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.

Scaling Reasoning Tokens via RL and Parallel Thinking: Evidence From Competitive Programming
Apr 1, 2026Qianfan Zhang, Tianyu Guo, Xuandi Ren +4Parallel Reasoning in Language Models Test-Time Scaling
Princeton University · UC Berkeley · Stanford University +1
RefineRL: Advancing Competitive Programming with Self-Refinement Reinforcement Learning
Apr 1, 2026Shaopeng Fu, Xingxing Zhang, Li Dong +1RL for Code Generation LLM Self-Refinement
Work done during an internship at Microsoft Research · KAUST · Microsoft Research
Kernel-Smith: A Unified Recipe for Evolutionary Kernel Optimization
Mar 30, 2026He Du, Qiming Ge, Jiakai Hu +18GPU Kernel Optimization GPU Kernel Generation
Shanghai AI Laboratory · Fudan University · MetaX
KAT-Coder-V2 Technical Report
Mar 29, 2026Fengxiang Li, Han Zhang, Haoyang Huang +43AI Coding Agents Agentic Code Generation
RTLSeek: Boosting the LLM-Based RTL Generation with Multi-Stage Diversity-Oriented Reinforcement Learning
Mar 29, 2026Xinyu Zhang, Zhiteng Chao, Yonghao Wang +6RTL Code Generation LLM Post-Training
State Key Lab of Processors, Institute of Computing Technology, Chinese Academy of Sciences, China · University of Chinese Academy of Sciences, China · Peking University, China +1
Composer 2 Technical Report
Mar 25, 2026Cursor Research, :, Aaron Chan +53Code Language Models Software Engineering Agents
A Deep Dive into Scaling RL for Code Generation with Synthetic Data and Curricula
Mar 25, 2026Cansu Sancaktar, David Zhang, Gabriel Synnaeve +1RL for Code Generation Synthetic Data Augmentation
University of Tübingen · Max Planck Institute for Intelligent Systems · Meta FAIR
DRTriton: Large-Scale Synthetic Data Driven Reinforcement Learning for Triton Kernel Generation
Mar 23, 2026Siqi Guo, Ming Lin, Tianbao YangGPU Kernel Generation GPU Kernel Optimization
Texas A&M University · Oracle
Context Bootstrapped Reinforcement Learning
Mar 19, 2026Saaket Agashe, Jayanth Srinivasa, Gaowen Liu +2RL for Language Model Reasoning Reinforcement Learning with Verifiable Rewards
University of California, Santa Barbara · Cisco Research
Execution-Grounded Credit Assignment for GRPO in Code Generation
Mar 17, 2026Abhijit Kumar, Natalya Kumar, Shikhar GuptaRL for Code Generation Credit Assignment
Code-A1: Adversarial Evolving of Code LLM and Test LLM via Reinforcement Learning
Mar 16, 2026Aozhe Wang, Yuchen Yan, Nan Zhou +5LLM Code Generation RL for Code Generation
Zhejiang University
EvolveCoder: Evolving Test Cases via Adversarial Verification for Code Reinforcement Learning
Mar 13, 2026Chi Ruan, Dongfu Jiang, Huaye Zeng +2RL for Code Generation Reinforcement Learning with Verifiable Rewards
University of Waterloo · Vector Institute · Harvard University
Self-Execution Simulation Improves Coding Models
Mar 11, 2026Gallil Maimon, Ori Yoran, Felix Kreuk +4Execution-Guided Code Generation LLM Self-Correction
FAIR team, Meta · Hebrew University of Jerusalem · Inria
Towards Cold-Start Drafting and Continual Refining: A Value-Driven Memory Approach with Application to NPU Kernel Synthesis
Mar 11, 2026Yujie Zheng, Zhuo Li, Shengtao Zhang +8Memory-Augmented Language Model Agents RL for Code Generation
Shanghai Jiao Tong University · Shanghai Artificial Intelligence Laboratory · Independent Researcher +1
SWE-Fuse: Empowering Software Agents via Issue-free Trajectory Learning and Entropy-aware RLVR Training
Mar 9, 2026Xin-Cheng Wen, Binbin Chen, Haoxuan Lan +3Software Engineering Agents LLM Agent Training
Ant Group · The Chinese University of Hong Kong
Breaking Training Bottlenecks: Effective and Stable Reinforcement Learning for Coding Models
Mar 8, 2026Zongqian Li, Shaohan Huang, Zewen Chi +5RL for Code Generation LLM Code Generation
Microsoft Research · University of Cambridge · Princeton University
ReflexiCoder: Teaching Large Language Models to Self-Reflect on Generated Code and Self-Correct It via Reinforcement Learning
Mar 6, 2026Juyong Jiang, Jiasi Shen, Sunghun Kim +3LLM Code Generation LLM Self-Correction
The Hong Kong University of Science and Technology (Guangzhou) · The Hong Kong University of Science and Technology · Amazon AGI +1
$V_1$ : Unifying Generation and Self-Verification for Parallel Reasoners
Mar 4, 2026Harman Singh, Xiuyu Li, Kusha Sareen +14Language Model Self-Verification Test-Time Scaling
UC Berkeley · Mila · Together AI +1
A Rubric-Supervised Critic from Sparse Real-World Outcomes
Mar 4, 2026Xingyao Wang, Valerie Chen, Heng Ji +1Reward Modeling AI Agent Evaluation
OpenHands · UIUC · CMU
CUDA Agent: Large-Scale Agentic RL for High-Performance CUDA Kernel Generation
Feb 27, 2026Weinan Dai, Hanlin Wu, Qiying Yu +13GPU Kernel Generation GPU Kernel Optimization
ByteDance Seed · Institute for AI Industry Research (AIR), Tsinghua University · SIA-Lab of Tsinghua AIR and ByteDance Seed
Learning to Generate Secure Code via Token-Level Rewards
Feb 26, 2026Jiazheng Quan, Xiaodong Li, Bin Wang +5Secure Code Generation RL for Code Generation
Fuyao University of Science and Technology · Xiamen University · Peking University +1
SWE-Protégé: Learning to Selectively Collaborate With an Expert Unlocks Small Language Models as Software Engineering Agents
Feb 25, 2026Patrick Tser Jern Kon, Archana Pradeep, Ang Chen +5Software Engineering Agents Small Language Models
University of Michigan · Meta · Stanford University
LLMs Can Learn to Reason Via Off-Policy RL
Feb 22, 2026Daniel Ritter, Owen Oertell, Bradley Guo +3RL for Language Model Reasoning RL Post-Training
Cornell University · Databricks · Harvard University
GLM-5: from Vibe Coding to Agentic Engineering
Feb 17, 2026GLM-5-Team, :, Aohan Zeng +184LLM Agent Training Agentic RL
TAROT: Test-driven and Capability-adaptive Curriculum Reinforcement Fine-tuning for Code Generation with Large Language Models
Feb 17, 2026Chansung Park, Juyong Jiang, Fan Wang +4LLM Code Generation RL for Code Generation
Electronics and Telecommunications Research Institute · The Hong Kong University of Science and Technology (Guangzhou) · The Hong Kong University of Science and Technology +2
CodeScaler: Scaling Code LLM Training and Test-Time Inference via Reward Models
Feb 4, 2026Xiao Zhu, Xinyu Zhou, Boyu Zhu +5RL for Code Generation Reward Modeling
LARK, HKUST(GZ) · Kuaishou Technology · UCL +3
COBALT: Contextual Bandit Learning with Offline Trajectories for Multi-Turn Code Generation
Feb 3, 2026Ziru Chen, Dongdong Chen, Ruinan Jin +3Code Generation RL for Code Generation
The Ohio State University. · Microsoft.
X-Coder: Advancing Competitive Programming with Synthetic Tasks, Solutions, and Tests
Jan 11, 2026Jie Wu, Haoling Li, Xin Zhang +8RL for Code Generation Synthetic Data Generation
Tsinghua University · Microsoft
ReST-RL: Reinforcing LLM Reasoning through Unified Self-Training and Value-Guided Search
Aug 27, 2025Sining Zhoubian, Dan Zhang, Jie TangRL for Code Generation RL for Language Model Reasoning
Department of Computer Science and Technology, Tsinghua University · Work done when interned at Z.ai. · School of Electronics and Computer Scinence, Univeristy of Southampton
Agnostics: Learning to Code in Any Programming Language via Reinforcement with a Universal Learning Environment
Aug 6, 2025Aleksander Boruch-Gruszecki, Yangtian Zi, Zixuan Wu +4RL for Code Generation Code Generation
1Northeastern University · University of Texas · 3Wellesley College

