아이디어 검색: 다양한 과학적 방법 탐색을 위한 트리 검색 지침

Idea Search: Guiding Tree Search with Ideas to Explore Diverse Scientific Methods

트리 검색 기반의 LLM 테스트 시간 스케일링은 자동화된 과학 코딩에 강력한 도구입니다. 그러나 순수한 트리 검색은 특히 광범위한 과학적 방법 탐색 공간에서 체계적인 탐색에 어려움을 겪으며, 때로는 지역 최적점에 빠지거나 비생산적인 루프에 갇힐 수 있습니다. 이러한 한계를 극복하기 위해, 우리는 동적으로 변화하는

Tree Search-based test-time scaling of LLMs is a powerful tool for automated scientific coding. However, pure Tree Search sometimes struggles with systematic exploration, becoming trapped in local optima, or unproductive loops, especially in the vast search space of scientific methods. To address this limitation, we propose Idea Search, a framework that systematically integrates a dynamic "Idea Bank" into Tree Search. Idea Search involves three steps: (1) decomposing existing methods into atomic ideas, (2) sampling from this bank of ideas to guide branches of code mutations, and (3) dynamically updating the bank with new ideas discovered through execution. On single-cell RNA-sequencing (scRNA-seq) batch integration, Idea Search reliably breaks the plateau of a strong pure Tree Search baseline, improving the mean score from 0.678 to 0.697 and reaching a best score of 0.728. We then characterize which design choices drive these gains: bank augmentation helps bandit sampling but not random sampling, "Exploratory" prompting that prioritizes new ideas surfaces the rare best-performing solutions, while increasing sampling-level exploration is counterproductive.