RL Fine-Tuning

RL: Reinforcement Learning

Follow this topic Ask about this topic

Momentum

18 papers in the last four weeks, up 260% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 162

All topics

LEAP: Lean Environment-Feedback via Adaptive Pruning for Code RL in GPU Kernel Generation
Aug 3, 2026Tankun Li, Zhi Chen, Yaohua TangRL for Code Generation GPU Kernel Generation
Moore Threads AI
Question Begets Question: Self-Evolving Curriculum for Reinforcement Fine-Tuning on Competition Mathematics
Aug 2, 2026Longtian Bao, Jianyou Wang, Yang Zhang +2Synthetic Data Generation Curriculum RL
University of Chicago · University of California, San Diego
Exact Action Values Are Not Enough: Rollout-Verified Reinforcement Fine-Tuning of a Reasoning Model for Multi-Zone VAV Control
Jul 30, 2026Takumi Shioda, Kohei Terashima, Tatsuo NagaiLanguage Model-Based Control Model-Free RL
The University of Tokyo · Tokyo University of Science
Kalman Meets Curriculum: Efficient Dynamic Prompt Selection for Adaptive RL Finetuning
Jul 30, 2026Haodong Zhu, Yangyang Ren, Yanjing Li +4RL for Language Model Reasoning Curriculum RL
1Beihang University · 2Zhongguancun Academy · 3Nanyang Technological university +1
Do You Really Need to Pretrain Q-Functions for Online RL Fine-Tuning?
Jul 29, 2026Perry Dong, Ron Polonsky, Dorsa Sadigh +1Continuous Control RL Fine-Tuning
Stanford University
SERPO: Self-Evolving Rubric Policy Optimization for Open-Ended Test-Time Reinforcement Learning
Jul 29, 2026Jianze Wang, Kunwang Zheng, Ying Liu +5Reinforcement Learning Test-Time RL
School of Artificial Intelligence and Automation, Huazhong University of Science and Technology · Alibaba Group · University of Science and Technology of China
A Physics-Informed Framework for PID Tuning of Chemical Processes Using Large Language Model Agents
Jul 29, 2026Zhoupeng Shou, Xiaodong Hong, Congjing Ren +3Language Model-Based Control Feedback Control
State Key Laboratory of Chemical Engineering, Department of Chemical and Biological Engineering, Zhejiang University, Hangzhou, China · Engineering Research Center of Functional Materials Intelligent Manufacturing of Zhejiang Province, ZJU-Hangzhou Global Scientific and Technological Innovation Center, Hangzhou, China · Ningbo Innovation Center, Zhejiang University, Zhejiang, China
Post-Training at the Edge of Detectability: A Game-Theoretic Approach to Fine-Tuning
Jul 29, 2026Keegan Harris, Brian W. Lee, Ian Waudby-Smith +3Reinforcement Learning KL-Regularized RL
University of California, Berkeley · Inria & École Normale Supérieure
Probing the Origins of Reasoning Performance: Representational Quality for Mathematical Problem-Solving in RL vs. SFT Fine-Tuned Models
Jul 28, 2026Antyabha Rahman, Akshaj Gurugubelli, Omar Ankit +2Numerical Reasoning in Language Models LLM Interpretability
University of New South Wales · Algoverse AI Research · University of Waterloo +1
Towards Robust Reinforcement Learning for Small-Scale Language Model Agents
Jul 27, 2026Md Rezwanul Haque, Md. Milon Islam, Fakhri KarrayRL for Language Models LLM Alignment
Centre for Pattern Analysis and Machine Intelligence, Department of Electrical and Computer Engineering, University of Waterloo, N2L 3G1, Ontario, Canada · Department of Computer Science and Engineering, Khulna University of Engineering & Technology, Khulna, Bangladesh · Department of Machine Learning, Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates
ACRL: Adaptive Control of Training-Inference Discrepancy for Stable Reinforcement Learning
Jul 27, 2026Wenwu Fan, Qihong Lin, Zhijie Xia +4RL Control RL for Language Models
Computing Product Line, Huawei
From Evaluation to Optimisation: Hierarchy-Aware Training Signals for CWE Prediction in Python
Jul 23, 2026Muntasir Adnan, Manile Srun, Carlos C. N. KuhnSoftware Vulnerability Detection LLMs for Cybersecurity
Open Source Institute, Faculty of Science and Technology, University of Canberra, Canberra, Australia.
Non-vacuous Generalization Bounds for Reinforcement Learning with Verifiable Rewards
Jul 16, 2026Yuxuan Zhu, Rohan Alur, Daniel KangPAC-Bayesian Generalization Bounds Reinforcement Learning with Verifiable Rewards
UIUC · MIT · Bridgewater AIA Labs
Verifier-Based Reinforcement Fine-Tuning of Reasoning Models for Thermal Energy Storage Control
Jul 14, 2026Takumi Shioda, Kohei Terashima, Tatsuo NagaiRL for Language Model Reasoning Building Energy Management
The University of Tokyo · Tokyo University of Science
A Learning-Rate-Gated Failure of GRPO in a Small Language and Vision-Language Model Web Agent: A Controlled Null and Its Mechanism
Jul 14, 2026Chengguang Gan, Zhixi Cai, Yunhao Liang +3Group Relative Policy Optimization RL Fine-Tuning
