PathFound: An Agentic Multimodal Model Activating Evidence-seeking Pathological Diagnosis

TL;DR

PathFound is an agentic multimodal model that mimics clinical evidence-seeking behavior to improve diagnostic accuracy in computational pathology through proactive information acquisition.

Contribution

It introduces an evidence-seeking inference framework combining visual, language, and reasoning models trained with reinforcement learning for pathology diagnosis.

Findings

Improves diagnostic accuracy across multiple models

Achieves state-of-the-art performance in diverse scenarios

Effectively discovers subtle pathological details

Abstract

Recent pathological foundation models have substantially advanced visual representation learning and multimodal interaction. However, most models still rely on a static inference paradigm in which whole-slide images are processed once to produce predictions, without reassessment or targeted evidence acquisition under ambiguous diagnoses. This contrasts with clinical diagnostic workflows that refine hypotheses through repeated slide observations and further examination requests. We propose PathFound, an agentic multimodal model designed to support evidence-seeking inference in pathological diagnosis. PathFound integrates the power of pathological visual foundation models, vision-language models, and reasoning models trained with reinforcement learning to perform proactive information acquisition and diagnosis refinement by progressing through the initial diagnosis, evidence-seeking, and final decision stages. Across several large multimodal models, adopting this strategy consistently improves diagnostic accuracy, indicating the effectiveness of evidence-seeking workflows in computational pathology. Among these models, PathFound achieves state-of-the-art diagnostic performance across diverse clinical scenarios and demonstrates strong potential to discover subtle details, such as nuclear features and local invasions.