Data to 7 Oct 2026

Co-Evolving LLM Coder and Unit Tester via Reinforcement Learning

arXiv 2506.03136 ↗First posted 3 Jun 2025cs.CLcited by 51

Not on the map. Why?

Abstract (arXiv)

We propose CURE, a novel reinforcement learning framework with a dedicated reward design that co-evolves coding and unit test generation capabilities based on their interaction outcomes, without any ground-truth code as supervision. This approach enables flexible and scalable training and allows the unit tester to learn directly from the coder's mistakes. Our derived ReasonFlux-Coder-7B and 14B models improve code generation accuracy by 5.3% and Best-of-N accuracy by 9.0% after optimization on Qwen2.5-Instruct models, outperforming similarly sized Qwen-Coder, DeepSeek-Coder, and Seed-Coder. They naturally extend to downstream tasks such as test-time scaling and agentic coding-achieving a 8.1% improvement over the base model. For the long-CoT model, our ReasonFlux-Coder-4B consistently outperforms Qwen3-4B while achieving 64.8% inference efficiency in unit test generation. Notably, we also find that our model can serve as an effective reward model for reinforcement learning on base models. Project: https://github.com/Gen-Verse/CURE

Key facts. Cited by 51 papers in the map (data through 7 Oct 2026). Builds on 43 of its 57 references that are in the map. First posted on arXiv 3 Jun 2025.

Builds on

43 of 57 references.

References · 43

2017Proximal Policy Optimization Algorithmscited by 14,441
2021Training Verifiers to Solve Math Word Problemscited by 9,743
2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,767
2024Qwen2.5 Technical Reportcited by 4,713
2023Let's Verify Step by Stepcited by 3,598
2021Program Synthesis with Large Language Modelscited by 3,509
2025DAPO: An Open-Source LLM Reinforcement Learning System at Scalecited by 2,678
2024LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Codecited by 1,906
2022Competition-Level Code Generation with AlphaCodecited by 1,427
2023Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generationcited by 1,332

31 more

2023Large Language Models Cannot Self-Correct Reasoning Yetcited by 965
2024SimPO: Simple Preference Optimization with a Reference-Free Rewardcited by 951
2025Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?cited by 948
2024Large Language Monkeys: Scaling Inference Compute with Repeated Samplingcited by 946
2025Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Modelcited by 450
2024Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translationcited by 390
2022CodeT: Code Generation with Generated Testscited by 369
2025Demystifying Long Chain-of-Thought Reasoning in LLMscited by 323
2025MMaDA: Multimodal Large Diffusion Language Modelscited by 241
2025Inference-Time Scaling for Generalist Reward Modelingcited by 233
2023An Empirical Evaluation of Using Large Language Models for Automated Unit Test Generationcited by 193
2024MaxMin-RLHF: Alignment with Diverse Human Preferencescited by 121
2019IPO: Interior-point Policy Optimization under Constraintscited by 119
2020Unit Test Case Generation with Transformers and Focal Contextcited by 118
2024Code Generation with AlphaCodium: From Prompt Engineering to Flow Engineeringcited by 100
2025S*: Test Time Scaling for Code Generationcited by 95
2023ChatUniTest: A Framework for LLM-Based Test Generationcited by 94
2025GenPRM: Scaling Test-Time Compute of Process Reward Models via Generative Reasoningcited by 94
2023No More Manual Tests? Evaluating and Improving ChatGPT for Unit Test Generationcited by 82
2024o1-Coder: an o1 Replication for Codingcited by 77
2024StepCoder: Improve Code Generation with Reinforcement Learning from Compiler Feedbackcited by 74
2024Value-Incentivized Preference Optimization: A Unified Approach to Online and Offline RLHFcited by 73
2025ReasonFlux: Hierarchical LLM Reasoning via Scaling Thought Templatescited by 62
2025ScoreFlow: Mastering LLM Agent Workflows via Score-based Preference Optimizationcited by 50
2023Enhancing Large Language Models in Coding Through Multi-Perspective Self-Consistencycited by 46
2023A3Test: Assertion-Augmented Automated Test Case Generationcited by 33
2025Dynamic Scaling of Unit Tests for Code Reward Modelingcited by 31
2024TestART: Improving LLM-based Unit Testing via Co-evolution of Automated Generation and Repair Iterationcited by 20
2025Learning to Generate Unit Tests for Automated Debuggingcited by 16
2024A Large-scale Empirical Study on Fine-tuning Large Language Models for Unit Testingcited by 15
2025Dynamic Chain-of-Thought: Towards Adaptive Deep Reasoningcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 23; 2026: 28.

51 papers.

