RL for Language Model Reasoning

RL: Reinforcement Learning

Follow this topic Ask about this topic

Momentum

91 papers in the last four weeks, up 176% on the four weeks before. 0.9% of all new papers.

Jul 13Week of Sep 28

Latest papers 707

All topics

Enhancing the Code Reasoning Capabilities of LLMs via Consistency-based Reinforcement Learning
May 18, 2026Zhanyue Qin, Jia Feng, Yibo Lyu +4Reinforcement Learning RL for Language Model Reasoning
Harbin Institute of Technology · The Chinese University of Hong Kong
Entropy-Gradient Inversion: Moving Toward Internal Mechanism of Large Reasoning Models
May 18, 2026Junyao Yang, Chen Qian, Kun Wang +4LLM Interpretability RL for Language Model Reasoning
National University of Singapore · Renmin University of China · Nanyang Technological University +1
SAPO: Step-Aligned Policy Optimization for Reasoning-Based Generative Recommendation
May 17, 2026Zaiyi Zheng, Guanghui Min, Yaochen Zhu +4RL for Language Model Reasoning Credit Assignment in RL
University of Virginia · 2Nokia
How Off-Policy Can GRPO Be? Mu-GRPO for Efficient LLM Reinforcement Learning
May 17, 2026Minghao Tian, Yunfei Xie, Chen WeiRL for Language Model Reasoning Group Relative Policy Optimization
Rice University
Self-Supervised On-Policy Distillation for Reasoning Language Models
May 17, 2026Zhiquan Tan, Yinrong HongRL for Language Model Reasoning Process Supervision
Tsinghua University · Beihang University
Leveraging Error Diversity in Group Rollouts for Reinforcement Learning
May 17, 2026Wenpu Liu, Yuqi Xu, Weichu Xie +8Reward Shaping RL for Language Model Reasoning
Peking University · Shanghai Innovation Institute
Weak-to-Strong Elicitation via Mismatched Wrong Drafts
May 17, 2026Wei DengRL for Language Models RL for Language Model Reasoning
Independent Researcher
Reasoning Before Diagnosis: Physician-Inspired Structured Thinking for ECG Classification
May 17, 2026Yang Wu, Xiaoyan Yuan, Hau-San Wong +1RL for Language Model Reasoning Electrocardiogram Classification
1City University of Hong Kong · 2Beijing Institute of Technology · 3Shenzhen MSU-BIT University
DISA: Offline Importance Sampling for Distribution-Matching LLM-RL
May 17, 2026Shaobo Wang, Yujie Chen, Yafeng Sun +9Reinforcement Learning RL for Language Model Reasoning
Shanghai Jiao Tong University · The Hong Kong University of Science and Technology (Guangzhou) · The University of Science and Technology of China +2
D $^2$ Evo: Dual Difficulty-Aware Self-Evolution for Data-Efficient Reinforcement Learning
May 16, 2026Ru Zhang, Renda Li, Ziyu Ma +4RL for Language Model Reasoning Curriculum RL
Alibaba Group · AMAP, Alibaba Group · BUPT
Learning-Zone Energy: Online Data Selection for Efficient RL Post-Training
May 16, 2026Peng Cui, Boyao Yang, Jun ZhuRL for Language Model Reasoning RL Post-Training
Dept. of Comp. Sci. & Tech., Institute for AI, BNRist Center, Tsinghua-Bosch Joint ML Center, THBI Lab, Tsinghua University, Beijing 100084, China · Dept. of Automation, Tsinghua University, Beijing 100084, China
The Unlearnability Phenomenon in RLVR for Language Models
May 16, 2026Yulin Chen, He He, Chen ZhaoReinforcement Learning RL for Language Model Reasoning
1New York University · 2NYU Shanghai
PopuLoRA: Co-Evolving LLM Populations for Reasoning Self-Play
May 16, 2026Roger Creus Castanyer, Geoffrey Bradway, Lorenz Wolf +3Self-Play RL RL for Language Model Reasoning
Vmax
Nudging Beyond the Comfort Zone: Efficient Strategy-Guided Exploration for RLVR
May 15, 2026Chanuk Lee, Sangwoo Park, Minki Kang +1RL for Language Model Reasoning RL Exploration
KAIST
SAGE: Shaping Anchors for Guided Exploration in RLVR of LLMs
May 15, 2026Chanuk Lee, Minki Kang, Sung Ju HwangKL-Regularized RL RL for Language Model Reasoning
KAIST
VSPO: Vector-Steered Policy Optimization for Behavioral Control
May 15, 2026Xuechen Zhang, Zijian Huang, Kai Yang +3Language Model Steering RL for Language Model Reasoning
University of Michigan
GRLO: Towards Generalizable Reinforcement Learning in Open-Ended Environments from Zero
May 14, 2026Shangjian Yin, Yu Fu, Yue Dong +1Reinforcement Learning RL for Language Model Reasoning
University of California, Riverside
Learning from Language Feedback via Variational Policy Distillation
May 14, 2026Yang Li, Erik Nijkamp, Semih Yavuz +1On-Policy Self-Distillation RL for Language Model Reasoning
Salesforce AI Research
Boosting Reinforcement Learning with Verifiable Rewards via Randomly Selected Few-Shot Guidance
May 14, 2026Kai Yan, Alexander G. Schwing, Yu-Xiong WangRL for Language Model Reasoning Reinforcement Learning with Verifiable Rewards
University of Illinois Urbana-Champaign
Learning from Failures: Correction-Oriented Policy Optimization with Verifiable Rewards
May 14, 2026Mengjie Ren, Jie Lou, Boxi Cao +6RL for Code Generation LLM Self-Correction
Chinese Information Processing Laboratory, Institute of Software, Chinese Academy of Sciences · University of Chinese Academy of Sciences · Xiaohongshu Inc.
Prompting Policies for Multi-step Reasoning and Tool-Use in Black-box LLMs with Iterative Distillation of Experience
May 14, 2026Krishna Sayana, Ketan Todi, Ambarish JashRL for Language Models LLM Prompting
Google Research, Mountain View, CA
Learning to Build the Environment: Self-Evolving Reasoning RL via Verifiable Environment Synthesis
May 14, 2026Yucheng Shi, Zhenwen Liang, Kishan Panaganti +3Reinforcement Learning RL for Language Model Reasoning
Tencent HY LLM
Reinforcement Learning for Tool-Calling Agents in Fast Healthcare Interoperability Resources (FHIR)
May 13, 2026Marius S. Knorr, Robert Müller, Jan P. Bremer +1Healthcare RL for Language Model Reasoning
IDM gGmbH, University Medical Center Hamburg-Eppendorf, Hamburg, Germany · Aganthos
Physics-R1: An Audited Olympiad Corpus and Recipe for Visual Physics Reasoning
May 13, 2026Shan YangVisual Reasoning RL for Language Model Reasoning
Independent Researcher
Beyond Mode-Seeking RL: Trajectory-Balance Post-Training for Diffusion Language Models
May 13, 2026Saba Ahmadi, Prasanna Parthasarathi, Yufei CuiRL for Language Model Reasoning RL for Diffusion Models
Noah’s Ark Lab
STRIDE: Learnable Stepwise Language Feedback for LLM Reasoning
May 13, 2026Junjie Zhang, Guozheng Ma, Shunyu Liu +5RL for Language Model Reasoning Process Supervision
Generative AI Lab, College of Computing and Data Science, Nanyang Technological University, Singapore 639798 · Tongyi Lab, Alibaba Group
Achieving Gold-Medal-Level Olympiad Reasoning via Simple and Unified Scaling
May 13, 2026Yafu Li, Runzhe Zhan, Haoran Zhang +25RL for Language Model Reasoning LLM Mathematical Reasoning
Shanghai AI Laboratory · The Chinese University of Hong Kong · Shanghai Jiao Tong University +2
Respecting Self-Uncertainty in On-Policy Self-Distillation for Efficient LLM Reasoning
May 13, 2026Junlong Ke, Zichen Wen, Weijia Li +2On-Policy Self-Distillation RL for Language Model Reasoning
2Tsinghua University · 1Shanghai Jiao Tong University · 3Shanghai AI Laboratory
Teacher-Guided Policy Optimization for On-Policy Reasoning Distillation under Large Policy Divergence
May 13, 2026Xinyu Liu, Kechen Jiao, Chunyang Xiao +10RL for Language Model Reasoning Policy Optimization
School of Computer Science and Engineering, Northeastern University, China · Tsinghua University · Meituan +2
TEMPO: Temporal Enforcement via Mode-Separated Policy Optimization for Trustworthy LLM Backtesting
May 13, 2026Zeyu Zhang, Bradly C. StadieLLM Evaluation RL for Language Model Reasoning
Department of Statistic and Data Science Northwestern University