Apr 1, 2026J/K move · Enter open · S save

Scaling Reasoning Tokens via RL and Parallel Thinking: Evidence From Competitive Programming

Qianfan Zhang, Tianyu Guo, Xuandi Ren, Jiale Chen+3

Princeton University · UC Berkeley · Stanford University+1

Parallel Reasoning in Language Models Test-Time Scaling Large Reasoning Models RL for Code Generation Competitive Programming

Open paper AskPDF arXiv

We study how to scale reasoning token budgets for competitive programming through two complementary approaches: training-time reinforcement learning (RL) and test-time parallel thinking. During RL training, we observe an approximately log-linear relationship between validation accuracy and the average number of generated reasoning tokens over successive checkpoints, and show two ways to shift this training trajectory: verification RL warmup raises the starting point, while randomized clipping produces a steeper trend in the observed regime. As scaling single-generation reasoning during RL quickly becomes expensive under full attention, we introduce a multi-round parallel thinking pipeline that distributes the token budget across threads and rounds of generation, verification, and refinement. We train the model end-to-end on this pipeline to match the training objective to the test-time structure. Starting from Seed-OSS-36B, the full system with 16 threads and 16 rounds per thread matches the underlying RL model's oracle pass@16 at pass@1 using 7.6 million tokens per problem on average, and surpasses GPT-5-high on 456 hard competitive programming problems from AetherCode.