让软件自动进化代码与文档，修复漏洞并保持语义一致。
EvoGraph: Hybrid Directed Graph Evolution toward Software 3.0
- 用带类型有向图表示软件资产，结合小模型进行智能修改。
- 修复83%安全漏洞，COBOL转Java功能等价率达93%，文档2分钟内更新。
- 适合需要持续演化的遗留系统现代化，降低90%计算成本。
我们提出EvoGraph，一个使软件系统能够自主演化源码、构建流程、文档和任务单的框架。该框架将所有产物表示为带类型的有向图，利用专用于特定语言的小型语言模型（SLMs）施加学习到的突变操作，并通过多目标适应度选择存活个体。在三个基准测试中，EvoGraph成功修复83%已知安全漏洞，将COBOL代码转换为Java后实现93%的功能等价性（经测试验证），并使文档新鲜度保持在两分钟内。实验显示，相比强基线方法，延迟降低40%，特性上线时间缩短七倍。我们进一步扩展该方法至evoGraph，使用语言特异性的小模型对.NET、Lisp、CGI、ColdFusion、旧版Python及C代码库进行现代化改造，在跨语言迁移中实现82%-96%的语义等价性，同时相比大模型降低90%计算开销。EvoGraph的设计针对遗留系统现代化中的实际失效模式，如隐式契约、性能保留与集成演进。结果表明，这为实现可持续控制下的Software 3.0提供了可行路径。
原文摘要 · Abstract (English)
We introduce **EvoGraph**, a framework that enables software systems to evolve their own source code, build pipelines, documentation, and tickets. EvoGraph represents every artefact in a typed directed graph, applies learned mutation operators driven by specialized small language models (SLMs), and selects survivors with a multi-objective fitness. On three benchmarks, EvoGraph fixes 83% of known security vulnerabilities, translates COBOL to Java with 93% functional equivalence (test verified), and maintains documentation freshness within two minutes. Experiments show a 40% latency reduction and a sevenfold drop in feature lead time compared with strong baselines. We extend our approach to **evoGraph**, leveraging language-specific SLMs for modernizing .NET, Lisp, CGI, ColdFusion, legacy Python, and C codebases, achieving 82-96% semantic equivalence across languages while reducing computational costs by 90% compared to large language models. EvoGraph's design responds to empirical failure modes in legacy modernization, such as implicit contracts, performance preservation, and integration evolution. Our results suggest a practical path toward Software 3.0, where systems adapt continuously yet remain under measurable control.
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。