MedFlowBench evaluates VLM agents on full radiology and pathology studies by requiring both task answers and verifiable evidence like key slices and regions of interest, revealing that answer-only scores overestimate performance.
hub Canonical reference
et al.: MedAgent-Pro: Towards Evidence-based Multi-modal Medical Diagnosis via Reasoning Agentic Workflow (Jul 2025)
Canonical reference. 100% of citing Pith papers cite this work as background.
19
Pith papers citing it
3
external citations · Pith
Background
100% of classified citations
abstract
In modern medicine, clinical diagnosis relies on the comprehensive analysis of primarily textual and visual data, drawing on medical expertise to ensure systematic and rigorous reasoning. Recent advances in large Vision-Language Models (VLMs) and agent-based methods hold great potential for medical diagnosis, thanks to the ability to effectively integrate multi-modal patient data. However, they often provide direct answers and draw empirical-driven conclusions without quantitative analysis, which reduces their reliability and clinical usability. We propose MedAgent-Pro, a new agentic reasoning paradigm that follows the diagnosis principle in modern medicine, to decouple the process into sequential components for step-by-step, evidence-based reasoning. Our MedAgent-Pro workflow presents a hierarchical diagnostic structure to mirror this principle, consisting of disease-level standardized plan generation and patient-level personalized step-by-step reasoning. To support disease-level planning, an RAG-based agent is designed to retrieve medical guidelines to ensure alignment with clinical standards. For patient-level reasoning, we propose to integrate professional tools such as visual models to enable quantitative assessments. Meanwhile, we propose to verify the reliability of each step to achieve evidence-based diagnosis, enforcing rigorous logical reasoning and a well-founded conclusion. Extensive experiments across a wide range of anatomical regions, imaging modalities, and diseases demonstrate the superiority of MedAgent-Pro to mainstream VLMs, agentic systems and state-of-the-art expert models. Ablation studies and human evaluation by clinical experts further validate its robustness and clinical relevance. Code is available at https://github.com/jinlab-imvr/MedAgent-Pro.
hub tools
citation-role summary
background 4
method 1
citation-polarity summary
polarities
background 5representative citing papers
DermAgent orchestrates seven vision-language tools in a Plan-Execute-Reflect loop with dual-modality retrieval from 413k cases and a critic module to outperform GPT-4o by 17.6% in zero-shot dermatological diagnosis accuracy.
OS-SPEAR is a new evaluation toolkit that tests 22 OS agents and identifies trade-offs between efficiency and safety or robustness.
A dual clinical-computational taxonomy for medical LLM reasoning plus a five-level 5k-sample benchmark showing specialists excel at diagnosis and general models at decision support/dialogue.
Proposes TopoAgent, an LLM agent framework that automatically selects and configures topological descriptors from persistent homology for medical image analysis without task-specific training.
CPAgents is a three-agent framework that generates interpretable composite phenotypes from cardiac imaging features and shows improved disease discrimination over baselines in a population cohort.
MedCTA is a new benchmark with 107 real-world tasks and process-aware metrics that shows frontier multimodal models remain brittle at autonomous tool selection, execution, and trajectory completion in clinical settings.
MedScribe reformulates CT radiology reporting as an agentic evidence-acquisition workflow using LLM-invoked diagnostic tools and pathology-aligned retrieval, yielding higher clinical accuracy and consistency than standard VLMs on CT-RATE and RadChestCT.
EndoGov uses specialist agents plus a governance layer with hard and soft rule paths to deliver guideline-compliant endometrial cancer risk stratification, reporting 0.943 accuracy and 0.93% logic-violation rate on TCGA-UCEC while outperforming neural baselines on CPTAC-UCEC.
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.
A four-phase multi-agent co-scientist tests natural-language hypotheses on cardiac and glioma MRI and labels outcomes Supported, Refuted, Underpowered, or Invalid with an executable evidence trail.
EchoAgent is a new agentic AI system that integrates visual observation, quantitative measurement, and expert knowledge reasoning to achieve reliable echocardiography interpretation with up to 80% accuracy on CAMUS and MIMIC-EchoQA datasets.
GLANCE introduces a bi-loop multi-agent framework with global-local coordination mechanisms that outperforms baselines by up to 33% on music-grounded nonlinear video editing tasks using a new MVEBench benchmark.
LLMs match or beat supervised BERT models on detecting whether a discharge note contains an actionable clinical task but trail on classifying the exact type of action, pointing to the need for datasets that explain why each span was labeled actionable.
Evo-MedAgent adds three evolving memory stores to LLM agents for chest X-ray diagnosis, raising MCQ accuracy from 0.68 to 0.79 on GPT-5-mini and 0.76 to 0.87 on Gemini-3 Flash without any training.
DEEPMED Search is an open-source platform with source-adaptive routing and introspective multi-agent verification for generating citation-backed medical research reports.
ReaORE is a progressive open relation extraction method that applies coarse-to-fine reasoning to improve generalization to unseen relations over clustering or direct LLM generation.
