mlsanityData to 7 Oct 2026

EoH-S: Evolution of Heuristic Set using LLMs for Automated Heuristic Design

arXiv 2508.03082 ↗First posted 5 Aug 2025cs.AIcited by 32

Not on the map. Why?

Abstract (arXiv)

Automated Heuristic Design (AHD) using Large Language Models (LLMs) has achieved notable success in recent years. Despite the effectiveness of existing approaches, they only design a single heuristic to serve all problem instances, often inducing poor generalization across different distributions or settings. To address this issue, we propose Automated Heuristic Set Design (AHSD), a new formulation for LLM-driven AHD. The aim of AHSD is to automatically generate a small-sized complementary heuristic set to serve diverse problem instances, such that each problem instance could be optimized by at least one heuristic in this set. We show that the objective function of AHSD is monotone and supermodular. Then, we propose Evolution of Heuristic Set (EoH-S) to apply the AHSD formulation for LLM-driven AHD. With two novel mechanisms of complementary population management and complementary-aware memetic search, EoH-S could effectively generate a set of high-quality and complementary heuristics. Comprehensive experimental results on three AHD tasks with diverse instances spanning various sizes and distributions demonstrate that EoH-S consistently outperforms existing state-of-the-art AHD methods and achieves up to 60% performance improvements.

Key facts. Cited by 32 papers in the map (data through 7 Oct 2026). Builds on 13 of its 50 references that are in the map. First posted on arXiv 5 Aug 2025.

Builds on

13 of 50 references.

References · 13

  1. 2017A Survey on Multi-Task Learningcited by 838
  2. 2025AlphaEvolve: A coding agent for scientific and algorithmic discoverycited by 763
  3. 2024ReEvo: Large Language Models as Hyper-Heuristics with Reflective Evolutioncited by 266
  4. 2020Generalize a Small Pre-trained Model to Arbitrarily Large TSP Instancescited by 161
  5. 2023Neural Combinatorial Optimization with Heavy Decoder: Toward Large Scale Generalizationcited by 140
  6. 2025Monte Carlo Tree Search for Comprehensive Exploration in LLM-Based Automatic Heuristic Designcited by 100
  7. 2024LLaMEA: A Large Language Model Evolutionary Algorithm for Automatically Generating Metaheuristicscited by 92
  8. 2024HSEvo: Elevating Automatic Heuristic Design with Diversity-Driven Harmony Search and Genetic Algorithm Using LLMscited by 68
  9. 2024A Systematic Survey on Large Language Models for Algorithm Designcited by 65
  10. 2025CALM: Co-evolution of Algorithms and Language Model for Automatic Heuristic Designcited by 28
  11. 2022On the Generalization of Neural Combinatorial Optimization Heuristicscited by 24
  12. 2025Beyond the Hype: Benchmarking LLM-Evolved Heuristics for Bin Packingcited by 9
1 more
  1. 2024Prompt Learning for Generalized Vehicle Routingcited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 29.

32 papers.

Sort:

By area:

  1. 2025CodeEvolve: an open source evolutionary coding agent for algorithmic discovery and optimizationcited by 37
  2. 2025A Systematic Survey on Large Language Models for Evolutionary Optimization: From Modeling to Solvingcited by 9
  3. 2026G-LNS: Generative Large Neighborhood Search for LLM-Based Automatic Heuristic Designcited by 7
  4. 2025VRPAgent: LLM-Driven Discovery of Heuristic Operators for Vehicle Routing Problemscited by 6
  5. 2026PathWise: Planning through World Model for Automated Heuristic Design via Self-Evolving LLMscited by 5
  6. 2026Automated Discovery Has No Universally Superior Harnesscited by 4
  7. 2026TIDE: Tuning-Integrated Dynamic Evolution for LLM-Based Automated Heuristic Designcited by 3
  8. 2026AHD Agent: Agentic Reinforcement Learning for Automatic Heuristic Designcited by 3
  9. 2026MEMENTO: Memory-Guided Memetic Code-as-Policy Evolutioncited by 3
  10. 2026Game-Theoretic Co-Evolution for LLM-Based Heuristic Discoverycited by 2
  11. 2026LLM-Driven Co-Evolutionary Automated Heuristic Design for Bi-Component Coupled Combinatorial Optimizationcited by 2
  12. 2026Algorithmic Prompt-Augmentation for Efficient LLM-Based Heuristic Design for A* Searchcited by 1
20 more
  1. 2026Breaking Validity-Induced Boundaries to Expand Algorithm Search Space: A Two-Stage AST-Based Operator for LLM-Driven Automated Heuristic Evolutioncited by 1
  2. 2026SpecAHD: Localize to Specialize for Automated Heuristic Design in Large-Scale Routing Problemscited by 1
  3. 2026MuEvo: LLM-Driven Evolution of Multi-Heuristic Ensemblecited by 1
  4. 2026ATLAS: Scaffold-Free Algorithm Synthesis by LLMs via Embedding-Guided Quality-Diversity Searchcited by 1
  5. 2026CoupleEvo: Evolving Heuristics for Coupled Optimization Problems Using Large Language Modelscited by 0
  6. 2026LLMSYS-HPOBench: Hyperparameter Optimization Benchmark Suite for Real-World LLM Systemscited by 0
  7. 2026MeEvo: Metacognitive Evolution Combined with Natural Evolution for Automatic Heuristic Designcited by 0
  8. 2026RAISE: LLM-based Automated Heuristic Design with Robust Adversary Instance Searchcited by 0
  9. 2026RELIC: Revealed Principles for Learning Interpretable Composable Skills in Multi-Agent Planningcited by 0
  10. 2026LLM-Guided Evolutionary Search for Constraint Model Reformulation to Improve Solver Efficiencycited by 0
  11. 2026Beyond Average Performance: Dynamic Instance Clustering and Specialized Algorithm Design in LLM-Assisted Evolutionary Searchcited by 0
  12. 2026PACE: Primitive-Aware Code Evolution for Automated Algorithm Designcited by 0
  13. 2026MOSAIC: Adversarial Co-evolution of Specialist Heuristics and Problem Instances for LLM-based Automated Heuristic Designcited by 0
  14. 2026ES-AHD: An Evolution Strategy Framework for Automatic Heuristic Designcited by 0
  15. 2026LLM-Driven Algorithm Design for Quantum Circuit Synthesis based on Binary Decision Diagramscited by 0
  16. 2026RouteRepair: Instance-Level Failure Diagnosis and Targeted Repair in LLM-Based Automated Heuristic Design for Routing Optimizationcited by 0
  17. 2026T-GADE: Thermodynamical Generative-AI-Driven Evolution of LLM Artifactscited by 0
  18. 2026PINNForge: Execution-Grounded Evolutionary Design of Physics-Informed Neural Networkscited by 0
  19. 2026LLMs as Adaptive Meta-Solvers: Strategy-Diverse RL for Industrial-Scale Optimizationcited by 0
  20. 2026SimpleEvol: An Agent-Loop Framework for LLM-Driven Automated Heuristic Design with Minimal Human Priorscited by 0