arXiv cs.AI· Jianghan Zhu, Cong Zhang, Ni Zhang, Yifan Yang, Yew Soon Ong, Zhiguang Cao·· 4 小时前AI 评分41
HEMO：利用自进化优化多目标组合优化的 LLM 算子设计框架
HEMO: Harness Self-Evolution for Multi-Objective Combinatorial Optimization
AI 导读
研究者提出 HEMO，将多目标组合优化（MOCO）中自动算子设计（AOD）的 harness 本身作为自进化目标，通过持久 harness 状态逐模块更新检索、算子改进、父代选择与搜索编排逻辑，并以 discounted UCB 调度器引导适应。实验覆盖 8 个 MOCO 任务和 2 种进化骨干，在传统进化、神经及 LLM-based AOD 基线中表现优异，并能迁移到相关任务。
正文 · 原文
Abstract:Automatic operator design (AOD) has increasingly adopted large language models (LLMs) to generate problem-specific search and variation operators for multi-objective combinatorial optimization (MOCO). Yet most methods evolve the operators while leaving the process that discovers them fixed. This limits adaptation as new Pareto trade-offs and operator interactions change where and how the search should proceed. We introduce HEMO, which makes the AOD harness itself a self-evolving optimization target. HEMO maintains a persistent harness state and updates one module at a time, revising the logic that determines which experience to retrieve, which operators to improve, which parents to select, and how to formulate the orchestration of search steps. Downstream solution quality and runtime guide these updates, while a discounted UCB scheduler directs adaptation toward promising modules as their utility changes. A persistent memory filesystem preserves candidate outcomes and diagnostic feedback across harness states, enabling successive states to build on accumulated optimization experience. Experiments across eight MOCO tasks and two structurally distinct evolutionary backbones demonstrate strong performance against conventional evolutionary, neural, and LLM-based AOD baselines, together with effective transfer to related tasks. HEMO extends automatic operator design beyond evolving individual operators to improving the search process that discovers them.
| Comments: | 48 pages, including supplementary material; 5 figures and 13 tables |
| Subjects: | Neural and Evolutionary Computing (cs.NE); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.40023 [cs.NE] |
| (or arXiv:2610.40023v1 [cs.NE] for this version) | |
| https://doi.org/10.48550/arXiv.2610.40023 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Jianghan Zhu [view email]
[v1]
Thu, 29 Oct 2026 13:32:00 UTC (3,909 KB)
来源：arXiv cs.AI · arxiv.org