# PathoSage: Towards Multi-Source Evidence Adjudication in Pathology via Experience-Aware Agentic Workflow

arXiv: https://arxiv.org/abs/2606.07549 · HTML: https://mlsanity.com/paper/2606.07549/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Medical vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 30 of its 77 references that are in the map.
- First posted on arXiv 18 May 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Medical vision-language models](https://mlsanity.com/mllm/medical-vision-language-models/)
- LLM agents and tool use / [Medical and scientific domain agents](https://mlsanity.com/agents/medical-and-scientific-domain-agents/)

## Builds on (most cited first, 30 of 30)

- [PathVQA: 30000+ Questions for Medical Visual Question Answering](https://mlsanity.com/paper/2003.10286/) (2020)
- [MedXpertQA: Benchmarking Expert-Level Medical Reasoning and Understanding](https://mlsanity.com/paper/2501.18362/) (2025)
- [MemOS: A Memory OS for AI System](https://mlsanity.com/paper/2507.03724/) (2025)
- [XSkill: Continual Learning from Experience and Skills in Multimodal Agents](https://mlsanity.com/paper/2603.12056/) (2026)
- [MemVerse: Multimodal Memory for Lifelong Learning Agents](https://mlsanity.com/paper/2512.03627/) (2025)
- [PathAlign: A vision-language model for whole slide images in histopathology](https://mlsanity.com/paper/2406.19578/) (2024)
- [CPathAgent: An Agent-based Foundation Model for Interpretable High-Resolution Pathology Image Analysis Mimicking Pathologists' Diagnostic Logic](https://mlsanity.com/paper/2505.20510/) (2025)
- [Evidence-based diagnostic reasoning with multi-agent copilot for human pathology](https://mlsanity.com/paper/2506.20964/) (2025)
- [PathAgent: Toward Interpretable Analysis of Whole-slide Pathology Images via Large Language Model-based Agentic Reasoning](https://mlsanity.com/paper/2511.17052/) (2025)
- [A co-evolving agentic AI system for medical imaging analysis](https://mlsanity.com/paper/2509.20279/) (2025)
- [ToolMem: Enhancing Multimodal Agents with Learnable Tool Capability Memory](https://mlsanity.com/paper/2510.06664/) (2025)
- [A Versatile Pathology Co-pilot via Reasoning Enhanced Multimodal Large Language Model](https://mlsanity.com/paper/2507.17303/) (2025)
- [Pathology-CoT: Learning Visual Chain-of-Thought Agent from Expert Whole Slide Image Diagnosis Behavior](https://mlsanity.com/paper/2510.04587/) (2025)
- [OctoMed: Data Recipes for State-of-the-Art Multimodal Medical Reasoning](https://mlsanity.com/paper/2511.23269/) (2025)
- [PRISM2: Unlocking Multi-Modal General Pathology AI with Clinical Dialogue](https://mlsanity.com/paper/2506.13063/) (2025)
- [A multimodal and temporal foundation model for virtual patient representations at healthcare system scale](https://mlsanity.com/paper/2604.18570/) (2026)
- [WSI-Agents: A Collaborative Multi-Agent System for Multi-Modal Whole Slide Image Analysis](https://mlsanity.com/paper/2507.14680/) (2025)
- [PathReasoner-R1: Instilling Structured Reasoning into Pathology Vision-Language Model via Knowledge-Guided Policy Optimization](https://mlsanity.com/paper/2601.21617/) (2026)
- [Bridging the Gap in Ophthalmic AI: MM-Retinal-Reason Dataset and OphthaReason Model toward Dynamic Multimodal Reasoning](https://mlsanity.com/paper/2508.16129/) (2025)
- [SurvAgent: Hierarchical CoT-Enhanced Case Banking and Dichotomy-Based Multi-Agent System for Multimodal Survival Prediction](https://mlsanity.com/paper/2511.16635/) (2025)
- [TeamPath: Building MultiModal Pathology Experts with Reasoning AI Copilots](https://mlsanity.com/paper/2511.17652/) (2025)
- [PathFound: An Agentic Multimodal Model Activating Evidence-seeking Pathological Diagnosis](https://mlsanity.com/paper/2512.23545/) (2025)
- [SAGE: Agentic Framework for Interpretable and Clinically Translatable Computational Pathology Biomarker Discovery](https://mlsanity.com/paper/2602.00953/) (2026)
- [When Does RL Help Medical VLMs? Disentangling Vision, SFT, and RL Gains](https://mlsanity.com/paper/2603.01301/) (2026)
- [Histopathology Multi-modal Embedding for Pathology Composed Retrieval](https://mlsanity.com/paper/2502.07221/) (2025)
- [PulseMind: A Multi-Modal Medical Model for Real-World Clinical Diagnosis](https://mlsanity.com/paper/2601.07344/) (2026)
- [MMNavAgent: Multi-Magnification WSI Navigation Agent for Clinically Consistent Whole-Slide Analysis](https://mlsanity.com/paper/2603.02079/) (2026)
- [NuNext: Reframing Nucleus Detection as Next-Point Detection](https://mlsanity.com/paper/2603.07098/) (2026)
- [Anatomy-R1: Enhancing Anatomy Reasoning in Multimodal Large Language Models via Anatomical Similarity Curriculum and Group Diversity Augmentation](https://mlsanity.com/paper/2512.19512/) (2025)
- [Hepato-LLaVA: An Expert MLLM with Sparse Topo-Pack Attention for Hepatocellular Pathology Analysis on Whole Slide Images](https://mlsanity.com/paper/2602.19424/) (2026)

## Abstract (arXiv)

Recent advances in Multimodal Large Language Models (MLLMs) and agent workflows have shown strong promise for computational pathology, yet reliable patch-level reasoning remains challenging. End-to-end pathology MLLMs often hallucinate morphological features, while recent agentic systems usually merge tool outputs and retrieved knowledge into a shared context, making decisions vulnerable to conflicting evidence and context contamination. We propose PathoSage, a three-stage framework that explicitly separates knowledge retrieval, evidence collection, and evidence adjudication for patch-level pathology multimodal reasoning. Its core component, Structured Evidence Deliberation, independently evaluates heterogeneous evidence from tools, performs conflict analysis, and generates the final judgment in a fresh context to reduce anchoring bias. We further introduce a training-free Beta-Bernoulli experience system with continuous credit assignment to model long-term tool reliability and construct similarity-weighted priors for future tool use. Experiments show that PathoSage effectively mitigates VQA hallucinations and classifier disagreement, outperforming strong pathology MLLM and agentic baselines. Our results highlight explicit evidence adjudication and reliability-aware tool modeling as key ingredients for robust pathology agents.