用因果推理引导程序进化，提升AI科学家的探索效率。
CausalEvolve: Towards Open-Ended Discovery with Causal Scratchpad
- 引入因果草稿，识别影响结果的关键因素。
- 在4个开放科学任务中显著提升进化效率与解的质量。
- 适合研究自动程序优化与智能探索的学者参考。
基于演化机制的智能体（如AlphaEvolve）是利用大语言模型构建人工智能科学家的重要成果。这类智能体通过迭代改进和演化程序，解决开放性科学问题，借助大语言模型的先验知识与推理能力。然而，现有方法缺乏对演化的定向引导，也缺少有效组织和利用过往演化经验的机制，导致演化效率下降，并在接近已知性能边界时出现振荡行为。为此，我们提出CausalEvolve，其配备因果草稿，利用大语言模型识别并推理演化中的关键引导因素。初始阶段，该系统识别可互补提升目标性能的结果级因素；演化过程中，通过分析演化中的意外模式与溯因推理，假设新因素，进而提供新方向。在4个挑战性开放科学任务上的综合实验表明，CausalEvolve有效提升了演化效率，并发现更优解。
原文摘要 · Abstract (English)
Evolve-based agent such as AlphaEvolve is one of the notable successes in using Large Language Models (LLMs) to build AI Scientists. These agents tackle open-ended scientific problems by iteratively improving and evolving programs, leveraging the prior knowledge and reasoning capabilities of LLMs. Despite the success, existing evolve-based agents lack targeted guidance for evolution and effective mechanisms for organizing and utilizing knowledge acquired from past evolutionary experience. Consequently, they suffer from decreasing evolution efficiency and exhibit oscillatory behavior when approaching known performance boundaries. To mitigate the gap, we develop CausalEvolve, equipped with a causal scratchpad that leverages LLMs to identify and reason about guiding factors for evolution. At the beginning, CausalEvolve first identifies outcome-level factors that offer complementary inspirations in improving the target objective. During the evolution, CausalEvolve also inspects surprise patterns during the evolution and abductive reasoning to hypothesize new factors, which in turn offer novel directions. Through comprehensive experiments, we show that CausalEvolve effectively improves the evolutionary efficiency and discovers better solutions in 4 challenging open-ended scientific tasks.
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。