RL for Code Generation

RL: Reinforcement Learning

Overview

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

CardsList

161 papers12 papers in the last four weeks, down 57% on the four weeks before. 0.1% of all new papers.

  1. Learning to Generate Secure Code via Token-Level Rewards

    Feb 26, 2026Jiazheng Quan, Xiaodong Li, Bin Wang +5Secure Code GenerationRL for Code Generation

  2. 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 AgentsSmall Language Models

  3. LLMs Can Learn to Reason Via Off-Policy RL

    Feb 22, 2026Daniel Ritter, Owen Oertell, Bradley Guo +3RL for Language Model ReasoningRL Post-Training

  4. 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 GenerationRL for Code Generation

  5. CodeScaler: Scaling Code LLM Training and Test-Time Inference via Reward Models

    Feb 4, 2026Xiao Zhu, Xinyu Zhou, Boyu Zhu +5RL for Code GenerationReward Modeling

  6. COBALT: Contextual Bandit Learning with Offline Trajectories for Multi-Turn Code Generation

    Feb 3, 2026Ziru Chen, Dongdong Chen, Ruinan Jin +3Code GenerationRL for Code Generation

  7. ReST-RL: Reinforcing LLM Reasoning through Unified Self-Training and Value-Guided Search

    Aug 27, 2025Sining Zhoubian, Dan Zhang, Jie TangRL for Code GenerationRL for Language Model Reasoning

  8. 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 GenerationCode Generation

  9. HARDTESTGEN: A High-Quality RL Verifier Generation Pipeline for LLM Algorithmic Coding

    May 30, 2025Zhongmou He, Yee Man Choi, Kexun Zhang +7Automated Test GenerationCode Generation Evaluation