让AI像人一样分步设计算法，靠验证反馈优化每一步选择。
AlgoSkill: Learning to Design Algorithms by Scheduling Human-Like Skills
- 将算法设计拆解为可复用的技能序列，按需调度
- 在竞赛编程和组合优化任务上超越现有方法30%以上
- 适合需要严谨推理和复杂度优化的算法研发者
从自然语言问题描述中设计算法，需识别问题结构、读取约束、选择范式、验证正确性并优化复杂度。现有大模型方法多依赖直接生成或通用自修正，上述步骤隐含未显式建模。我们提出AlgoSkill，将算法设计建模为在带类型标记的算法技能库上的序贯决策过程，包含抽象、约束分析、状态设计、数据结构选择、证明检查、反例构造与复杂度优化等技能。学习到的调度器根据当前设计状态选择技能，而蒙特卡洛树搜索（MCTS）控制器利用编译、测试、压力测试和复杂度分析的验证反馈探索技能序列。在竞赛编程与组合优化基准上的实验表明，AlgoSkill优于直接生成、思维链提示、自修正及无类型技能的MCTS方法。消融实验显示，类型化技能、基于验证的修复和搜索式调度均对性能有贡献。结果支持将自动算法设计视为验证引导的技能调度，而非一次性代码生成。
原文摘要 · Abstract (English)
Designing an algorithm from a natural-language problem statement requires identifying the problem structure, reading constraints, choosing a suitable paradigm, checking correctness, and refining complexity. Existing large language model (LLM) methods often rely on direct generation or generic self-refinement, leaving these steps implicit. We propose AlgoSkill, which models algorithm design as sequential decision-making over a typed library of algorithmic skills, including abstraction, constraint analysis, state design, data-structure selection, proof checking, counterexample construction, and complexity refinement. A learned scheduler proposes skills from the current design state, while a Monte Carlo Tree Search (MCTS) controller explores skill sequences using verification feedback from compilation, testing, stress testing, and complexity analysis. Experiments on competitive programming and combinatorial optimization benchmarks show that AlgoSkill improves over direct LLM generation, chain-of-thought prompting, self-refinement, and MCTS without typed skills. Ablations show that typed skills, verification-based repair, and search-based scheduling each contribute to performance. These results support treating automatic algorithm design as verification-guided skill scheduling rather than one-shot code generation.
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。