透過深度研究增強AlphaEvolve實現科學演算法發現

摘要

大型語言模型作為科學助手的潛力巨大，然而現有的代理系統要么僅依賴於算法進化，要么孤立地進行深度研究，這兩種方式都存在關鍵的局限性。純粹的算法進化，如AlphaEvolve，僅依賴於LLM的內部知識，在複雜領域中很快就會遇到瓶頸；而純粹的深度研究則提出未經驗證的想法，導致不切實際或無法實施的解決方案。我們提出了DeepEvolve，這是一個將深度研究與算法進化相結合的代理系統，它將外部知識檢索、跨文件代碼編輯和系統化調試整合到一個反饋驅動的迭代循環中。每次迭代不僅提出新的假設，還對其進行精煉、實施和測試，避免了淺層改進和無效的過度精煉。在化學、數學、生物學、材料和專利等九個基準測試中，DeepEvolve持續改進初始算法，產生了可執行的新算法，並取得了持續的增益。通過彌合無指導進化與無基礎研究之間的差距，DeepEvolve為推進科學算法發現提供了一個可靠的框架。我們的代碼可在https://github.com/liugangcode/deepevolve獲取。

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.

透過深度研究增強AlphaEvolve實現科學演算法發現

Scientific Algorithm Discovery by Augmenting AlphaEvolve with Deep Research

摘要

Support