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.

翻译：基于演化机制的智能体（如AlphaEvolve）是利用大语言模型构建AI科学家的显著成功案例之一。这类智能体通过迭代改进与演化程序，借助大语言模型的先验知识与推理能力，处理开放式科学问题。尽管取得了成功，现有基于演化的智能体仍缺乏针对演化过程的定向引导机制，以及有效组织与利用历史演化经验中获取知识的策略。因此，它们在接近已知性能边界时会出现演化效率下降并表现出振荡行为。为弥补这一不足，我们开发了CausalEvolve，其配备的因果草稿模块能够利用大语言模型识别并推理演化过程中的引导因子。在初始阶段，CausalEvolve首先识别结果层面的因子，这些因子为改进目标指标提供互补性启发。在演化过程中，系统通过检测演化中的意外模式并运用溯因推理来假设新因子，从而开辟新的探索方向。通过综合实验，我们证明CausalEvolve在四项具有挑战性的开放式科学任务中有效提升了演化效率并发现了更优解决方案。