SAGE: Agentic Framework for Interpretable and Clinically Translatable Computational Pathology Biomarker Discovery

TL;DR

SAGE is a multi-agent framework that systematically generates, evaluates, and validates image-based biomarkers in computational pathology using biological evidence and reasoning.

Contribution

It introduces a structured, multi-agent system for biomarker discovery that integrates biological knowledge, novelty assessment, and automated validation.

Findings

Enables biologically grounded hypothesis generation.

Provides a debate-based mechanism for novelty assessment.

Automates validation on multimodal pathology datasets.

Abstract

Engineered image-based biomarkers offer a clinically interpretable alternative to black-box AI in computational pathology, yet their discovery remains largely intuition-driven, guided by fragmented literature rather than rigorous biological validation. We introduce SAGE (Structured Agentic system for hypothesis Generation and Evaluation), a multi-agent framework that grounds biomarker discovery in biological evidence through three mechanisms: (i) knowledge-graph-anchored hypothesis generation via multi-path ontological reasoning, (ii) a debate-based multi-agent novelty assessment that stress-tests candidate biomarkers against existing literature, and (iii) an end-to-end automated validation pipeline that translates hypotheses directly into executable analyses on multimodal pathology datasets. Together, these components shift biomarker discovery from an intuition-driven, literature-browsing exercise into a structured, traceable reasoning process that clinicians and researchers can inspect, trust, and build upon.