BioInsight: Multi-Agent Orchestration for Interactive Biomedical Knowledge Discovery
For biomedical researchers, this addresses the limitation of static AI-generated reports by enabling interactive exploration of evidence, though the novelty is incremental as it combines existing multi-agent and interface generation techniques.
BioInsight introduces a multi-agent system that transforms static biomedical reports into interactive, evidence-centered interfaces, enabling researchers to inspect evidence, assess uncertainty, and refine hypotheses. Evaluated on biomedical QA and evidence synthesis tasks, it achieves best performance, suggesting a shift toward interactive artifacts.
Biomedical researchers increasingly use AI-generated analyses and reports to interpret protein-level signals, but static outputs are often insufficient for research decision-making, where users need to inspect evidence, assess uncertainty, compare mechanisms, and refine hypotheses. We present \textsc{BioInsight}, a multi-agent system that moves from static biomedical report generation to interactive evidence-centered interactive interface generation. Given a disease name, a protein association table, and optional cohort metadata, BioInsight organizes disease-specific evidence through typed intermediate artifacts, including ranked pathways, literature evidence packets, protein-level reasoning notes, citation-grounded reports, dashboard schemas, and rendered interactive interfaces. The system decomposes evidence retrieval from mechanistic reasoning, normalizes citations through deterministic components, and converts the same structured evidence used in the report into an interactive interface. We evaluate BioInsight on standardized biomedical QA, challenging protein-function reasoning, and end-to-end biomedical evidence synthesis. Results show that BioInsight achieves best, and suggest that biomedical AI systems should move beyond text-only and static reports toward provenance-preserving, interactive evidence artifacts.