mlsanityData to 14 Oct 2026

Klear-CodeTest: Scalable Test Case Generation for Code Reinforcement Learning

arXiv 2508.05710 ↗First posted 7 Aug 2025cs.SE cs.AIcited by 9

On the map: LLM reasoning → Reasoning for agents, planning and code

Abstract (arXiv)

Precise, correct feedback is crucial for effectively training large language models (LLMs) in code reinforcement learning. However, synthesizing high-quality test cases remains a profoundly challenging and unsolved problem. In this work, we present Klear-CodeTest, a comprehensive test case synthesis framework featuring rigorous verification to ensure quality and reliability of test cases. Our approach achieves broad coverage of programming problems via a novel Generator-Validation (G-V) framework, ensuring correctness through a consistency validation mechanism that verifies outputs against gold solutions. The proposed G-V framework generates comprehensive test cases including both regular and corner cases, enhancing test coverage and discriminative power for solution correctness assessment in code reinforcement learning. In addition, we design a multi-layered security sandbox system optimized for online verification platforms, guaranteeing safe and reliable code execution. Through comprehensive experiments, we demonstrate the effectiveness of our curated dataset, showing significant improvements in model performance and training stability. The source codes, curated dataset and sandbox system are available at: https://github.com/Kwai-Klear/CodeTest.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning. Builds on 23 of its 30 references that are in the map. First posted on arXiv 7 Aug 2025.

Builds on

23 of 30 references.

Closest ancestors · 5

Same direction, newest first

  1. 2025CodeContests+: High-Quality Test Case Generation for Competitive Programming6 Jun
  2. 2025HardTests: Synthesizing High-Quality Test Cases for LLM Coding30 May
  3. 2025rStar-Coder: Scaling Competitive Code Reasoning with a Large-Scale Verified Dataset27 May
  4. 2024LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code12 Mar
  5. 2022Competition-Level Code Generation with AlphaCode8 Feb

Other references · 18

  1. 2025Qwen3 Technical Reportcited by 8,820
  2. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  3. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  4. 2021Program Synthesis with Large Language Modelscited by 3,637
  5. 2025DAPO: An Open-Source LLM Reinforcement Learning System at Scalecited by 2,810
  6. 2025Understanding R1-Zero-Like Training: A Critical Perspectivecited by 1,345
  7. 2020CodeBERT: A Pre-Trained Model for Programming and Natural Languagescited by 1,310
  8. 2021CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generationcited by 906
  9. 2021Measuring Coding Challenge Competence With APPScited by 902
  10. 2024A Survey on Large Language Models for Code Generationcited by 658
  11. 2022CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learningcited by 358
  12. 2023CodeT5+: Open Code Large Language Models for Code Understanding and Generationcited by 333
6 more
  1. 2023TACO: Topics in Algorithmic COde generation datasetcited by 160
  2. 2025MiMo: Unlocking the Reasoning Potential of Language Model -- From Pretraining to Posttrainingcited by 121
  3. 2023RLTF: Reinforcement Learning from Unit Test Feedbackcited by 114
  4. 2023Execution-based Code Generation using Deep Reinforcement Learningcited by 99
  5. 2024Can Language Models Solve Olympiad Programming?cited by 72
  6. 2023Hot or Cold? Adaptive Temperature Sampling for Code Generation with Large Language Modelscited by 38

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 7.

9 papers.

  1. 2025From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligencecited by 15
  2. 2026SCALER:Synthetic Scalable Adaptive Learning Environment for Reasoningcited by 8
  3. 2025How Many Code and Test Cases Are Enough? Evaluating Test Cases Generation from a Binary-Matrix Perspectivecited by 4
  4. 2026RefineRL: Advancing Competitive Programming with Self-Refinement Reinforcement Learningcited by 2
  5. 2026Beyond Problem Solving: UOJ-Bench for Evaluating Code Generation, Hacking, and Repair in Competitive Programmingcited by 2
  6. 2026X-Coder: Advancing Competitive Programming with Synthetic Tasks, Solutions, and Testscited by 1
  7. 2026ScaleBox: Enabling High-Fidelity and Scalable Code Verification for Large Language Modelscited by 1
  8. 2026The Generalization Spectrum: A Chromatographic Approach to Evaluating Learning Algorithmscited by 0
  9. 2026Coding Agents as Test-Suite Auditors: Finding What Official Suites Miss While Approaching What They Catchcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Two-Stage Reinforcement Learning for Sound and Adversarial Test Generation in Code LLMs
  2. 2026EvolveCoder: Evolving Test Cases via Adversarial Verification for Code Reinforcement Learning
  3. 2025ACECODER: Acing Coder RL via Automated Test-Case Synthesis
  4. 2026CodeScaler: Scaling Code LLM Training and Test-Time Inference via Reward Models
  5. 2025Rethinking Verification for LLM Code Generation: From Generation to Testing
  6. 2026Robust Code RL via Faulty-Code-Driven Test case Synthesis and Dense Reward Shaping
  7. 2025Co-Evolving LLM Coder and Unit Tester via Reinforcement Learning
  8. 2026CodeContests-O: Powering LLMs via Feedback-Driven Iterative Test Case Generation