通过将深度研究融入AlphaEvolve实现科学算法发现

摘要

大型语言模型作为科学助手展现出巨大潜力，然而现有智能体要么仅依赖算法进化，要么孤立进行深度研究，这两种方式都存在显著局限。纯粹的算法进化，如AlphaEvolve所示，仅依赖于LLM的内部知识，在复杂领域迅速达到瓶颈；而单纯的深度研究则提出未经验证的想法，导致方案不切实际或难以实施。我们提出了DeepEvolve，一个将深度研究与算法进化相结合的智能体，它整合了外部知识检索、跨文件代码编辑和系统化调试，形成反馈驱动的迭代循环。每次迭代不仅提出新假设，还对其进行精炼、实现与测试，避免了浅层改进与无效的过度优化。在化学、数学、生物学、材料科学及专利领域的九项基准测试中，DeepEvolve持续优化初始算法，生成可执行的新算法，并带来持续的性能提升。通过弥合无引导进化与无基础研究之间的鸿沟，DeepEvolve为推进科学算法发现提供了一个可靠框架。我们的代码已发布于https://github.com/liugangcode/deepevolve。

English

Large language models hold promise as scientific assistants, yet existing agents either rely solely on algorithm evolution or on deep research in isolation, both of which face critical limitations. Pure algorithm evolution, as in AlphaEvolve, depends only on the internal knowledge of LLMs and quickly plateaus in complex domains, while pure deep research proposes ideas without validation, resulting in unrealistic or unimplementable solutions. We present DeepEvolve, an agent that integrates deep research with algorithm evolution, uniting external knowledge retrieval, cross-file code editing, and systematic debugging under a feedback-driven iterative loop. Each iteration not only proposes new hypotheses but also refines, implements, and tests them, avoiding both shallow improvements and unproductive over-refinements. Across nine benchmarks in chemistry, mathematics, biology, materials, and patents, DeepEvolve consistently improves the initial algorithm, producing executable new algorithms with sustained gains. By bridging the gap between unguided evolution and research without grounding, DeepEvolve provides a reliable framework for advancing scientific algorithm discovery. Our code is available at https://github.com/liugangcode/deepevolve.

通过将深度研究融入AlphaEvolve实现科学算法发现

Scientific Algorithm Discovery by Augmenting AlphaEvolve with Deep Research

摘要

Support