RL for Code Generation

RL: Reinforcement Learning

This field trains language models to write, repair, and optimize programs by using execution environments, unit tests, compilers, formal verifiers, or renderers as feedback. Common approaches include reinforcement learning with verifiable rewards, often using GRPO or PPO, alongside synthetic tasks, curricula, and multi-turn tool-using agents. Newer methods add dense or token-level credit, reward models, self-correction, and search, with evaluation spanning HumanEval, MBPP, APPS, LiveCodeBench, SWE-bench, hardware kernels, and visual-to-code tasks. A central challenge is making feedback reliable and informative without reward hacking or excessive rollout costs, while ensuring gains transfer beyond the training tasks and execution harnesses.

Latest papers

150 papers24 papers in the last four weeks, up 26% on the four weeks before. 0.1% of all new papers.

Domain-Adaptable Reinforcement Learning for Code Generation with Dense Rewards
May 20, 2026Erfan Aghadavoodi Jolfaei, Daniel Maninger, Abhinav Anand +2RL for Code Generation Reinforcement Learning
Technische Universität Darmstadt, Darmstadt, Germany · Hessian Center for Artificial Intelligence (hessian.AI), Darmstadt, Germany · National Research Center for Applied Cybersecurity ATHENE, Darmstadt, Germany.
Beyond Inference-Time Search: Reinforcement Learning Synthesizes Reusable Solvers
May 18, 2026Soheyl Massoudi, Gabriel Apaza, Milad Habibi +1RL for Code Generation LLM-Based Program Synthesis
ETH Zürich Zürich, Switzerland · University of Maryland College Park, MD, USA
Beyond Execution: Static-Analysis Rewards and Hint-Conditioned Diffusion RL for Code Generation
May 16, 2026Shuyin Ouyang, Zhaozhi Qian, Faroq AL-Tam +2RL for Code Generation Diffusion Guidance
King’s College London · Elm Europe
Solvita: Enhancing Large Language Models for Competitive Programming via Agentic Evolution
May 14, 2026Han Li, Jinyu Tian, Rili Feng +10RL for Code Generation Continual Learning for LLM Agents
Nanjing University · Independent Researcher · Tsinghua University
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.
GenCircuit-RL: Reinforcement Learning from Hierarchical Verification for Genetic Circuit Design
May 14, 2026Noah FlynnRL for Code Generation Program Synthesis
University of California, Berkeley, CA, USA.
HLS-Seek: QoR-Aware Code Generation for High-Level Synthesis via Proxy Comparative Reward Reinforcement Learning
May 13, 2026Qingyun Zou, Feng Yu, Hongshi Tan +3RL for Code Generation Reward Modeling
National University of Singapore
ChipMATE: Multi-Agent Training via Reinforcement Learning for Enhanced RTL Generation
May 13, 2026Zhongkai Yu, Yichen Lin, Chenyang Zhou +12RL for Code Generation Code Generation
UCSD · Columbia University
Primal Generation, Dual Judgment: Self-Training from Test-Time Scaling
May 11, 2026Yizhu Jiao, Ruixiang Zhang, Richard Bai +3RL for Code Generation Test-Time Scaling
Apple · University of Illinois Urbana-Champaign
PYTHALAB-MERA: Validation-Grounded Memory, Retrieval, and Acceptance Control for Frozen-LLM Coding Agents
May 8, 2026Mehmet IscanRL for Code Generation Execution-Guided Code Generation
PythaLab, Yildiz Technical University
Signal Reshaping for GRPO in Weak-Feedback Agentic Code Repair
May 8, 2026Jia Li, Yuxin Su, Ting Peng +3RL for Code Generation Reward Shaping
The Chinese University of Hong Kong · Sun Yat-sen University · Tencent
Schedule-and-Calibrate: Utility-Guided Multi-Task Reinforcement Learning for Code LLMs
May 7, 2026Yujia Chen, Yang Ye, Xiao Chu +2RL for Code Generation Reinforcement Learning
Harbin Institute of Technology, Shenzhen · Huawei Cloud Computing Technologies Co., Ltd.
Rollout Pass-Rate Control: Steering Binary-Reward RL Toward Its Most Informative Regime
May 6, 2026Tianshu Zhu, Wenyu Zhang, Xiaoying Zuo +8RL for Code Generation Reinforcement Learning
Baidu
Correct Is Not Enough: Training Reasoning Planners with Executor-Grounded Rewards
May 5, 2026Tianyang Han, Hengyu Shi, Junjie Hu +3RL for Code Generation Process Reward Models
1D4 Lab · 2Independent Researcher
Strategy-Aware Optimization Modeling with Reasoning LLMs
May 4, 2026Ruiqing Zhao, Fengzhi Li, Yuan Zuo +5RL for Code Generation LLM-Based Program Synthesis
School of Computer Science and Engineering, Beihang University, Beijing, China · JIUTIAN Research, Beijing, China · MIIT Key Laboratory of Data and Decision Intelligence, Beihang University, Beijing, China
Exploring Pass-Rate Reward in Reinforcement Learning for Code Generation
May 1, 2026Xin-Ye Li, Ren-Biao Liu, Yun-Ji Zhang +3RL for Code Generation Reinforcement Learning
State Key Laboratory of Novel Software Technology, Nanjing University, Nanjing 210023, China · School of Artificial Intelligence, Nanjing University, Nanjing 210023, China
Improving LLM Code Generation via Requirement-Aware Curriculum Reinforcement Learning
May 1, 2026Shouyu Yin, Zhao Tian, Junjie Chen +1RL for Code Generation Curriculum Learning
Tianjin University, Tianjin, China · Dalian Maritime University, Dalian, China
Do Prompt-Elicited Trajectories Reflect Training-Time Reward Hacking? A Systematic Study on Monitoring Trainig-Time Reward Hacking in Code Generation
Apr 26, 2026Lichen Li, Hengguang Zhou, Yijun Liang +2RL for Code Generation Reward Hacking
Peking University · University of California, Los Angeles · University of Maryland +2
CharTide: Data-Centric Chart-to-Code Generation via Tri-Perspective Tuning and Inquiry-Driven Evolution
Apr 24, 2026Xiangxi Zheng, Kuang He, Jiayi Hu +6RL for Code Generation VLM Adaptation
Nanjing University · LLM Team, Shopee Pte. Ltd. · East China Normal University +2
Parallel-SFT: Improving Zero-Shot Cross-Programming-Language Transfer for Code RL
Apr 22, 2026Zhaofeng Wu, Shiqi Wang, Boya Peng +5Supervised Fine-Tuning RL for Code Generation
Meta Superintelligence Labs · MIT
WebGen-R1: Incentivizing Large Language Models to Generate Functional and Aesthetic Websites with Reinforcement Learning
Apr 22, 2026Juyong Jiang, Chenglin Cai, Chansung Park +4RL for Code Generation RL for Language Models
The Hong Kong University of Science and Technology (Guangzhou) · Alibaba · Tongyi Lab, Alibaba Group +3
Training and Agentic Inference Strategies for LLM-based Manim Animation Generation
Apr 20, 2026Ravidu Suien Rammuni Silva, Ahmad Lotfi, Isibor Kennedy Ihianle +2RL for Code Generation T2V Generation
Department of Computer Science, Nottingham Trent University, Nottingham, United Kingdom · Department of Physics and Mathematics, Nottingham Trent University, Nottingham, United Kingdom
MARS $^2$ : Scaling Multi-Agent Tree Search via Reinforcement Learning for Code Generation
Apr 16, 2026Pengfei Li, Shijie Wang, Fangyuan Li +7RL for Code Generation Multi-Agent Collaboration
Shanghai Artificial Intelligence Laboratory · Shanghai Innovation Institute · Harbin Institute of Technology +1
An Imperfect Verifier is Good Enough: Learning with Noisy Rewards
Apr 9, 2026Andreas Plesner, Francisco Guzmán, Anish AthalyeRL for Code Generation Reinforcement Learning
Handshake AI · ETH Zurich
Scientific Graphics Program Synthesis via Dual Self-Consistency Reinforcement Learning
Apr 7, 2026Juekai Lin, Yun Zhu, Honglin Lin +6Image-to-Code Generation Code Generation
Zhejiang University Hangzhou, China · Shanghai Artificial Intelligence Laboratory Shanghai, China · Peking University Beijing, China
OmniDiagram: Advancing Unified Diagram Code Generation via Visual Interrogation Reward
Apr 7, 2026Haoyue Yang, Xuanle Zhao, Xuexin Liu +2Code Generation RL for Code Generation
Institute of Automation, Chinese Academy of Sciences · University of Chinese Academy of Sciences · Zhejiang University
Scaling Coding Agents via Atomic Skills
Apr 6, 2026Yue LiuCoding Agents LLM Agent Skill Learning
NUS
GrandCode: Achieving Grandmaster Level in Competitive Programming via Agentic Reinforcement Learning
Apr 3, 2026Ornith Team, Xiaoya Li, Guoyin Wang +3RL for Code Generation Agentic RL
DeepReinforce Team
MM-ReCoder: Advancing Chart-to-Code Generation with Reinforcement Learning and Self-Correction
Apr 2, 2026Zitian Tang, Xu Zhang, Jianbo Yuan +4Chart-to-Code Generation Code Generation
Brown University · Amazon AGI
From Rebound to Remedy: Understanding and Mitigating Reward Hacking via Representation Engineering
Apr 1, 2026Rui Wu, Ruixiang TangReward Hacking RL Fine-Tuning
Department of Computer Science Rutgers University

