BioInsight: Multi-Agent Orchestration for Interactive Biomedical Knowledge Discovery

2026-06-18

AI Summary

Static AI reports struggle to meet the interactive demands of biomedical research, particularly in evidence review, uncertainty assessment, and iterative hypothesis refinement. To address this limitation, this work proposes the first system that integrates multi-agent collaboration with evidence provenance, generating typed intermediate artifacts from disease names, protein association tables, and optional cohort metadata, which are then automatically rendered into an interactive evidence-centric interface. By decoupling mechanistic reasoning from evidence retrieval and standardizing certainty-qualified citations, the approach enables an interpretable and traceable knowledge discovery pipeline. The system achieves state-of-the-art performance across benchmark tasks in biomedical question answering, protein function inference, and end-to-end evidence synthesis, demonstrating the efficacy of interactive evidence artifacts in supporting dynamic scientific inquiry.

Abstract

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.

Problem

• interactive biomedical knowledge discovery
• static AI reports
• evidence-centered interface
• biomedical decision-making
• protein-level reasoning

Innovation

• multi-agent system
• interactive interface generation
• evidence-centered reasoning
• structured biomedical artifacts
• provenance-preserving AI