TDD-Agent Turns Generated Tests Into Evolving Reasoning Artifacts Instead of Post-Hoc Validators

arXiv 2608.16742·medium signalXBlueskyLinkedInCopy link

Rather than using LLM-generated tests as static checkers — which misleads when the tests are themselves wrong — TDD-Agent prompts for executable tests first to force behavioral clarification, then runs iterative dual-track refinement over code and tests using execution feedback. A prompt-only variant (TDD-prompt) isolates the test-first effect and consistently improves on reasoning-based prompting baselines on LiveCodeBench; the full framework outperforms retrieval- and agent-based baselines on the repository-level RepoEval. Notably, refinement improves the tests too — higher pass rates, coverage and mutation scores — which is the part that transfers to real harness design.