May 20, 2026J/K move · Enter open · S save

Domain-Adaptable Reinforcement Learning for Code Generation with Dense Rewards

Erfan Aghadavoodi Jolfaei, Daniel Maninger, Abhinav Anand, Mert Tiftikci+1

Technische Universität Darmstadt, Darmstadt, Germany · Hessian Center for Artificial Intelligence (hessian.AI), Darmstadt, Germany · National Research Center for Applied Cybersecurity ATHENE, Darmstadt, Germany.

RL for Code Generation Reinforcement Learning Execution-Guided Code Generation Dense Reward RL Reinforcement Learning with Verifiable Rewards

Open paper AskPDF arXiv

Large language models show strong potential for automated code generation, but lack guarantees for correctness, quality, safety, and domain-specific constraints. For instance in robotics, where code generation is increasingly being used for planning and executing actions, awareness of the environment and physical constraints is critical. To facilitate the adaption of code-generating LLMs to diverse requirements, including domain-specific ones, we present a reinforcement learning framework that fine-tunes pre-trained LLMs using proximal policy optimization. Our customizable execution-aware reward formula captures and optimizes syntax, functional correctness, code style, security, and simulator executability. A token-level reward mapping mechanism enables effective credit assignment from execution outcomes to generated tokens. The framework is evaluated on general-purpose code generation (MBPP/MBPP+) and robotic program synthesis (RoboEval). The results show substantial improvements in functional correctness and simulator executability, including an absolute pass@1 increase of 19% on MBPP and a reduction in execution failures by 51% on RoboEval. These findings demonstrate that structured reinforcement learning can effectively align language models to correct program generation and domain-specific requirements.