用动态思想库引导树搜索，提升科学代码生成多样性与性能
Idea Search: Guiding Tree Search with Ideas to Explore Diverse Scientific Methods
- 将科学方法拆解为原子思想，构建可更新的思想库
- 在单细胞测序任务中将平均得分从0.678提升至0.697，最高达0.728
- 探索性提示有效发现最优解，适合需要创新的科研自动化场景
基于树搜索的LLM测试时扩展是自动化科学编程的强大工具。然而，纯树搜索在广阔的科学方法搜索空间中常陷入局部最优或无意义循环，难以系统探索。为此，我们提出Idea Search框架，通过动态“思想库”整合到树搜索中：首先将现有方法分解为原子思想；其次从思想库采样以引导代码变异分支；最后通过执行结果动态更新思想库。在单细胞RNA测序（scRNA-seq）批次整合任务中，Idea Search稳定突破强基线的性能瓶颈，平均得分从0.678提升至0.697，最佳得分达0.728。我们进一步分析发现：思想库扩充有助于赌徒采样但无助于随机采样；强调新思想的“探索性”提示能有效暴露罕见最优解，而增加采样层面探索反而适得其反。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。