May 18, 2026, cs.LGJ/K move · Enter open · S save

Enhancing the Code Reasoning Capabilities of LLMs via Consistency-based Reinforcement Learning

Zhanyue Qin, Jia Feng, Yibo Lyu, Yun Peng+3

Harbin Institute of Technology · The Chinese University of Hong Kong

Reinforcement Learning RL for Language Model Reasoning

Open paper AskPDF arXiv

Code reasoning refers to the task of predicting the output of a program given its source code and specific inputs. It can measure the reasoning capability of large language models (LLMs) and also benefit downstream tasks such as code generation and mathematical reasoning. Existing work has verified the effectiveness of reinforcement learning on the task. However, these methods design rewards solely based on final outputs or coarse-grained signals, and neglect the inherent consistency of the stepwise reasoning process in the task. Therefore, these methods often result in sparse reward or reward hacking, which limits the full play of enhanced learning capabilities. To alleviate these issues, we propose CodeThinker, a consistency-driven reinforcement learning framework for code reasoning. Specifically, CodeThinker has three key components: (1) a stepwise reasoning-aware model training module, which utilizes a consistency tracing paradigm as a template to synthesize training data that captures the stepwise reasoning process; (2) a dynamic beam sampling strategy, which aims to improve the quality of sampled outputs under a fixed sampling budget; and (3) a consistency reward mechanism that can effectively alleviate reward hacking. Experiments on three popular benchmarks show that CodeThinker achieves state-of-the-art performance across multiple LLMs. For instance, it outperforms the strongest baseline by 4.3% in accuracy when deployed on Qwen2.5-Coder-7B-Instruct. We also validate the effectiveness of CodeThinker on downstream tasks. Results show that, without additional training, CodeThinker obtains average accuracy gains of 5.33 and 3.11 percentage points on mathematical reasoning and code reasoning tasks covering 17 programming languages, respectively.

Momentum

Related topics

Latest papers 707