BioDyad: Synchronize Biomedical Discovery and Machine Learning Engineering
This study addresses the challenge of coordinating evidence acquisition with program search in biomedical agents by proposing a dual-level architecture encompassing scientific discovery and engineering execution. These two levels are coupled through Monte Carlo graph search, enabling seamless integration between hypothesis generation and procedural implementation. The method leverages large language model agents alongside hierarchical memory management to establish a dynamic reuse mechanism among evidence, plans, and execution outcomes, thereby facilitating knowledge-guided automated modeling. Evaluated on the BioXArena benchmark, the proposed approach achieves the highest task success rate and overall composite score, significantly outperforming existing baselines.