Independent Researcher · Monash University · University of Chinese Academy of Sciences +2
Active Offline-to-Online Reinforcement Learning
Jul 13, 2026Alper Kamil Bozkurt, Shangtong Zhang, Yuichi MotaiOffline RL RL Fine-Tuning
Virginia Commonwealth University, USA · University of Virginia, USA
When Implausible Tokens Get Reinforced: Tail-Aware Credit Calibration for LLM Reinforcement Learning
Jul 8, 2026Xiuyi Lou, Zicheng Xu, Yu-Neng Chuang +4RL for Language Models Token-Level Credit Assignment
Johns Hopkins University · Rice University · Workato +1
Improving LLM-Generated Process Model Quality Through Reinforcement Learning: The Role of Reward Function Design
Jul 7, 2026Alexander Rombach, Chantale Lauer, Nijat MehdiyevRL for Language Models Multi-Objective Language Model Alignment
German Research Center for Artificial Intelligence (DFKI), Campus D3 2, Saarbrücken, 66123, Saarland, Germany · Saarland University, Campus D3 2, Saarbrücken, 66123, Saarland, Germany
Reinforcement Learning for Data-Efficient Code-Switched ASR
Jul 2, 2026Ziwei Ye, Peter VickersCode-Switching Speech Recognition Audio-Language Models
Independent Researcher · Spotify Canada
Is One Layer Enough? Training A Single Transformer Layer Can Match Full-Parameter RL Training
Jul 1, 2026Zijian Zhang, Rizhen Hu, Athanasios Glentis +4RL for Language Models Fine-Tuning
University of Minnesota · Peking University · Amazon
Loss Smoothing for Stable Adaptation Under Distribution Shift
Jul 1, 2026Darshan Patil, Ekaterina Lobacheva, Razvan Pascanu +1Fine-Tuning RL Fine-Tuning
Chandar Research Lab · Mila – Quebec AI Institute · Université de Montréal +2
Active-GRPO: Adaptive Imitation and Self-Improving Reasoning for Molecular Optimization
Jul 1, 2026Xuefeng Liu, Mingxuan Cao, Qinan Huang +3Molecular Optimization Large Language Model-Guided Optimization
School of Medicine, Stanford University · 2Data Science Institute, University of Chicago · 3Pritzker School of Molecular Engineering, University of Chicago +2
DRIFT: Difficulty Routing Self-DIstillation with Rhythm-Gated Exploration and Success BuFfer Training
Jun 29, 2026Haisen Luo, Yiwei Liu, Haoning Wang +13Self-Training for Language Models RL for Language Model Reasoning
3Beike Language and Intelligence · 2ENS Paris-Saclay · 1Tsinghua University
PS-PPO: Prefix-Sampling PPO for Critic-Free RLHF
Jun 29, 2026Doo Hwan Hwang, Kee-Eung KimReinforcement Learning RL for Language Model Reasoning
Kim Jaechul Graduate School of AI, KAIST, Daejeon, South Korea.
Two-Stage Fine-Tuning for Protein Sequence Generation with Targeted Amino-Acid Composition
Jun 26, 2026Violeta Basten-Romero, Rubén Muñoz-Tafalla, Anna María Díaz-Rovira +3Protein Language Models Protein Design
Barcelona Supercomputing Center (BSC), Plaça d’Eusebi Güell, 1-3, 08034, Barcelona, Spain · Department of Bioinformatics, School of Mathematics and Statistics (FME), Universitat Politècnica de Catalunya - BarcelonaTech (UPC), 08034 Barcelona, Spain · Nostrum Biodiscovery S.L., Av. Josep Tarradellas, 8-10, 3-2, 08029, Barcelona, Spain +1
Why Multi-Step Tool-Use Reinforcement Learning Collapses and How Supervisory Signals Fix It
Jun 24, 2026Yupu Hao, Zhuoran Jin, Huanxuan Liao +2Supervised Fine-Tuning LLM Reliability
1The Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China · School of Artiﬁcial Intelligence, University of Chinese Academy of Sciences, Beijing, China
FORCE: Efficient VLA Reinforcement Fine-Tuning via Value-Calibrated Warm-up and Self-Distillation
Jun 24, 2026Shuyi Zhang, Yunfan Lou, Hongyang Cheng +8RL for Robotics Vision-Language-Action Models
Institute of Automation, Chinese Academy of Sciences, Beijing, China · Beijing Academy of Artificial Intelligence, Beijing, China · State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University, Beijing, China
WinDOM: Self-Family Distillation for Small-Model GUI Grounding
Jun 24, 2026Chengheng Li-Chen, Zhiqian Zhou, Hao Chen +1Synthetic Data Generation GUI Grounding
Ecole Polytechnique Fédérale de Lausanne (EPFL), Lausanne, Switzerland · Logitech · Universitat Politècnica de Catalunya (UPC), Barcelona, Spain.
Reinforcement Learning for Computer-Use Agents with Autonomous Evaluation
Jun 23, 2026Marta Sumyk, Oleksandr KosovanRL for GUI Agents RL Fine-Tuning
Ukrainian Catholic University, Lviv, Ukraine
Supervised Reinforcement Learning for the Coordination of Distributed Energy Resources
Jun 23, 2026Haoyuan Deng, Yihong Zhou, Thomas Morstyn +1Reinforcement Learning RL Fine-Tuning
The University of Hong Kong, Hong Kong SAR, China · University of Oxford, Oxford, U.K. · The University of Hong Kong Shenzhen Institute of Research and Innovation, Shenzhen, China

