{"ID":2854618,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.14635","arxiv_id":"2510.14635","title":"ATGen: Adversarial Reinforcement Learning for Test Case Generation","abstract":"Large Language Models (LLMs) excel at code generation, yet their outputs often contain subtle bugs, for which effective test cases are a critical bottleneck. Existing test generation methods, whether based on prompting or supervised fine-tuning, rely on static datasets. This imposes a ``fixed-difficulty ceiling'', fundamentally limiting their ability to uncover novel or more complex bugs beyond their training scope. To overcome this, we introduce ATGen, a framework that trains a test case generator via adversarial reinforcement learning. ATGen pits a test generator against an adversarial code generator that continuously crafts harder bugs to evade the current policy. This dynamic loop creates a curriculum of increasing difficulty challenging current policy. The test generator is optimized via Reinforcement Learning (RL) to jointly maximize ``Output Accuracy'' and ``Attack Success'', enabling it to learn a progressively stronger policy that breaks the fixed-difficulty ceiling of static training. Extensive experiments demonstrate that ATGen significantly outperforms state-of-the-art baselines. We further validate its practical utility, showing it serves as both a more effective filter for Best-of-N inference and a higher-quality reward source for training code generation models. Our work establishes a new, dynamic paradigm for improving the reliability of LLM-generated code.","short_abstract":"Large Language Models (LLMs) excel at code generation, yet their outputs often contain subtle bugs, for which effective test cases are a critical bottleneck. Existing test generation methods, whether based on prompting or supervised fine-tuning, rely on static datasets. This imposes a ``fixed-difficulty ceiling'', fund...","url_abs":"https://arxiv.org/abs/2510.14635","url_pdf":"https://arxiv.org/pdf/2510.14635v1","authors":"[\"Qingyao Li\",\"Xinyi Dai\",\"Weiwen Liu\",\"Xiangyang Li\",\"Yasheng Wang\",\"Ruiming Tang\",\"Yong Yu\",\"Weinan Zhang\"]","published":"2025-10-16T12:49:25Z","proceeding":"cs.SE","tasks":"[\"cs.SE\"]","methods":"[\"Reinforcement Learning\",\"Large Language Model\",\"Language Model\"]","has_code":false}