Repo0：面向从零到全代码生成的设计驱动框架
Repo0: Design-Driven Zero-to-All Code Generation
浏览论文内容
中文总结 AI 辅助
Repo0是面向从零到全代码生成的连续结构演化框架，通过Dual-DAG架构等技术，在RepoCraft数据集上相较RPG大幅提升了代码生成的功能覆盖率与通过率。
中文摘要 AI 辅助
大型语言模型智能体在代码生成领域已取得显著进展，但现有多数系统均假设存在预定义的仓库架构，这一假设并不适用于从零到全代码生成场景——在此场景中，智能体需从自然语言需求直接构建完整软件项目，同时在开发全过程中维持模块化仓库架构。我们提出Repo0，这是一个面向从零到全代码生成的连续结构演化框架。Repo0维护显式架构状态，该状态实例化为双有向无环图（Dual-DAG），由需求级DAG、组件级DAG及其对齐关系构成。从自然语言需求出发，Repo0通过模块化指标引导的结构操作迭代演化组件边界，直至结构收敛；收敛后的架构随后指导测试驱动开发代码生成。我们在RepoCraft提供的6个真实仓库上，使用GPT-5 mini和DeepSeek V3.2对Repo0进行评估，结果显示Repo0在所有设置下均取得最高的功能覆盖率和通过率。与最强的仓库规划基线RPG相比，Repo0的功能覆盖率最高提升20.08个百分点，通过率最高提升29.74个百分点。 ablation实验及结构演化分析进一步证明了Dual-DAG架构状态、模块化引导的结构演化以及显式结构收敛的重要性。
英文摘要
Large language model agents have made substantial progress in code generation, yet most existing systems assume a predefined repository architecture. This assumption does not hold in zero-to-all code generation, where an agent must construct an entire software project directly from natural-language requirements while maintaining a modular repository architecture throughout development. We present Repo0, a continuous structural evolution framework for zero-to-all code generation. Repo0 maintains an explicit architectural state instantiated as a Dual-Directed-Acyclic-Graph (Dual-DAG), consisting of a requirement-level DAG, a component-level DAG, and their alignment relation. Starting from natural-language requirements, it iteratively evolves component boundaries through structural actions guided by modularity metrics until structural convergence, after which the converged architecture guides test-driven development code generation. We evaluate Repo0 on six real-world repositories from RepoCraft using GPT-5 mini and DeepSeek V3.2. Repo0 achieves the highest Functionality Coverage and Pass Rate across all settings. Compared with RPG, the strongest repository-planning baseline, Repo0 improves Functionality Coverage by up to 20.08 percentage points and Pass Rate by up to 29.74 percentage points. Ablation and structural-evolution analyses further demonstrate the importance of the Dual-DAG architectural state, modularity-guided structural evolution, and explicit structural convergence.
发表机构
- Shanghai Jiao Tong University（上海交通大学）
- Chongqing University（重庆大学）
机构由 AI 辅助整理，请以论文原文为准。
