Repo0：设计驱动的从零到全量代码生成

摘要

大语言模型智能体在代码生成方面取得了显著进展，但现有大多数系统都假设存在预定义的代码仓库架构。这一假设在从零到全量代码生成场景中并不成立，在该场景下，智能体必须直接从自然语言需求构建整个软件项目，并在整个开发过程中保持模块化的仓库架构。我们提出Repo0，一种用于从零到全量代码生成的持续结构演化框架。Repo0维护一个显式的架构状态，具体实例化为双有向无环图（Dual-DAG），由需求级DAG、组件级DAG及其对齐关系组成。从自然语言需求出发，它通过由模块化度量引导的结构化操作迭代演化组件边界，直至结构收敛，随后收敛后的架构指导测试驱动开发的代码生成。我们使用GPT-5 mini和DeepSeek V3.2在RepoCraft中的六个真实仓库上评估Repo0。Repo0在所有设置下均取得了最高的功能覆盖率（Functionality Coverage）和通过率（Pass Rate）。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。消融实验和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。

English

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.