# PathoArgus: Advancing Evidence-Grounded Long-Context Visual Reasoning across Gigapixel Whole-Slide and Multi-Slide Case Contexts

arXiv: https://arxiv.org/abs/2608.17607 · HTML: https://mlsanity.com/paper/2608.17607/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning.
- Builds on 22 of its 32 references that are in the map.
- First posted on arXiv 18 Aug 2026.

## Placed in

- LLM reasoning / [Clinical and biomedical applications](https://mlsanity.com/lr/clinical-and-biomedical-applications/)

## Builds on (most cited first, 22 of 22)

- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models](https://mlsanity.com/paper/2504.10479/) (2025)
- [LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day](https://mlsanity.com/paper/2306.00890/) (2023)
- [GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning](https://mlsanity.com/paper/2507.01006/) (2025)
- [MedGemma Technical Report](https://mlsanity.com/paper/2507.05201/) (2025)
- [Lingshu: A Generalist Foundation Model for Unified Multimodal Medical Understanding and Reasoning](https://mlsanity.com/paper/2506.07044/) (2025)
- [HuatuoGPT-Vision, Towards Injecting Medical Visual Knowledge into Multimodal LLMs at Scale](https://mlsanity.com/paper/2406.19280/) (2024)
- [MedVLM-R1: Incentivizing Medical Reasoning Capability of Vision-Language Models (VLMs) via Reinforcement Learning](https://mlsanity.com/paper/2502.19634/) (2025)
- [Quilt-LLaVA: Visual Instruction Tuning by Extracting Localized Narratives from Open-Source Histopathology Videos](https://mlsanity.com/paper/2312.04746/) (2023)
- [MIRAGE: The Illusion of Visual Understanding](https://mlsanity.com/paper/2603.21687/) (2026)
- [MedGemma 1.5 Technical Report](https://mlsanity.com/paper/2604.05081/) (2026)
- [Patho-R1: A Multimodal Reinforcement Learning-Based Pathology Expert Reasoner](https://mlsanity.com/paper/2505.11404/) (2025)
- [Vision-DeepResearch: Incentivizing DeepResearch Capability in Multimodal Large Language Models](https://mlsanity.com/paper/2601.22060/) (2026)
- [WSI-VQA: Interpreting Whole Slide Images by Generative Visual Question Answering](https://mlsanity.com/paper/2407.05603/) (2024)
- [PathAgent: Toward Interpretable Analysis of Whole-slide Pathology Images via Large Language Model-based Agentic Reasoning](https://mlsanity.com/paper/2511.17052/) (2025)
- [Navigating Gigapixel Pathology Images with Large Multimodal Models](https://mlsanity.com/paper/2511.19652/) (2025)
- [PathNavigate: A Training-Free Pathology Agent with Surprise-Guided Scan and Shared Slide Memory for Whole-Slide Image VQA](https://mlsanity.com/paper/2605.23559/) (2026)
- [EviPathBench: Benchmarking Evidence Acquisition and Reasoning in Vision-Language Models for Whole-Slide Pathology](https://mlsanity.com/paper/2607.19261/) (2026)
- [PathView-Bench: Can Multimodal Large Language Models Achieve Fine-grained Multiscale Understanding of Pathology Images?](https://mlsanity.com/paper/2607.28318/) (2026)
- [Do Pathology Vision-Language Models Truly See Pathology?](https://mlsanity.com/paper/2607.21065/) (2026)
- [CTIS-QA: Clinical Template-Informed Slide-level Question Answering for Pathology](https://mlsanity.com/paper/2601.01769/) (2026)

## Abstract (arXiv)

Whole-slide pathology reasoning requires models to integrate gigapixel-scale visual evidence across complete case-linked slides, yet current question-answering benchmarks primarily measure final answer accuracy--a metric vulnerable to linguistic priors and benchmark regularities, and insufficient to establish that predictions are grounded in the supplied tissue. We introduce PathoArgus-Bench, a benchmark and evaluation protocol that explicitly tests the full evidence chain: availability, accessibility, use, and responsiveness. PathoArgus-Bench comprises 22,078 four-choice questions from 4,913 patients across 15 TCGA projects, covering six pathology capabilities across three levels of evidence demand, and operates under a fixed reader budget that retains only a small fraction of the gigapixel context. To further isolate evidence-grounded reasoning, we contribute ESG (Evidence State Quartets), a controlled set of 483 quartets where the question text is fixed while the target WSI set is moved, replaced, or removed, requiring consistent predictions across all states. Evaluating 20 general-purpose, medical, and pathology-specific systems reveals a stark gap: while GPT-5.6 achieves 57.09% overall accuracy and 57.04% on ESG, it correctly completes only 19 of 483 quartets (3.93% QExact), exposing that row-level accuracy does not translate into reliable evidence grounding. We also introduce PathoArgus, a fixed-budget reader that allocates context via question relevance and spatial coverage, attaining 50.39% overall accuracy yet only 1.86% QExact--demonstrating that improved context access alone does not ensure consistent evidence-based prediction. Our benchmark and diagnostics establish that acquiring useful whole-slide context is necessary but far from sufficient, and call for a shift from answer-centric to evidence-grounded evaluation in computational pathology.