Klear-CodeTest: Scalable Test Case Generation for Code Reinforcement Learning
This addresses the problem of precise feedback for training large language models in code generation, though it appears incremental as it builds on existing test case synthesis methods with enhanced verification.
The paper tackles the challenge of synthesizing high-quality test cases for code reinforcement learning by introducing Klear-CodeTest, a framework that uses a Generator-Validation approach to ensure correctness and coverage, resulting in significant improvements in model performance and training stability.
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.