Aug 3, 2026, cs.LGJ/K move · Enter open · S save

LEAP: Lean Environment-Feedback via Adaptive Pruning for Code RL in GPU Kernel Generation

Tankun Li, Zhi Chen, Yaohua Tang

Moore Threads AI

RL for Code Generation GPU Kernel Generation RL Fine-Tuning

Open paper AskPDF arXiv

Post-training large language models (LLMs) via reinforcement learning (RL) has significantly advanced code generation capabilities. To bypass the heavy memory footprint of critic networks, current state-of-the-art frameworks leverage critic-free paradigms like Group Relative Policy Optimization (GRPO) tied to rule-based verification sandboxes. However, applying these frameworks to low-level systems programming, such as CUDA kernel generation-presents severe challenges: binary pass/fail rewards introduce severe signal sparsity, while multi-turn environmental feedback loops suffer from prohibitive compilation latencies and reward dilution across trajectories. In this work, we introduce LEAP (Lean Environment-Feedback via Adaptive Pruning), a scalable and computationally efficient multi-turn RL framework optimized for low-level hardware accelerator alignment. LEAP features Difficulty-Conditioned Pruning (DCP), a dynamic gating mechanism that adaptively cuts off simple and overly catastrophic tasks from multi-turn expansion, focusing resource-heavy compilation and hardware exploration exclusively on high-value, complex tasks. To fully operationalize these paths without manual hyperparameter engineering, we propose a Rank-Based Reward formulation. By deriving scale-free relative advantages from pairwise tournament outcomes within the GRPO rollout group, our method inherently penalizes token inefficiency on simple prompts while maximizing learning gradients on challenging distributions. Empirical evaluations show that LEAP achieves superior first-turn proficiency and robust multi-turn debugging resilience while converging faster than unpruned multi-turn baselines, establishing a practical paradigm for low-level code RL.

Momentum

Related topics

Latest papers 162