CodeSpec: Dual Executable Specifications for Agentic Long-Horizon Feature Development
Source
arxiv.org
Author
Peiding Wang, Li Zhang, Fang Liu, Taichuan Li, Yinghao Zhu
Date
Why it matters
Long-horizon feature work drifts because the design only ever exists in free-form reasoning. Compiling sub-requirements into paired architecture and behavior specifications that can be checked for chain completeness beat Claude Code on FeatureBench, at 70.7% pass rate.
Terms in this piece · Glossary
spec-driven development — Writing and agreeing the specification first, then having an agent implement against it — the spec, not the code, becomes the artifact you maintain.
articleSpecFirst: Behavioral Specification Elicitation as a First-Class Step in Agent-Based Program Synthesis from ScratchYihao Chen, Shi Chang, Feng Lin, Khaled Chawa, Boyuan Chen, Shaowei Wang, Ahmed E. Hassan
articleSPECMINE: A Large-Scale Corpus of Spec-Driven Development ArtifactsShyam Agarwal, Bogdan Vasilescu