cs.CVNov 14, 2026

PathLoop: Self-Evolving Multi-Agent Reasoning for Evidence-Grounded Whole-Slide Image Analysis

Authors: Jincheng Li, Zhengyi Liu, Zelin Liu, Yihui Zhan, Yifei Sun, Xiangyu Li, Minye Shao, Lingyao Kong, 

Organizations: University of Science and Technology of China · Shanghai Artificial Intelligence Laboratory · MIRACLE Lab · The Hong Kong University of Science and Technology (Guangzhou) · 

Abstract

Analyzing whole-slide images (WSIs) requires combining evidence across tissue regions and spatial scales. Multi-agent systems offer a promising approach to this task. However, existing systems make limited use of molecular evidence, often select visually prominent but less representative regions while overlooking global context, and struggle to reuse experience from previous cases. To address these challenges, we present PathLoop, a self-evolving multi-agent framework that integrates omics data for evidence-grounded WSI analysis. Specifically, PathLoop coordinates visual and omics interpreters across slide, patch, and pixel levels, using molecular signals to guide region selection and combining local tissue details with global slide features. A judgment agent then checks the consistency of the collected evidence against Pathology-Wiki, a knowledge base built from 48 entries across 24 organ systems, and triggers re-examination when the evidence is inconsistent. To reuse past experience, a four-level memory stores reasoning trajectories, practical tips, skills, and tools to guide future cases, forming a loop of evidence collection, review, and memory update. We evaluate PathLoop on four TCGA cohorts with biomarker prediction, survival prediction, and subtype classification. The results demonstrate the effectiveness of PathLoop across these tasks and support its use for evidence-grounded WSI analysis.

Figures & tables

Explore similar work

CardsList
  1. PathAgentBench: Benchmarking Evidence-Seeking Vision-Language Models on Whole-Slide Pathology Image

    Jul 21, 2026Dankai Liao, Tianyi Zhang, Yufeng Wu +6VLM EvaluationMedical VLMs

  2. Beyond Relevance: Bayesian Evidence Acquisition for Agentic Whole-Slide Image Reasoning

    Aug 6, 2026Bryan Wong, Xun Xu, Huazhu Fu +2Visual Question AnsweringComputational Pathology

  3. SlideBank: A Persistent Hierarchical Evidence Bank for Consistent Whole-Slide Reasoning

    Aug 31, 2026Beidi Zhao, Gexin Huang, Ciro Zhang +6Memory-Augmented VLMsMedical Visual Question Answering