Automated Algorithmic Discovery for Scientific Computing through LLM-Guided Evolutionary Search: A Case Study in Gravitational-Wave Detection

TL;DR

This paper introduces Evo-MCTS, a novel framework combining LLMs and evolutionary search to automatically discover interpretable algorithms for scientific computing, demonstrated through gravitational-wave detection.

Contribution

The paper presents a generalizable, domain-agnostic approach integrating LLMs with tree-structured evolutionary search for interpretable algorithm discovery in scientific computing.

Findings

Achieved 20.2% improvement over domain-specific methods

Achieved 59.1% improvement over LLM-based optimization frameworks

Produced interpretable algorithms that incorporate multiple functional components

Abstract

Automated algorithm discovery in scientific computing faces fundamental challenges: vast design spaces with expensive evaluations, domain-specific physical constraints requiring expert knowledge, and the necessity for interpretable solutions that scientists can validate and understand. We present the Evo-MCTS (Evolutionary Monte Carlo Tree Search) framework, integrating large language models (LLMs) with tree-structured evolutionary search for interpretable algorithm discovery. Evo-MCTS combines reflective code synthesis leveraging LLM domain knowledge, multi-scale evolutionary operations on structured code representations, and interpretable algorithmic pathways emerging from tree-guided exploration. When applied to gravitational wave detection-a challenging domain with continuous parameter spaces and strict physical constraints-Evo-MCTS achieves 20.2% improvement over domain-specific methods and 59.1% over LLM-based optimization frameworks. This improvement arises from its ability to consistently converge toward interpretable algorithmic structures that integrate multiple functional components. Our domain-agnostic architecture establishes a generalizable methodology for automated algorithm discovery in scientific computing, where algorithmic transparency and physical validity are as essential as performance optimization.