用形式化契约解决代码生成中的意图模糊问题，提升大型项目生成的稳定性。
Contract-Coding: Towards Repo-Level Generation via Structured Symbolic Paradigm
- 通过形式化语言契约将模糊需求转化为可执行结构
- 在Greenfield-5上实现47%功能成功率，结构完整度近乎完美
- 适合需要高可靠性、大规模代码自动生成的工程场景
从以意图为中心的软件工程（常称“Vibe Coding”）转向，暴露出关键的上下文保真度权衡：模糊的用户意图会淹没线性推理链，导致复杂仓库级生成中的架构崩溃。我们提出Contract-Coding，一种结构化符号范式，通过自主符号锚定，将非结构化意图与可执行代码相连接。通过将模糊意图投影到正式语言契约中，该框架作为单一事实来源（SSOT），实现了拓扑独立性，有效隔离模块间实现细节，降低拓扑执行深度，释放架构并行性。实证显示，在Greenfield-5基准测试中，当前最先进代理存在多种幻觉问题，而Contract-Coding实现47%的功能成功率，同时保持近乎完美的结构完整性。本工作标志着迈向仓库级自主工程的关键一步：从严格“规范遵循”转向鲁棒的意图驱动架构合成。代码已公开于https://github.com/imliinyi/Contract-Coding。
原文摘要 · Abstract (English)
The shift toward intent-driven software engineering (often termed "Vibe Coding") exposes a critical Context-Fidelity Trade-off: vague user intents overwhelm linear reasoning chains, leading to architectural collapse in complex repo-level generation. We propose Contract-Coding, a structured symbolic paradigm that bridges unstructured intent and executable code via Autonomous Symbolic Grounding. By projecting ambiguous intents into a formal Language Contract, our framework serves as a Single Source of Truth (SSOT) that enforces topological independence, effectively isolating inter-module implementation details, decreasing topological execution depth and unlocking Architectural Parallelism. Empirically, while state-of-the-art agents suffer from different hallucinations on the Greenfield-5 benchmark, Contract-Coding achieves 47\% functional success while maintaining near-perfect structural integrity. Our work marks a critical step towards repository-scale autonomous engineering: transitioning from strict "specification-following" to robust, intent-driven architecture synthesis. Our code is available at https://github.com/imliinyi/Contract-Coding.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。