ATLAS：基于嵌入引导的质量多样性搜索的无支架大语言模型算法合成
ATLAS: Scaffold-Free Algorithm Synthesis by LLMs via Embedding-Guided Quality-Diversity Search
浏览论文内容
中文总结 AI 辅助
ATLAS是基于LLM的无支架全算法合成框架，通过嵌入引导质量多样性搜索解决全算法设计空间问题，在NP难问题上优于相关基线，可保留不同区域的多类算法。
中文摘要 AI 辅助
大多数基于大语言模型（LLM）的自动化算法设计方法会在人类指定的支架内优化特定组件，固定整体结构与组件间的交互。本文提出ATLAS，一种用于组合优化中无支架全算法合成的嵌入引导质量多样性框架。问题规范提供目标与约束；最小I/O接口仅固定实例与解的格式；LLM选择并重构组件、交互及控制流。这种自由度扩大了搜索空间，存在无效候选及过早收敛至单一设计区域的风险。ATLAS可独立检测执行、接口及可行性故障，重新计算目标并应用误差条件修复；基于相似度的存档管理在嵌入空间区域间保留算法，以应对过早收敛。其三层搜索机制：优化最佳设计、为其他区域提供专属优化机会、执行跨区域合成以重组组件及其交互。在四个NP难问题上，ATLAS的表现优于多种最先进的组件合成方法及匹配的全合成基线，同时与强大的人工设计算法具有竞争力。一次ATLAS运行可保留来自不同嵌入空间区域的多个性能相当的算法，而非单一设计。代码检查发现，这些多组件设计在主要构造或全局搜索主干上存在差异。我们的结果表明，嵌入引导的质量多样性搜索可使扩大后的全算法设计空间具备实际可搜索性。源代码及精确可执行提示可在<此https URL>获取。
英文摘要
Most LLM-based automated algorithm design methods optimize a designated component within a human-specified scaffold, fixing overall organization and component interactions. We present ATLAS, an embedding-guided quality-diversity framework for scaffold-free full-algorithm synthesis in combinatorial optimization. The problem specification supplies objectives and constraints; a minimal I/O interface fixes only instance and solution formats; the LLM chooses and restructures components, interactions, and control flow. This freedom enlarges the search space, risking invalid candidates and premature convergence to one design region. ATLAS independently detects execution, interface, and feasibility failures, recomputes objectives, and applies error-conditioned repair; similarity-based archive management preserves algorithms across embedding-space regions to counter premature convergence. Its three-layer search refines the best design, gives other regions dedicated refinement opportunities, and performs cross-region synthesis to recombine components and their interactions. Across four NP-hard problems, ATLAS outperforms several state-of-the-art component-synthesis methods and a matched full-synthesis baseline while remaining competitive with strong human-designed algorithms. One ATLAS run retains several algorithms with comparable performance from distinct embedding-space regions rather than a single design. Code inspection finds that these multi-component designs differ in their primary construction or global-search backbone. Our results suggest that embedding-guided quality-diversity search can make the enlarged full-algorithm design space practically searchable. Source code and exact executable prompts are available at https://github.com/Danial-Yazdani/ATLAS .
