mlsanityData to 14 Oct 2026

Improving Existing Optimization Algorithms with LLMs

arXiv 2502.08298 ↗First posted 12 Feb 2025cs.AI cs.CL cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

The integration of Large Language Models (LLMs) into optimization has created a powerful synergy, opening exciting research opportunities. This paper investigates how LLMs can enhance existing optimization algorithms. Using their pre-trained knowledge, we demonstrate their ability to propose innovative heuristic variations and implementation strategies. To evaluate this, we applied a non-trivial optimization algorithm, Construct, Merge, Solve and Adapt (CMSA) -- a hybrid metaheuristic for combinatorial optimization problems that incorporates a heuristic in the solution construction phase. Our results show that an alternative heuristic proposed by GPT-4o outperforms the expert-designed heuristic of CMSA, with the performance gap widening on larger and denser graphs. Project URL: https://imp-opt-algo-llms.surge.sh/

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 17 of its 29 references that are in the map. First posted on arXiv 12 Feb 2025.

Builds on

17 of 29 references.

References · 17

  1. 2024Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preferencecited by 1,184
  2. 2024A Survey on Large Language Models for Code Generationcited by 658
  3. 2024CodeAgent: Enhancing Code Generation with Tool-Integrated Agent Systems for Real-World Repo-level Coding Challengescited by 282
  4. 2020Unsupervised Translation of Programming Languagescited by 263
  5. 2022Large Language Models Meet NL2Code: A Surveycited by 138
  6. 2023Self-planning Code Generation with Large Language Modelscited by 124
  7. 2024LLaMEA: A Large Language Model Evolutionary Algorithm for Automatically Generating Metaheuristicscited by 97
  8. 2023Improving Code Generation by Training with Natural Language Feedbackcited by 76
  9. 2024A Survey on LLM-based Code Generation for Low-Resource and Domain-Specific Programming Languagescited by 66
  10. 2023Large Language Models for Compiler Optimizationcited by 52
  11. 2024A Survey on Evaluating Large Language Models in Code Generation Taskscited by 44
  12. 2023Large Language Model-Aware In-Context Learning for Code Generationcited by 43
5 more
  1. 2024Evolving Code with A Large Language Modelcited by 43
  2. 2024LLM4AD: A Platform for Algorithm Design with Large Language Modelcited by 33
  3. 2024Prototype2Code: End-to-end Front-end Code Generation from UI Design Prototypescited by 10
  4. 2025Beyond the Hype: Benchmarking LLM-Evolved Heuristics for Bin Packingcited by 9
  5. 2024Grounding Data Science Code Generation with Input-Output Specificationscited by 7

Built on by

Cited by year

Citing papers per year: 2025: 4.

4 papers.

  1. 2025Combinatorial Optimization for All: Using LLMs to Aid Non-Experts in Improving Optimization Algorithmscited by 7
  2. 2025Large Language Models in Operations Research: Methods, Applications, and Challengescited by 6
  3. 2025ACEvo: Adversarial Co-Evolution of Problem Distributions and Solvers for Combinatorial Optimizationcited by 4
  4. 2025LLM-Based Instance-Driven Heuristic Bias In the Context of a Biased Random Key Genetic Algorithmcited by 0