CodeSpec: Dual Executable Specifications for Agentic Long-Horizon Feature Development
This paper proposes CodeSpec, a method for reliable feature development in repository-level software using dual executable specifications.
Introduces CodeSpec, a dual executable specification method for reliable feature development in repository-level software
Keywords
Before reading this…
Applications
- →Feature development in existing repositories
To understand this paper, make sure you know these concepts first:
- Understanding of software development, codebases, and toolsfind papers →
Abstract
More Like ThisLLM-based code agents have advanced repository-level software development through iterative interaction with codebases and tools. However, feature development requires integrating new behaviors into existing architectures through coherent cross-component functional chains. Existing agents typically derive such chains through free-form reasoning, often producing unreliable feature designs with incomplete functional chains. Moreover, textual designs are difficult to verify and enforce, making it challenging to maintain design-implementation consistency throughout long-horizon development. We propose CodeSpec, a dual executable specification method for repository-level feature development. It builds reliable functional chains from evidence pairing sub-requirement semantics with repository architectures, then compiles them into complementary architecture and behavior specifications that check chain completeness and correctness while preserving design-implementation consistency over long interactions. On FeatureBench, which targets feature development in existing repositories, CodeSpec achieves 70.7%, 55.0%, and 49.9% pass rates under DeepSeek-V4-Pro, outperforming representative baselines such as Claude Code. Results on the repository generation benchmark NL2Repo-Bench further demonstrate its generalizability.