arXiv：cs.CL· Haibo Jin, Peng Kuang, Xucheng Yu, Jerry Wang, Dehao Wu, Haohan Wang·· 3 小时前AI 评分58
LEGO：基于 Agent 原生可复用代码原语的大规模仓库工程研究
Large-scale Repository Engineering via Agent-Native Reusable Code Primitives
AI 导读
论文提出 Code Primitives（带接口契约、依赖闭包、验证测试和来源信息的 agent 原生可复用可执行组件），并构建含 1,424 个已验证原语的 CodeFace 库和 LEGO 方法，用于仓库级代码构建。
正文
Abstract:Large language models equipped with development environments have moved code generation toward repository-scale construction, yet building complete repositories remains difficult because interacting modules, interfaces, configurations, tests, and dependencies must work together. We introduce Code Primitives, agent-native reusable executable components with interface contracts, dependency closures, validation tests, and provenance. Each primitive uses a resident LLM to assess relevance and adapt its implementation, interfaces, and dependencies to the target repository, and we organize 1,424 validated primitives in CodeFace, a searchable library for repository construction. We introduce LEGO (Large-scale repository Engineering via aGent-native reusable cOde primitives), which activates task-relevant primitives, integrates their adapted implementations with task-specific code while resolving cross-component constraints, and revises the result against executed tests. To measure construction end to end, we build LEGO-REPO, a benchmark of 522 executable reconstruction tasks spanning seven software domains, 22 capability tracks, and five difficulty levels, scored against native test suites between an empty-package floor and original-source ceiling. The strongest of 13 evaluated backbones reaches a delivery score of 0.318 and scores zero on 41.0% of tasks; LEGO improves all 13 by 0.1474 on average and raises GPT-5.6-terra from 0.3180 to 0.5134 (+61.4%). In controlled comparisons, adapted primitives outperform retrieved code supplied as context or vendored unchanged. The effect persists against independent repository agents, across three external benchmarks, and with a disjointly re-mined CodeFace; GPT-OSS-20B for adaptation and diagnosis retains 95.1% of the homogeneous score at 24.0% lower cost.
| Comments: | 44 pages |
| Subjects: | Software Engineering (cs.SE); Computation and Language (cs.CL); Computer Vision and Pattern Recognition (cs.CV) |
| Cite as: | arXiv:2610.09079 [cs.SE] |
| (or arXiv:2610.09079v1 [cs.SE] for this version) | |
| https://doi.org/10.48550/arXiv.2610.09079 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Haibo Jin [view email]
[v1]
Tue, 6 Oct 2026 20:20:50 UTC (538 KB)
来源：arXiv：cs.CL · arxiv.org