Research map / Vision-language and multimodal / Multimodal LLMs
Toward Interpretable Analysis of Whole-slide Pathology Images via Large Language Model-based Agentic Reasoning
Jingyun Chen, Linghan Cai, Zhikang Wang, Yi Huang, Songhan Jiang, Shenjin Huang, Hongpeng Wang, Yongbing Zhang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add Multi-Step Reasoning in the Executor (ablation) | PathAgent-offline · SlideBench-VQA (BCNB) | overall accuracy: 41.62 -> 44.97 | Improved |
| add Navigator for RoI retrieval (ablation) | PathAgent-offline · SlideBench-VQA (BCNB) | overall accuracy: 41.62 -> 50.68 | Improved |
| add both Multi-Step Reasoning and Navigator (ablation) | PathAgent-offline · SlideBench-VQA (BCNB) | overall accuracy: 41.62 -> 55.72 | Improved |
| add Navigator for RoI retrieval (ablation) | PathAgent-offline · SlideBench-VQA (BCNB) | average iterations: 1.83 -> 1.32 | Improved |
| add Multi-Step Reasoning in the Executor (ablation) | PathAgent-offline · SlideBench-VQA (BCNB) Molecular Subtype | accuracy: 20.19 -> 26.28 | Improved |
| add Navigator for RoI retrieval (ablation) | PathAgent-offline · SlideBench-VQA (BCNB) Receptor Status | accuracy: 52.38 -> 58.27 | Improved |
| replace Qwen3-4B Executor with Qwen3-32B (Patho-R1-7B Perceptor) (ablation) | PathAgent-offline · WSI-VQA | accuracy: 56.32 -> 57.29 | Improved |
| replace Quilt-LLaVA Perceptor with Patho-R1-7B (Qwen3-4B Executor) (ablation) | PathAgent-offline · WSI-VQA | accuracy: 52.95 -> 56.32 | Improved |
| replace Qwen3-4B Executor with Qwen3-235B-A22B (online) | PathAgent · SlideBench-VQA (BCNB) | overall accuracy: 55.72 -> 59.31 | Improved |
| replace Qwen3-4B Executor with Qwen3-235B-A22B (online) | PathAgent · PathMMU (overall) | accuracy: 53.19 -> 72.54 | Improved |
| replace Qwen3-4B Executor with Qwen3-235B-A22B (online) | PathAgent · SlideBench-VQA (BCNB) HER2 Expression | accuracy: 25.34 -> 27.26 | Mixed |
| increase initial patch sampling ratio beyond 10% (ablation) | PathAgent · WSI-VQA | overall accuracy | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- WSI-LLaVA — WSI-LLaVA: A Multimodal Large Language Model for Whole Slide Image (ICCV 2025) · better on 4 of 4 shared results
- SlideChat — SlideChat: A Large Vision-Language Assistant for Whole-Slide Pathology Image Understanding (CVPR 2025) · better on 3 of 3 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- CPathAgent: An Agent-based Foundation Model for Interpretable High-Resolution Pathology Image Analysis Mimicking Pathologists' Diagnostic Logic (NeurIPS 2025 · similarity 0.94)
- MLLM-HWSI: A Multimodal Large Language Model for Hierarchical Whole Slide Image Understanding (CVPR 2026 · similarity 0.89)
- PathVQ: Reforming Computational Pathology Foundation Model for Whole Slide Image Analysis via Vector Quantization (NeurIPS 2025 · similarity 0.89)
- SlideChat: A Large Vision-Language Assistant for Whole-Slide Pathology Image Understanding (CVPR 2025 · similarity 0.88)
- PathView-Bench: Can Multimodal Large Language Models Achieve Fine-grained Multiscale Understanding of Pathology Images? (NeurIPS 2026 · similarity 0.88)
- Patho-R1: A Multimodal Reinforcement Learning-Based Pathology Expert Reasoner (AAAI 2026 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
