LLM自主演化代码，攻克布尔可满足性难题
Autonomous Code Evolution Meets NP-Completeness
- 用LLM代理在整库代码规模上自动优化算法
- 在SAT竞赛2024基准上超越2025冠军解法
- 适合对自动化算法优化与AI编程感兴趣的读者
大型语言模型（LLMs）近期展现出强大的编程能力，不仅可静态生成代码，还能通过智能体框架实现迭代式自演化。受AlphaEvolve启发，我们提出SATLUTION，首个将基于LLM的代码演化扩展至完整项目规模的框架，涵盖数百个文件、数万行C/C++代码。针对经典的NP完全问题——布尔可满足性（SAT），SATLUTION在严格正确性保障和分布式运行时反馈下，协调LLM代理直接演化求解器仓库，并同步自演化其演化策略与规则。基于SAT竞赛2024的代码库与基准测试，所演化出的求解器在性能上显著超越2025年人类设计的优胜方案，同时优于2024年及2025年双届冠军在2024年基准上的表现。
原文摘要 · Abstract (English)
Large language models (LLMs) have recently shown strong coding abilities, enabling not only static code generation but also iterative code self-evolving through agentic frameworks. Recently, AlphaEvolve \cite{novikov2025alphaevolve} demonstrated that LLM-based coding agents can autonomously improve algorithms and surpass human experts, with scopes limited to isolated kernels spanning hundreds of lines of code. Inspired by AlphaEvolve, we present SATLUTION, the first framework to extend LLM-based code evolution to the full repository scale, encompassing hundreds of files and tens of thousands of lines of C/C++ code. Targeting Boolean Satisfiability (SAT), the canonical NP-complete problem and a cornerstone of both theory and applications. SATLUTION orchestrates LLM agents to directly evolve solver repositories under strict correctness guarantees and distributed runtime feedback, while simultaneously self-evolving its own evolution policies and rules. Starting from SAT Competition 2024 codebases and benchmark, SATLUTION evolved solvers that decisively outperformed the human-designed winners of the SAT Competition 2025, and also surpassed both 2024 and 2025 champions on the 2024 benchmarks.
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。