Agentic LLMs autonomously execute complex neuro-radiological workflows like glioma segmentation and multi-timepoint response assessment by directing off-the-shelf tools, without any model training.
A co-evolving agentic ai system for medical imaging analysis
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
years
2026 7representative citing papers
Systematic factorial analysis shows optimized LLM input configurations for pathology WSIs raise GPT-5 performance from 15.1% to 39.5% on TCGA cancer classification and 38.1% to 62.9% on GTEx organ classification, with generalization to held-out data.
PathNavigate introduces a scan-search-readout routine with surprise-guided low-mag scanning and shared slide memory to improve training-free WSI-VQA accuracy and efficiency.
NeuroClaw is a domain-specialized multi-agent framework with NeuroBench benchmark that improves executability and reproducibility for multimodal neuroimaging research.
An RL-trained tool-using agent improves chest CT report generation over CT-Chat by 5.8 macro-F1 points, 24.7 robustness points, and 37% faithfulness while exposing intermediate tool traces.
PathoSage is a three-stage framework using Structured Evidence Deliberation and a Beta-Bernoulli experience system to improve patch-level pathology reasoning by mitigating hallucinations and tool conflicts.
NeuroAgent uses a hierarchical LLM agent framework with Generate-Execute-Validate loops to automate neuroimaging preprocessing, reaching 84.8% end-to-end correctness and 0.9518 AUC for Alzheimer's classification on 1470 ADNI subjects using four modalities.
citing papers explorer
-
Agentic Large Language Models for Training-Free Neuro-Radiological Image Analysis
Agentic LLMs autonomously execute complex neuro-radiological workflows like glioma segmentation and multi-timepoint response assessment by directing off-the-shelf tools, without any model training.
-
How Seemingly Inconsequential Design Choices Dictate Performance of LLMs in Pathology
Systematic factorial analysis shows optimized LLM input configurations for pathology WSIs raise GPT-5 performance from 15.1% to 39.5% on TCGA cancer classification and 38.1% to 62.9% on GTEx organ classification, with generalization to held-out data.
-
PathNavigate: A Training-Free Pathology Agent with Surprise-Guided Scan and Shared Slide Memory for Whole-Slide Image VQA
PathNavigate introduces a scan-search-readout routine with surprise-guided low-mag scanning and shared slide memory to improve training-free WSI-VQA accuracy and efficiency.
-
NeuroClaw Technical Report
NeuroClaw is a domain-specialized multi-agent framework with NeuroBench benchmark that improves executability and reproducibility for multimodal neuroimaging research.
-
RadAgent: A tool-using AI agent for stepwise interpretation of chest computed tomography
An RL-trained tool-using agent improves chest CT report generation over CT-Chat by 5.8 macro-F1 points, 24.7 robustness points, and 37% faithfulness while exposing intermediate tool traces.
-
PathoSage: Towards Multi-Source Evidence Adjudication in Pathology via Experience-Aware Agentic Workflow
PathoSage is a three-stage framework using Structured Evidence Deliberation and a Beta-Bernoulli experience system to improve patch-level pathology reasoning by mitigating hallucinations and tool conflicts.
-
NeuroAgent: LLM Agents for Multimodal Neuroimaging Analysis and Research
NeuroAgent uses a hierarchical LLM agent framework with Generate-Execute-Validate loops to automate neuroimaging preprocessing, reaching 84.8% end-to-end correctness and 0.9518 AUC for Alzheimer's classification on 1470 ADNI subjects using four modalities.