Reinforcement Learning

Also known as RL

Follow this topic Ask about this topic

Momentum

144 papers in the last four weeks, up 243% on the four weeks before. 1.4% of all new papers.

Jul 13Week of Sep 28

Latest papers 1,138

All topics

Why Does Reinforcement Learning Generalize? A Feature-Level Mechanistic Study of Post-Training in Large Language Models
Apr 27, 2026Dan Shi, Zhuowen Han, Simon Ostermann +3Reinforcement Learning RL for Language Model Reasoning
TJUNLP Lab, School of Computer Science and Technology, Tianjin University, China · German Research Center for Artificial Intelligence (DFKI), Saarbrücken, Germany · Saarland University, Saarbrücken, Germany
asRoBallet: Closing the Sim2Real Gap via Friction-Aware Reinforcement Learning for Underactuated Spherical Dynamics
Apr 27, 2026Fang Wan, Guangyi Huang, Tianyu Wu +5Humanoid Robot Locomotion Reinforcement Learning
Southern University of Science and Technology · Shenzhen, China · The University of Hong Kong +4
SpecRLBench: A Benchmark for Generalization in Specification-Guided Reinforcement Learning
Apr 27, 2026Zijian Guo, İlker Işık, H. M. Sabbir Ahmad +1RL Benchmarks Reinforcement Learning
Boston University
Hierarchical Behaviour Spaces
Apr 27, 2026Michael Tryfan Matthews, Anssi Kanervisto, Jakob Foerster +3Reinforcement Learning Hierarchical RL
Meta Superintelligence Labs · University of Oxford
A Reward-Free Viewpoint on Multi-Objective Reinforcement Learning
Apr 27, 2026Ying-Tu Chen, Wei Hung, Bing-Shu Wu +2Multi-Objective Reinforcement Learning Reinforcement Learning
National Yang Ming Chiao Tung University, Hsinchu, Taiwan · Massachusetts Institute of Technology
DPEPO: Diverse Parallel Exploration Policy Optimization for LLM-based Agents
Apr 27, 2026Junshuo Zhang, Chengrui Huang, Feng Guo +6Reinforcement Learning RL Exploration
University of Electronic Science and Technology of China · DiDi
Model-Free Inference of Investor Preferences: A Relative Entropy IRL Approach
Apr 27, 2026Chen XuReward Modeling Reinforcement Learning
Department of Engineering, Shenzhen MSU-BIT University. Address: 1 International University Park Road, Longgang District, Shenzhen, Guangdong, China.
Scalable Production Scheduling: Linear Complexity via Unified Homogeneous Graphs
Apr 26, 2026Jonathan Hoss, Moritz Link, Noah KlarmannGraph Neural Networks Reinforcement Learning
Faculty of Management and Engineering, Rosenheim Technical University of Applied Sciences, Germany
GIFT: Global stabilisation via Intrinsic Fine Tuning
Apr 25, 2026Rory Young, Nicolas PugeaultRL Control Reinforcement Learning
School of Computing Science University of Glasgow
K-Score: Kalman Filter as a Principled Alternative to Reward Normalization in Reinforcement Learning
Apr 24, 2026Zixuan Xia, Quanxi LiReinforcement Learning Policy Gradient Methods
University of Bern, Bern, Switzerland.
Preserve Support, Not Correspondence: Dynamic Routing for Offline Reinforcement Learning
Apr 24, 2026Zhancun Mu, Guangyu Zhao, Yiwu Zhong +1Reinforcement Learning Offline RL
School of Intelligence Science and Technology, Peking University
Do Not Imitate, Reinforce: Iterative Classification via Belief Refinement
Apr 23, 2026Mahdi Kallel, Johannes Tölle, Ahmed Hendawy +1Reinforcement Learning Classification
Center for Artificial Intelligence and Data Science, University of Würzburg · Department of Computer Science, Technical University of Darmstadt
Insect-inspired modular architectures as inductive biases for reinforcement learning
Apr 23, 2026Anne E. StaplesRL Control Reinforcement Learning
Department of Mechanical Engineering, Virginia Tech, Blacksburg, Virginia 24061, USA
Replay-buffer engineering for noise-aware quantum circuit optimization
Apr 23, 2026Akash Kundu, Sebastian FeldReinforcement Learning Experience Replay
Delft University of Technology, Delft, The Netherlands · Quantum Computing Division, QuTech, The Netherlands
Task-specific Subnetwork Discovery in Reinforcement Learning for Autonomous Underwater Navigation
Apr 23, 2026Yi-Ling Liu, Melvin Laux, Mariela De Lucas Alvarez +2Reinforcement Learning Underwater Robotics
Robotics Innovation Center, German Research Center for Artificial Intelligence, Bremen, Germany · Robotics Research Group, University of Bremen, Bremen, Germany
Dynamical Priors as a Training Objective in Reinforcement Learning
Apr 23, 2026Sukesh SubaharanReinforcement Learning Policy Gradient Methods
Coimbatore Medical College Coimbatore, TN India
Understanding and Mitigating Spurious Signal Amplification in Test-Time Reinforcement Learning for Math Reasoning
Apr 23, 2026Yongcan Yu, Lingxiao He, Jian Liang +5Reinforcement Learning RL for Language Model Reasoning
1NLPR & MAIS, Institute of Automation, Chinese Academy of Sciences · *Work done during an internship at Meituan · School of Artificial Intelligence, University of Chinese Academy of Sciences +2
Measure Twice, Click Once: Co-evolving Proposer and Visual Critic via Reinforcement Learning for GUI Grounding
Apr 23, 2026Wenkai Wang, Xiyun Li, Hongcan Guo +5Reinforcement Learning GUI Grounding
Zhejiang University · Tencent AI Lab · The University of Hong Kong
Self-Guided Plan Extraction for Instruction-Following Tasks with Goal-Conditional Reinforcement Learning
Apr 22, 2026Zoya Volovikova, Nikita Sorokin, Dmitriy Lukashevskiy +2Reinforcement Learning LLM-Guided RL
1AXXX · 2MIRAI
Distributional Value Estimation Without Target Networks for Robust Quality-Diversity
Apr 22, 2026Behrad Koohy, Jamie BayneDistributional RL Reinforcement Learning
Luffy.AI Culham, Oxfordshire, United Kingdom
Maximum Entropy Semi-Supervised Inverse Reinforcement Learning
Apr 22, 2026Julien Audiffren, Michal Valko, Alessandro Lazaric +1Reinforcement Learning Maximum Entropy RL
1CMLA, ENS Cachan · 2SequeL team, INRIA Lille - Nord Europe · 3Adobe Research
Efficient Reinforcement Learning using Linear Koopman Dynamics for Nonlinear Robotic Systems
Apr 21, 2026Wenjian Hao, Yuxuan Fang, Zehui Lu +1Robotic Control Reinforcement Learning
School of Aeronautics and Astronautics, Purdue University, West Lafayette, IN 47907, USA · independent researcher
Rethinking Reinforcement Fine-Tuning in LVLM: Convergence, Reward Decomposition, and Generalization
Apr 21, 2026Carter Adams, Rafael Oliveira, Gabriel Almeida +1Tool Use in VLMs Reinforcement Learning
Federal University of Bahia
TEMPO: Scaling Test-time Training for Large Reasoning Models
Apr 21, 2026Qingyang Zhang, Xinke Kong, Haitao Wu +7Reinforcement Learning Inference-Time Optimization
Tianjin University · Tongyi Lab, Alibaba Group · The Chinese University of Hong Kong +1
Intentional Updates for Streaming Reinforcement Learning
Apr 21, 2026Arsalan Sharifnassab, Mohamed Elsayed, Kris De Asis +2Reinforcement Learning Temporal-Difference Learning
Openmind Research Institute · Department of Computing Science, University of Alberta.
Beyond Bellman: High-Order Generator Regression for Continuous-Time Policy Evaluation
Apr 21, 2026Yaowei Zheng, Richong Zhang, Shenxi Wu +5Reinforcement Learning Value Function Estimation
School of Computer Science and Engineering, Beihang University, China · Fudan University, China · Faculty of Humanities and Social Sciences, University of Nottingham, China +1
Curiosity-Critic: Cumulative Prediction Error Improvement as a Tractable Intrinsic Reward for World Model Training
Apr 20, 2026Vin Bhaskara, Haicheng WangIntrinsic Reward Methods Reinforcement Learning
Department of Computer Science, University of Toronto, Toronto, Canada.
Bounded Ratio Reinforcement Learning
Apr 20, 2026Yunke Ao, Le Chen, Bruce D. Lee +5Reinforcement Learning Group Relative Policy Optimization
ETH Zurich · MPI for Intelligent Systems · University of Alberta +2
Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data
Apr 20, 2026Zhenwen Liang, Yujun Zhou, Sidi Lu +3Reinforcement Learning RL for Language Model Reasoning
Tencent AI Lab · University of Notre Dame
Negative Advantages Is a Double-Edged Sword: Calibrating advantages in GRPO for Search Agents
Apr 20, 2026Jiayi Wu, Ruobing Xie, Zeqian Huang +6Reinforcement Learning RL for Language Model Reasoning
School of Data Science and Engineering, East China Normal University · Tencent · Tsinghua University

