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

ACL ARR 2025 February Submission7455 Authors

Abstract:

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 large language models (LLMs) can be integrated into evolutionary algorithms (EAs) for heuristic design, their potential is hindered by limitations in balancing exploitation and exploration. We introduce Quality-Uncertainty Balanced Evolution (QUBE), a novel approach that enhances LLM+EA methods by redefining the priority criterion within the FunSearch framework. QUBE employs the Quality-Uncertainty Trade-off Criterion (QUTC), based on our proposed Uncertainty-Inclusive Quality metric, to evaluate and guide the evolutionary process. Through extensive experiments on challenging NP-complete problems, QUBE demonstrates significant performance improvements over FunSearch and baseline methods.
Our code will be made public upon acceptance.

Paper Type: Long

Research Area: NLP Applications

Research Area Keywords: code generation and understanding, mathematical NLP

Contribution Types: Theory

Languages Studied: English

Submission Number: 7455