Scientific Algorithm Discovery by Augmenting AlphaEvolve with Deep Research
This work addresses the challenge of developing reliable scientific assistants for researchers in fields like chemistry and biology, though it appears incremental as it combines existing approaches rather than introducing a new paradigm.
The paper tackled the problem of scientific algorithm discovery by integrating deep research with algorithm evolution to overcome limitations of existing agents, resulting in DeepEvolve, which consistently improved initial algorithms across nine benchmarks in various domains, producing executable new algorithms with sustained gains.
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.