用图分析提前发现代码修改可能破坏的测试，大幅减少AI编程助手出错。
TDAD: Test-Driven Agentic Development - Reducing Code Regressions in AI Coding Agents via Graph-Based Impact Analysis
- 构建代码与测试间的依赖图，预判修改影响范围。
- 在SWE-bench上将回归率从6.08%降至1.82%，降低70%。
- 轻量级技能可复用，比强行教流程更有效。
AI编程助手虽能解决实际软件问题，但常引入回归——导致此前通过的测试失败。现有基准主要关注修复率，对回归行为研究不足。本文提出TDAD（Test-Driven Agentic Development），一个开源工具，为AI编程助手提供变更前的影响分析。TDAD构建代码与测试间的依赖图，使代理在提交补丁前知晓需验证哪些测试，并可自我修正。该依赖图以轻量级代理技能形式提供，为运行时查询的静态文本文件。在SWE-bench Verified上评估，使用两个开源模型在消费级硬件上运行（Qwen3-Coder 30B，100实例；Qwen3.5-35B-A3B，25实例），相比基线，TDAD将回归率从6.08%降至1.82%，减少70%。而仅添加TDD流程指令但无针对性测试上下文，反而使回归率升至9.94%，甚至高于无干预情况。当作为代理技能部署于另一模型与框架时，问题修复率从24%提升至32%，证实提供上下文信息优于强制流程规范。所有代码、数据及日志均公开于https://github.com/pepealonso95/TDAD。
原文摘要 · Abstract (English)
AI coding agents can resolve real-world software issues, yet they frequently introduce regressions -- breaking tests that previously passed. Current benchmarks focus almost exclusively on resolution rate, leaving regression behavior under-studied. This paper presents TDAD (Test-Driven Agentic Development), an open-source tool that performs pre-change impact analysis for AI coding agents. TDAD builds a dependency map between source code and tests so that before committing a patch, the agent knows which tests to verify and can self-correct. The map is delivered as a lightweight agent skill -- a static text file the agent queries at runtime. Evaluated on SWE-bench Verified with two open-weight models running on consumer hardware (Qwen3-Coder 30B, 100 instances; Qwen3.5-35B-A3B, 25 instances), TDAD reduced regressions by 70% (6.08% to 1.82%) compared to a vanilla baseline. In contrast, adding TDD procedural instructions without targeted test context increased regressions to 9.94% -- worse than no intervention at all. When deployed as an agent skill with a different model and framework, TDAD improved issue-resolution rate from 24% to 32%, confirming that surfacing contextual information outperforms prescribing procedural workflows. All code, data, and logs are publicly available at https://github.com/pepealonso95/TDAD.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。