Automated Algorithmic Discovery for Scientific Computing through LLM-Guided Evolutionary Search: A Case Study in Gravitational-Wave Detection
This addresses the problem of discovering interpretable and physically valid algorithms for scientists in domains like gravitational wave detection, though it appears incremental as it builds on existing evolutionary and LLM-based methods.
The paper tackled automated algorithm discovery in scientific computing by developing the Evo-MCTS framework, which integrates LLMs with evolutionary search, and achieved a 20.2% improvement over domain-specific methods and 59.1% over LLM-based optimization frameworks in gravitational wave detection.
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.