大型语言模型何以成为优秀优化器？LLM引导进化搜索的轨迹分析

摘要

近期研究表明，在进化和代理优化系统中协调大语言模型（LLM）具有广阔前景，然而驱动这些优化增益的内在机制仍不明确。本研究对LLM引导的进化搜索展开大规模分析，收集了15种LLM在8项任务中的优化轨迹。尽管零样本问题解决能力与最终优化结果存在相关性，但其仅能解释部分差异：初始能力相近的模型往往会产生截然不同的搜索轨迹与结果。通过轨迹分析发现，强LLM优化器表现为局部优化器，能持续产生渐进式改进，同时逐步将搜索范围收敛至语义空间的特定区域；而弱优化器则出现显著语义漂移，表现为偶发性突破后陷入停滞。值得注意的是，多种解决方案新颖性指标均无法预测最终性能——只有当搜索过程充分聚焦于解空间的高性能区域时，新颖性才具有积极意义。本研究揭示了轨迹分析对于理解和改进基于LLM的优化系统的重要性，并为其设计与训练提供了可操作的见解。

English

Recent work has demonstrated the promise of orchestrating large language models (LLMs) within evolutionary and agentic optimization systems. However, the mechanisms driving these optimization gains remain poorly understood. In this work, we present a large-scale study of LLM-guided evolutionary search, collecting optimization trajectories for 15 LLMs across 8 tasks. Although zero-shot problem-solving ability correlates with final optimization outcomes, it explains only part of the variance: models with similar initial capability often induce dramatically different search trajectories and outcomes. By analyzing these trajectories, we find that strong LLM optimizers behave as local refiners, producing frequent incremental improvements while progressively localizing the search in semantic space. Conversely, weaker optimizers exhibit large semantic drift, with sporadic breakthroughs followed by stagnation. Notably, various measures of solution novelty do not predict final performance; novelty is beneficial only when the search remains sufficiently localized around high-performing regions of the solution space. Our results highlight the importance of trajectory analysis for understanding and improving LLM-based optimization systems and provide actionable insights for their design and training.

大型语言模型何以成为优秀优化器？LLM引导进化搜索的轨迹分析

What Makes an LLM a Good Optimizer? A Trajectory Analysis of LLM-Guided Evolutionary Search

摘要

Support