arXiv Machine Learning June 3, 2026 By Chuanyu Qin, Chenxu Yang, Qingyi Si, Naibin Gu, Peng Fu, Zheng Lin

Learning to Solve, Forgetting to Retain: Correct-Set Turnover in RLVR

Read the original on arXiv Machine Learning →

arXiv:2606. 03087v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) improves the ability of large language model, yet headline accuracy gains often conceal a hidden cost: previously solved problems quietly become unsolvable as training proceeds.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv AI

Jun 19

Beyond Reasoning Gains: Mitigating General-Capability Forgetting in Large Reasoning Models

arXiv:2510. 21978v2 Announce Type: replace-cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has delivered impressive gains in mathematical and multimodal reasoning and has become a standard post-training paradigm for contemporary language and vision-language models.

By Hoang Phan, Xianjun Yang, Yuanshun Yao, Jingyu Zhang, Shengjie Bi, Xiaocheng Tang, Madian Khabsa, Lijuan Liu, Deren Lei

llms reinforcement-learning multimodal benchmarks

arXiv Machine Learning

Jun 4

Policy Improvement Reinforcement Learning

arXiv:2604. 00860v3 Announce Type: replace Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has become a central post-training paradigm for improving the reasoning capabilities of large language models.

By Huaiyang Wang, Xiaojie Li, Deqing Wang, Haoyi Zhou, Zixuan Huang, Yaodong Yang, Jianxin Li, Yikun Ban

llms reinforcement-learning benchmarks

arXiv AI

Jul 8

Self-Review Reinforcement Learning (SRRL) with Cross-Episode Memory and Policy Distillation

arXiv:2607. 05541v1 Announce Type: cross Abstract: Reinforcement Learning is commonly used to train large language models using environmental feedback.

By Muhammad Zain Amin, Kibele Sebnem Yildirim

llms reinforcement-learning efficiency benchmarks

arXiv AI

4d ago

Unlocking the Critic: Reward-Free Policy Optimization for LLM Post-Training

arXiv:2609.37119v1 Announce Type: cross Abstract: Recent approaches to reinforcement learning (RL) post-training for large language models increasingly remove the critic to reduce training instabilit...

By Hongyang Li, Xiao Li, Caesar Wu, Said Mammar, Gr\'egoire Danoy, Pascal Bouvry

llms reinforcement-learning safety

arXiv AI

Aug 18

Delay, Plateau, or Collapse: Evaluating the Impact of Systematic Verification Error on RLVR

arXiv:2605. 02909v2 Announce Type: replace-cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has become a powerful approach for improving the reasoning capabilities of large language models (LLMs).

By Kazuki Egashira, Mark Vero, Jasper Dekoninck, Florian E. Dorner, Robin Staab, Martin Vechev

llms reinforcement-learning

arXiv AI

Jul 14

Nested-ReFT: Efficient Reinforcement Learning for Large Language Model Fine-Tuning via Off-Policy Rollouts

arXiv:2508. 10123v3 Announce Type: replace-cross Abstract: Advanced reasoning in LLMs on challenging domains like mathematical reasoning can be tackled using verifiable rewards based reinforced fine-tuning (ReFT).

By Maxime Heuillet, Yufei Cui, Boxing Chen, Audrey Durand, Prasanna Parthasarathi

llms reinforcement-learning fine-tuning benchmarks safety

One email a morning, machine-written

Related stories

Beyond Reasoning Gains: Mitigating General-Capability Forgetting in Large Reasoning Models

Policy Improvement Reinforcement Learning

Self-Review Reinforcement Learning (SRRL) with Cross-Episode Memory and Policy Distillation

Unlocking the Critic: Reward-Free Policy Optimization for LLM Post-Training

Delay, Plateau, or Collapse: Evaluating the Impact of Systematic Verification Error on RLVR

Nested-ReFT: Efficient Reinforcement Learning for Large Language Model Fine-Tuning via Off-Policy Rollouts