arXiv cs.AI· Zhuoliang Xie, Changliang Zhou, Genghui Li, Zhenkun Wang·· 9 天前AI 评分27
MECo：基于 LLM 的多任务进化框架实现零样本跨问题泛化
Multi-Task Evolution for Zero-Shot Cross-Problem Generalization using LLMs
AI 导读
研究者提出 MECo，一个由 LLM 驱动的多任务进化框架，用于零样本跨问题泛化。MECo 维护按任务区分的启发式种群，用基于跨任务种群表现的迁移差距引导种群交互，实现启发式的迁移与重组，并通过奖励各成员对源任务组合的额外覆盖来构建紧凑启发式集合，直接应用于目标问题而无需额外搜索或适配。
正文 · 原文
Abstract:Designing effective heuristics for diverse combinatorial optimization problems requires substantial expertise and repeated search. Large language models (LLMs) automate heuristic generation and refinement, but heuristic search typically depends on evaluation feedback from the problem being optimized. Generalizing to new problem definitions using only source-task feedback therefore remains a central challenge. We introduce MECo, an LLM-driven multi-task evolutionary framework for zero-shot cross-problem generalization. MECo maintains task-conditioned heuristic populations and uses a transfer gap based on cross-task population performance to guide their interactions. These interactions enable the transfer and recombination of heuristics. A complementary selection criterion then constructs a compact heuristic set by rewarding each member's additional coverage of source combinations. The selected set is applied to target problems without further search or adaptation. Experiments on 32 problem variants across vehicle routing (VRP) and flexible job-shop scheduling (FJSP) show that MECo achieves the lowest mean costs compared with eight automated heuristic design (AHD) baselines under the same budgets. On out-of-domain problems, it outperforms the strongest baseline in each family. Moreover, integrating the framework of MECo with different AHD methods improves their ID and OOD performance in both families, supporting its effectiveness across different methods.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.03316 [cs.AI] |
| (or arXiv:2610.03316v2 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.03316 arXiv-issued DOI via DataCite |
Submission history
From: Xie Zhuoliang [view email]
[v1]
Fri, 2 Oct 2026 13:53:34 UTC (338 KB)
[v2]
Thu, 8 Oct 2026 14:01:07 UTC (338 KB)
来源：arXiv cs.AI · arxiv.org