PathAgent: Toward Interpretable Analysis of Whole-slide Pathology Images via Large Language Model-based Agentic Reasoning
This addresses the need for interpretable diagnostic tools in pathology, offering a transparent assistant for clinicians, though it is incremental as it builds on existing LLM and agent frameworks.
The paper tackled the problem of opaque predictions in whole-slide image analysis by introducing PathAgent, an LLM-based agent framework that emulates human expert reasoning, resulting in strong zero-shot generalization across five datasets and surpassing task-specific baselines in visual question-answering tasks.
Analyzing whole-slide images (WSIs) requires an iterative, evidence-driven reasoning process that parallels how pathologists dynamically zoom, refocus, and self-correct while collecting the evidence. However, existing computational pipelines often lack this explicit reasoning trajectory, resulting in inherently opaque and unjustifiable predictions. To bridge this gap, we present PathAgent, a training-free, large language model (LLM)-based agent framework that emulates the reflective, stepwise analytical approach of human experts. PathAgent can autonomously explore WSI, iteratively and precisely locating significant micro-regions using the Navigator module, extracting morphology visual cues using the Perceptor, and integrating these findings into the continuously evolving natural language trajectories in the Executor. The entire sequence of observations and decisions forms an explicit chain-of-thought, yielding fully interpretable predictions. Evaluated across five challenging datasets, PathAgent exhibits strong zero-shot generalization, surpassing task-specific baselines in both open-ended and constrained visual question-answering tasks. Moreover, a collaborative evaluation with human pathologists confirms PathAgent's promise as a transparent and clinically grounded diagnostic assistant.