Apr 27, 2026, cs.CLJ/K move · Enter open · S save

Why Does Reinforcement Learning Generalize? A Feature-Level Mechanistic Study of Post-Training in Large Language Models

Dan Shi, Zhuowen Han, Simon Ostermann, Renren Jin+2

TJUNLP Lab, School of Computer Science and Technology, Tianjin University, China · German Research Center for Artificial Intelligence (DFKI), Saarbrücken, Germany · Saarland University, Saarbrücken, Germany

Reinforcement Learning RL for Language Model Reasoning RL Post-Training Interpretability in RL Generalization in RL

Open paper AskPDF arXiv

Reinforcement learning (RL)-based post-training often improves the reasoning performance of large language models (LLMs) beyond the training domain, while supervised fine-tuning (SFT) frequently leads to general capabilities forgetting. However, the mechanisms underlying this contrast remain unclear. To bridge this gap, we present a feature-level mechanistic analysis methodology to probe RL generalization using a controlled experimental setup, where RL- and SFT-tuned models are trained from the same base model on identical data. Leveraging our interpretability framework, we align internal activations across models within a shared feature space and analyze how features evolve during post-training. We find that SFT rapidly introduces many highly specialized features that stabilize early in training, whereas RL induces more restrained and continually evolving feature changes that largely preserve base models' representations. Focusing on samples where RL succeeds but the base model fails, we identify a compact, task-agnostic set of features that directly mediate generalization across diverse tasks. Feature-level interventions confirm their causal role: disabling these features significantly degrades RL models' generalization performance, while amplifying them improves base models' performance. The code is available at https://github.com/danshi777/RL-generalization.

Momentum

Related topics

Latest papers 1,138