paper-with-me

홈 › Papers

Evolution of Heuristics: Towards Efficient Automatic Algorithm Design Using Large Language Model

2024-01-04 · Fei Liu, Xialiang Tong, Mingxuan Yuan, Xi Lin, Fu Luo, Zhenkun Wang, Zhichao Lu, Qingfu Zhang

Heuristics are widely used for dealing with complex search and optimization problems. However, manual design of heuristics can be often very labour extensive and requires rich working experience and knowledge. This paper proposes Evolution of Heuristic (EoH), a novel evolutionary paradigm that leverages both Large Language Models (LLMs) and Evolutionary Computation (EC) methods for Automatic Heuristic Design (AHD). EoH represents the ideas of heuristics in natural language, termed thoughts. They are then translated into executable codes by LLMs. The evolution of both thoughts and codes in an evolutionary search framework makes it very effective and efficient for generating high-performance heuristics. Experiments on three widely studied combinatorial optimization benchmark problems demonstrate that EoH outperforms commonly used handcrafted heuristics and other recent AHD methods including FunSearch. Particularly, the heuristic produced by EoH with a low computational budget (in terms of the number of queries to LLMs) significantly outperforms widely-used human hand-crafted baseline algorithms for the online bin packing problem.

📄 PDF Abstract BibTeX arXiv:2401.02051

Code (6)

feiliu36/eoh 공식 구현
FeiLiu36/LLM4MOEA
XAI-liacs/BLADE
ai4co/llm-as-hh pytorch
ai4co/reevo pytorch
nico-koltermann/contextual-evolution-of-heuristics

Tasks

Combinatorial OptimizationLanguage ModelingLanguage ModellingLarge Language ModelTraveling Salesman Problem

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

Experience-Guided Reflective Co-Evolution of Prompts and Heuristics for Automatic Algorithm Design

2025-09-29 · Yihong Liu, Junyi Li, Wayne Xin Zhao, Hongyu Lu 외 arxiv

Combinatorial optimization problems are traditionally tackled with handcrafted heuristic algorithms, which demand extensive domain expertise and significant implementation effort. Recent progress has highlighted the pote…

CALM: Co-evolution of Algorithms and Language Model for Automatic Heuristic Design

2025-05-18 · Ziyao Huang, Weiwei Wu, Kui Wu, JianPing Wang 외

Tackling complex optimization problems often relies on expert-designed heuristics, typically crafted through extensive trial and error. Recent advances demonstrate that large language models (LLMs), when integrated into …

GPULanguage ModelingLanguage ModellingQuantization

QUBE: Enhancing Automatic Heuristic Design via Quality-Uncertainty Balanced Evolution

2024-12-30 · Zijie Chen, Zhanchao Zhou, Yu Lu, Renjun Xu 외

Solving NP-hard problems traditionally relies on heuristics, yet manually designing effective heuristics for complex problems remains a significant challenge. While recent advancements like FunSearch have shown that larg…

DiversityEvolutionary Algorithms

TrajEvo: Designing Trajectory Prediction Heuristics via LLM-driven Evolution

2025-05-07 · Zhikai Zhao, Chuanbo Hua, Federico Berto, Kanghoon Lee 외

Trajectory prediction is a crucial task in modeling human behavior, especially in fields as social robotics and autonomous vehicle navigation. Traditional heuristics based on handcrafted rules often lack accuracy, while …

DiversityPredictionTrajectory Prediction

AutoRNet: Automatically Optimizing Heuristics for Robust Network Design via Large Language Models

2024-10-23 · He Yu, Jing Liu

Achieving robust networks is a challenging problem due to its NP-hard nature and complex solution space. Current methods, from handcrafted feature extraction to deep learning, have made progress but remain rigid, requiri…

DiversityEvolutionary Algorithms