerates RL…

cs.LG2026

Self-Distilled RLVR

Chenxu Yang, Chuanyu Qin, Qingyi Si +7

On-policy distillation (OPD) has become a popular training paradigm in the LLM community. This paradigm selects a larger model as the teacher to provide dense, fine-grained signals…