ExecCritic: Learn to Test, Test to Improve for Coding Agents
Execution feedback can guide coding agents toward correct repository repairs, but only when the tests capture the behavior requested by the issue. Agent-generated tests can encode incomplete or incorrect behavioral targets; when the same trajectory writes both the patch and the test, their errors can agree and create false confidence. We introduce ExecCritic, combining a test--verify--revise scaffold with a role-specific reinforcement learning recipe for training agents within it. The scaffold separates test construction from source-code repair: a Test agent independently generates repository-native tests, a fail-closed harness qualifies and freezes them, and a Repair agent revises source code from their execution feedback without changing the tests. Both roles use Qwen-3.5-35B-A3B as the
通过独立生成测试和修复代码，减少虚假信心，提高代码代理的正确性。
- 核心方法
- 引入ExecCritic模型，将测试生成与源代码修复分离，使用角色特定的强化学习方法训练代理。Test代理生成独立测试，修复代理根据执行反馈修订源代码。
- 适合谁读
- 研究者 / 工程师
- 要解决的问题
- 当代码代理同时生成测试和修复代码时，可能会产生错误的一致性，导致虚假信心。
- 关键实验
- 未提供
- 主要贡献
- 提出了一种新的框架ExecCritic，通过分离测试和修复过程，提高了代码代理的准确性和可靠性。
- 意义与局限
- 该研究有助于提高自动代码修复系统的性能，减少错误的一致性问题，但需要更多的实验数据来验证其有效性和泛化能力。