AI 学会从零写整个代码仓库了
以前 AI 写代码只能修修补补，现在它开始能根据文档从头生成整个软件仓库了。研究者造了一个包含 4818 个完整仓库生成任务的数据集 DeNovoSWE，用「分而治之」和「批评-修复」的流程自动生成，不需要人工标注。在 Qwen3-30B 模型上微调后，在 BeyondSWE-Doc2Repo 评测中从 5.8% 飙升到 47.2%。这不是你明天就能用的工具，但它意味着 AI 离「听需求写一个完整软件」又近了一大步。
📄 原文摘要(英文)
As the capabilities of LLM-based code agents continue to advance, their expected role is expanding beyond localized bug fixing in existing codebases toward architecting and implementing complete software repositories from high-level specifications. However, training agents for such long-horizon software engineering tasks remains difficult due to the scarcity of large-scale, verifiable whole-repository generation data. In this paper, we introduce DeNovoSWE, a large-scale dataset for whole-repository generation. DeNovoSWE comprises 4,818 high-quality instances, where each instance requires generating a complete repository from documentation. Our dataset is automatically constructed through a carefully designed sandboxed agentic workflow, enabling scalable curation without human annotation. DeNovoSWE is constructed with "divide and conquer" and critic-repair philosophy. To balance data quality and diversity, we further introduce a difficulty-aware trajectory filtering strategy. Fine-tuning Qwen3-30B-A3B on DeNovoSWE substantially improves long-horizon SWE performance, raising its score on the challenging BeyondSWE-Doc2Repo benchmark from 5.8% to 47.2%.