AI Paper Atlas

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

ECCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Multimodal LLM benchmarks · 0 citations (OpenAlex)

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 changedWhereMeasuredEffect
add Multi-Step Reasoning in the Executor (ablation)PathAgent-offline · SlideBench-VQA (BCNB)overall accuracy: 41.62 -> 44.97Improved
add Navigator for RoI retrieval (ablation)PathAgent-offline · SlideBench-VQA (BCNB)overall accuracy: 41.62 -> 50.68Improved
add both Multi-Step Reasoning and Navigator (ablation)PathAgent-offline · SlideBench-VQA (BCNB)overall accuracy: 41.62 -> 55.72Improved
add Navigator for RoI retrieval (ablation)PathAgent-offline · SlideBench-VQA (BCNB)average iterations: 1.83 -> 1.32Improved
add Multi-Step Reasoning in the Executor (ablation)PathAgent-offline · SlideBench-VQA (BCNB) Molecular Subtypeaccuracy: 20.19 -> 26.28Improved
add Navigator for RoI retrieval (ablation)PathAgent-offline · SlideBench-VQA (BCNB) Receptor Statusaccuracy: 52.38 -> 58.27Improved
replace Qwen3-4B Executor with Qwen3-32B (Patho-R1-7B Perceptor) (ablation)PathAgent-offline · WSI-VQAaccuracy: 56.32 -> 57.29Improved
replace Quilt-LLaVA Perceptor with Patho-R1-7B (Qwen3-4B Executor) (ablation)PathAgent-offline · WSI-VQAaccuracy: 52.95 -> 56.32Improved
replace Qwen3-4B Executor with Qwen3-235B-A22B (online)PathAgent · SlideBench-VQA (BCNB)overall accuracy: 55.72 -> 59.31Improved
replace Qwen3-4B Executor with Qwen3-235B-A22B (online)PathAgent · PathMMU (overall)accuracy: 53.19 -> 72.54Improved
replace Qwen3-4B Executor with Qwen3-235B-A22B (online)PathAgent · SlideBench-VQA (BCNB) HER2 Expressionaccuracy: 25.34 -> 27.26Mixed
increase initial patch sampling ratio beyond 10% (ablation)PathAgent · WSI-VQAoverall accuracyHurt

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.

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy