ReEvo: Large Language Models as Hyper-Heuristics with Reflective Evolution

By Haoran Ye, Jiarui Wang, Zhiguang Cao, Guojie Song. Neural Information Processing Systems, 2024

302 citations recorded by the source corpus.

The omnipresence of NP-hard combinatorial optimization problems (COPs) compels domain experts to engage in trial-and-error heuristic design. The long-standing endeavor of design automation has gained new momentum with the rise of large language models (LLMs). This paper introduces Language Hyper-Heuristics (LHHs), an emerging variant of Hyper-Heuristics that leverages LLMs for heuristic generation, featuring minimal manual intervention and open-ended heuristic spaces. To empower LHHs, we present Reflective Evolution (ReEvo), a novel integration of evolutionary search for efficiently exploring the heuristic space, and LLM reflections to provide verbal gradients within the space. Across five heterogeneous algorithmic types, six different COPs, and both white-box and black-box views of COPs, ReEvo yields state-of-the-art and competitive meta-heuristics, evolutionary algorithms, heuristics, and neural solvers, while being more sample-efficient than prior LHHs.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/be7a88babf78512b545f585517704cb597388cbc

Citations in the corpus

• AlphaEvolve: A coding agent for scientific and algorithmic discovery (2025, unknown): “Similar approaches have found use in several scientific and mathematical tasks, including symbolic regression [35, 89], discovering heuristics for combinatorial optimization [63, 115, 117], and synthesizing molecular structures [105].”
• ATLAS: Scaffold-Free Algorithm Synthesis by LLMs via Embedding-Guided Quality-Diversity Search (2026, unknown): “Representative examples include F UN S EARCH [36], E O H [25], R E E VO [57], HSEvo [9], MCTS-AHD [61], CALM [18], H EUR A GENIX [55], ME O H [56], and E O H-S [27].”