TDAD: Test-Driven Agentic Development - Reducing Code Regressions in AI Coding Agents via Graph-Based Impact Analysis

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Alonso, Pepe, Yovine, Sergio, Braberman, Victor A.
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918397850157056
author Alonso, Pepe
Yovine, Sergio
Braberman, Victor A.
author_facet Alonso, Pepe
Yovine, Sergio
Braberman, Victor A.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2603_17973
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle TDAD: Test-Driven Agentic Development - Reducing Code Regressions in AI Coding Agents via Graph-Based Impact Analysis
Alonso, Pepe
Yovine, Sergio
Braberman, Victor A.
Software Engineering
Artificial Intelligence
68N30, 68T05
D.2.5; I.2.2
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.
title TDAD: Test-Driven Agentic Development - Reducing Code Regressions in AI Coding Agents via Graph-Based Impact Analysis
topic Software Engineering
Artificial Intelligence
68N30, 68T05
D.2.5; I.2.2
url https://arxiv.org/abs/2603.17973