mlsanityData to 14 Oct 2026

HiFo-Prompt: Prompting with Hindsight and Foresight for LLM-based Automatic Heuristic Design

arXiv 2508.13333 ↗First posted 18 Aug 2025cs.AI cs.NE math.OCcited by 16

Not on the map. Why?

Abstract (arXiv)

LLM-based Automatic Heuristic Design (AHD) within Evolutionary Computation (EC) frameworks has shown promising results. However, its effectiveness is hindered by the use of static operators and the lack of knowledge accumulation mechanisms. We introduce HiFo-Prompt, a framework that guides LLMs with two synergistic prompting strategies: Foresight and Hindsight. Foresight-based prompts adaptively steer the search based on population dynamics, managing the exploration-exploitation trade-off. In addition, hindsight-based prompts mimic human expertise by distilling successful heuristics from past generations into fundamental, reusable design principles. This dual mechanism transforms transient discoveries into a persistent knowledge base, enabling the LLM to learn from its own experience. Empirical results demonstrate that HiFo-Prompt significantly outperforms state-of-the-art LLM-based AHD methods, generating higher-quality heuristics while achieving substantially faster convergence and superior query efficiency. Our code is available at https://github.com/Challenger-XJTU/HiFo-Prompt.

Key facts. Cited by 16 papers in the map (data through 14 Oct 2026). Builds on 25 of its 94 references that are in the map. First posted on arXiv 18 Aug 2025.

Builds on

25 of 94 references.

References · 25

  1. 2017Attention Is All You Needcited by 60,361
  2. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  3. 2015Pointer Networkscited by 895
  4. 2023Large Language Models as Optimizerscited by 864
  5. 2020POMO: Policy Optimization with Multiple Optima for Reinforcement Learningcited by 348
  6. 2024ReEvo: Large Language Models as Hyper-Heuristics with Reflective Evolutioncited by 276
  7. 2024Evolution of Heuristics: Towards Efficient Automatic Algorithm Design Using Large Language Modelcited by 268
  8. 2023Neural Combinatorial Optimization with Heavy Decoder: Toward Large Scale Generalizationcited by 142
  9. 2025Monte Carlo Tree Search for Comprehensive Exploration in LLM-Based Automatic Heuristic Designcited by 109
  10. 2024LLaMEA: A Large Language Model Evolutionary Algorithm for Automatically Generating Metaheuristicscited by 97
  11. 2024LLM Hallucinations in Practical Code Generation: Phenomena, Mechanism, and Mitigationcited by 93
  12. 2024HSEvo: Elevating Automatic Heuristic Design with Diversity-Driven Harmony Search and Genetic Algorithm Using LLMscited by 73
13 more
  1. 2024Self-Contrast: Better Reflection Through Inconsistent Solving Perspectivescited by 71
  2. 2024A Systematic Survey on Large Language Models for Algorithm Designcited by 69
  3. 2024Multi-objective Evolution of Heuristic Using Large Language Modelcited by 54
  4. 2023Algorithm Evolution Using Large Language Modelcited by 53
  5. 2024A Sober Look at LLMs for Material Discovery: Are They Actually Good for Bayesian Optimization Over Molecules?cited by 48
  6. 2024UDC: A Unified Neural Divide-and-Conquer Framework for Large-Scale Combinatorial Optimization Problemscited by 47
  7. 2025Algorithm Discovery With LLMs: Evolutionary Search Meets Reinforcement Learningcited by 46
  8. 2020Cost-aware Bayesian Optimizationcited by 42
  9. 2025CALM: Co-evolution of Algorithms and Language Model for Automatic Heuristic Designcited by 29
  10. 2024Understanding the Importance of Evolutionary Search in Automated Heuristic Design with Large Language Modelscited by 22
  11. 2024Evolve Cost-aware Acquisition Functions Using Large Language Modelscited by 17
  12. 2024Deep Insights into Automated Optimization with Large Language Models and Evolutionary Algorithmscited by 12
  13. 2025RedAHD: Reduction-Based End-to-End Automatic Heuristic Design with Large Language Modelscited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 16.

16 papers.

Sort:

By area:

  1. 2026G-LNS: Generative Large Neighborhood Search for LLM-Based Automatic Heuristic Designcited by 7
  2. 2026TIDE: Tuning-Integrated Dynamic Evolution for LLM-Based Automated Heuristic Designcited by 3
  3. 2026SeaEvo: Advancing Algorithm Discovery with Strategy Space Evolutioncited by 3
  4. 2026RefineEvo: Planning-Guided Heuristic Evolution with Bidirectional Experiencecited by 2
  5. 2026Breaking Validity-Induced Boundaries to Expand Algorithm Search Space: A Two-Stage AST-Based Operator for LLM-Driven Automated Heuristic Evolutioncited by 1
  6. 2026MicroEvo: Knowledge-Guided LLM Sampling for Efficient Microarchitecture Design Space Explorationcited by 1
  7. 2026Language-Grounded Multi-Agent Planning for Personalized and Fair Participatory Urban Sensingcited by 0
  8. 2026CoupleEvo: Evolving Heuristics for Coupled Optimization Problems Using Large Language Modelscited by 0
  9. 2026MeEvo: Metacognitive Evolution Combined with Natural Evolution for Automatic Heuristic Designcited by 0
  10. 2026RELIC: Revealed Principles for Learning Interpretable Composable Skills in Multi-Agent Planningcited by 0
  11. 2026SCOPE: Synthetic Conditional Objectives for Policy Evolution in Black-Box Combinatorial Optimizationcited by 0
  12. 2026AutoSND: From Execution Evidence to Structural Policies for Automated Network Dismantling Heuristic Discoverycited by 0
4 more
  1. 2026From Hand-Crafted to LLM-Based Variation Operators in Metaheuristics: A Tutorialcited by 0
  2. 2026LLMs as Adaptive Meta-Solvers: Strategy-Diverse RL for Industrial-Scale Optimizationcited by 0
  3. 2026SimpleEvol: An Agent-Loop Framework for LLM-Driven Automated Heuristic Design with Minimal Human Priorscited by 0
  4. 2026AdaEva: Accelerating LLM-Driven Algorithm Design with Adaptive Partial Evaluationcited by 0