Sort:

By area:

2025R-Zero: Self-Evolving Reasoning LLM from Zero Datacited by 210
2025The Landscape of Agentic Reinforcement Learning for LLMs: A Surveycited by 195
2025A Survey of Reinforcement Learning for Large Reasoning Modelscited by 175
2026OpenClaw-RL: Train Any Agent Simply by Talkingcited by 83
2025Agent0: Unleashing Self-Evolving Agents from Zero Data via Tool-Integrated Reasoningcited by 68
2025WoW: Towards a World omniscient World model Through Embodied Interactioncited by 66
2025ReasonFlux-PRM: Trajectory-Aware PRMs for Long Chain-of-Thought Reasoning in LLMscited by 44
2025GenEnv: Difficulty-Aligned Co-Evolution Between LLM Agents and Environment Simulatorscited by 34
2025Chasing Moving Targets with Online Self-Play Reinforcement Learning for Safer Language Modelscited by 33
2025Guided Self-Evolving LLMs with Minimal Human Supervisioncited by 33
2025Demystifying Reinforcement Learning in Agentic Reasoningcited by 32
2026Tool-R0: Self-Evolving LLM Agents for Tool-Learning from Zero Datacited by 31

38 more

2025Stronger-MAS: Multi-Agent Reinforcement Learning for Collaborative LLMscited by 25
2025CodeRL+: Improving Code Generation via Reinforcement with Execution Semantics Alignmentcited by 22
2025A Survey on Agentic Multimodal Large Language Modelscited by 19
2026RLAnything: Forge Environment, Policy, and Reward Model in Completely Dynamic RL Systemcited by 19
2026SOD: Step-wise On-policy Distillation for Small Language Model Agentscited by 17
2025The Best of N Worlds: Aligning Reinforcement Learning with Best-of-N Sampling via max@k Optimisationcited by 16
2026Benchmarking Reward Hack Detection in Code Environments via Contrastive Analysiscited by 15
2025Loong: Synthesize Long Chain-of-Thoughts at Scale through Verifierscited by 14
2025From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligencecited by 13
2026V1: Unifying Generation and Self-Verification for Parallel Reasonerscited by 12
2025Learning to Generate Unit Test via Adversarial Reinforcement Learningcited by 11
2026R-Diverse: Mitigating Diversity Illusion in Self-Play LLM Trainingcited by 9
2025The Path of Self-Evolving Large Language Models: Achieving Data-Efficient Learning via Intrinsic Feedbackcited by 6
2025VideoChat-M1: Collaborative Policy Planning for Video Understanding via Multi-Agent Reinforcement Learningcited by 6
2026TestExplora: Benchmarking LLMs for Proactive Bug Discovery via Repository-Level Test Generationcited by 5
2026CodeScaler: Scaling Code LLM Training and Test-Time Inference via Reward Modelscited by 5
2025How Many Code and Test Cases Are Enough? Evaluating Test Cases Generation from a Binary-Matrix Perspectivecited by 4
2026Understanding Performance Gap Between Parallel and Sequential Sampling in Large Reasoning Modelscited by 3
2026ACE: Self-Evolving LLM Coding Framework via Adversarial Unit Test Generation and Preference Optimizationcited by 3
2026Discovery Foundation Models: Toward Open-Ended Discovery Intelligencecited by 3
2025HarnessLLM: Automatic Testing Harness Generation via Reinforcement Learningcited by 2
2026RM -RF: Reward Model for Run-Free Unit Test Evaluationcited by 2
2026LAD: Learning Advantage Distribution for Reasoningcited by 2
2026Credit-Budgeted ICPC-Style Coding: When Agents Must Pay for Every Decisioncited by 2
2026Rule2DRC: Benchmarking LLM Agents for DRC Script Synthesis with Execution-Guided Test Generationcited by 2
2026Scaling Large Reasoning Models beyond Human Supervision: A Path toward Superintelligencecited by 2
2025MAS2: Self-Generative, Self-Configuring, Self-Rectifying Multi-Agent Systemscited by 1
2026Soft-SVeRL: Self-Verified Reinforcement Learning with Soft Rewardscited by 1
2026EvoOtter: Evolutionary Reproduction Test Generatorcited by 1
2025DUET: Agentic Design Understanding via Experimentation and Testingcited by 0
2026Sci-CoE: Co-evolving Scientific Reasoning LLMs via Geometric Consensus with Sparse Supervisioncited by 0
2026Dynamic Adversarial Reinforcement Learning for Robust Multimodal Large Language Modelscited by 0
2026Easy Samples Are All You Need: Self-Evolving LLMs via Data-Efficient Reinforcement Learningcited by 0
2026GrowLoop: Self-Evolving Conversation Evaluation Seeded by Humancited by 0
2026Mathematical methods of reinforcement learningcited by 0
2026ISO: An RLVR-Native Optimization Stackcited by 0
2026Coding Agents as Test-Suite Auditors: Finding What Official Suites Miss While Approaching What They Catchcited by 0
2026ExecCritic: Learn to Test, Test to Improve for Coding Agentscited by 0

50 most cited of 51 All 51 (JSON)

Similar, not cited

Close in wording, no citation either way