BioDyad: Synchronize Biomedical Discovery and Machine Learning Engineering

2026-09-25

AI Summary

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.

Abstract

Agentic biomedical machine learning (ML) draws on complementary advances in biomedical evidence acquisition and executable program search. Existing systems connect aspects of these capabilities, but coordinating them throughout program search remains challenging. New evidence must guide candidate construction, execution outcomes must inform subsequent discovery and reuse, and validation demands must fit the search budget. We introduce BioDyad, which couples biomedical discovery and ML engineering through two hierarchies within Monte Carlo graph search. Its scientific hierarchy combines prior biomedical guidance with iterative discovery, then links biomedical plans to execution outcomes in memory for reuse across candidates. Its engineering hierarchy moves candidate programs from smoke execution, through train/validation evaluation, to full-data retraining. We evaluate BioDyad on the 76-task BioXArena benchmark under a two-hour per-task budget with three matched LLM backends. It achieves the highest penalized all-task score and task success rate among four agent methods and a one-shot baseline under each backend. These results support coordinating biomedical discovery and ML engineering to integrate external knowledge into executable programs across heterogeneous biomedical tasks.

Problem

• biomedical machine learning
• program search
• evidence acquisition
• agent coordination
• executable programs

Innovation

• Monte Carlo graph search
• Agentic biomedical machine learning
• dual hierarchies
• program search
• BioDyad