BCER agent improves end-to-end reliability of long-horizon MRI workflows via compilation, artifact binding, and bounded local recovery, outperforming reactive baselines especially on long-chain tasks across brain, prostate, and cardiac benchmarks.
A survey consolidating benchmarks, agent frameworks, real-world applications, and protocols for LLM-based autonomous agents into a proposed taxonomy with recommendations for future research.
citing papers explorer
-
MedOpenClaw and MedFlowBench: Auditing Medical Agents in Full-Study Workflows
MedFlowBench evaluates VLM agents on full radiology and pathology studies by requiring both task answers and verifiable evidence like key slices and regions of interest, revealing that answer-only scores overestimate performance.
-
DermAgent: A Self-Reflective Agentic System for Dermatological Image Analysis with Multi-Tool Reasoning and Traceable Decision-Making
DermAgent orchestrates seven vision-language tools in a Plan-Execute-Reflect loop with dual-modality retrieval from 413k cases and a critic module to outperform GPT-4o by 17.6% in zero-shot dermatological diagnosis accuracy.
-
OS-SPEAR: A Toolkit for the Safety, Performance,Efficiency, and Robustness Analysis of OS Agents
OS-SPEAR is a new evaluation toolkit that tests 22 OS agents and identifies trade-offs between efficiency and safety or robustness.
-
Aligning Clinical Needs and AI Capabilities: A Survey on LLMs for Medical Reasoning
A dual clinical-computational taxonomy for medical LLM reasoning plus a five-level 5k-sample benchmark showing specialists excel at diagnosis and general models at decision support/dialogue.
-
TopoAgent: An Agentic Framework for Automated Topology Learning in Medical Imaging
Proposes TopoAgent, an LLM agent framework that automatically selects and configures topological descriptors from persistent homology for medical image analysis without task-specific training.
-
CPAgents: Agentic Composite Phenotype Generation for Cardiac Disease Association
CPAgents is a three-agent framework that generates interpretable composite phenotypes from cardiac imaging features and shows improved disease discrimination over baselines in a population cohort.
-
MedCTA: A Benchmark for Clinical Tool Agents
MedCTA is a new benchmark with 107 real-world tasks and process-aware metrics that shows frontier multimodal models remain brittle at autonomous tool selection, execution, and trajectory completion in clinical settings.
-
MedScribe: Clinically Grounded CT Reporting through Agentic Workflows
MedScribe reformulates CT radiology reporting as an agentic evidence-acquisition workflow using LLM-invoked diagnostic tools and pathology-aligned retrieval, yielding higher clinical accuracy and consistency than standard VLMs on CT-RATE and RadChestCT.
-
EndoGov: A knowledge-governed multi-agent expert system for endometrial cancer risk stratification
EndoGov uses specialist agents plus a governance layer with hard and soft rule paths to deliver guideline-compliant endometrial cancer risk stratification, reporting 0.943 accuracy and 0.93% logic-violation rate on TCGA-UCEC while outperforming neural baselines on CPTAC-UCEC.
-
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.
-
VERITAS: A Multi-Agent Co-Scientist for Verifiable Image-Derived Hypothesis Testing
A four-phase multi-agent co-scientist tests natural-language hypotheses on cardiac and glioma MRI and labels outcomes Supported, Refuted, Underpowered, or Invalid with an executable evidence trail.
-
EchoAgent: Towards Reliable Echocardiography Interpretation with "Eyes","Hands" and "Minds"
EchoAgent is a new agentic AI system that integrates visual observation, quantitative measurement, and expert knowledge reasoning to achieve reliable echocardiography interpretation with up to 80% accuracy on CAMUS and MIMIC-EchoQA datasets.
-
GLANCE: A Global-Local Coordination Multi-Agent Framework for Music-Grounded Non-Linear Video Editing
GLANCE introduces a bi-loop multi-agent framework with global-local coordination mechanisms that outperforms baselines by up to 33% on music-grounded nonlinear video editing tasks using a new MVEBench benchmark.
-
Systematic Evaluation of Large Language Models for Post-Discharge Clinical Action Extraction
LLMs match or beat supervised BERT models on detecting whether a discharge note contains an actionable clinical task but trail on classifying the exact type of action, pointing to the need for datasets that explain why each span was labeled actionable.
-
Evo-MedAgent: Beyond One-Shot Diagnosis with Agents That Remember, Reflect, and Improve
Evo-MedAgent adds three evolving memory stores to LLM agents for chest X-ray diagnosis, raising MCQ accuracy from 0.68 to 0.79 on GPT-5-mini and 0.76 to 0.87 on Gemini-3 Flash without any training.
-
DEEPMED Search: An Open-Source Agentic Platform for Medical Deep Research with Introspective Verification
DEEPMED Search is an open-source platform with source-adaptive routing and introspective multi-agent verification for generating citation-backed medical research reports.
-
ReaORE: Reasoning-Guided Progressive Open Relation Extraction Empowered by Large Reasoning Models
ReaORE is a progressive open relation extraction method that applies coarse-to-fine reasoning to improve generalization to unseen relations over clustering or direct LLM generation.
-
BCER Agent: Reliable Long-Horizon MRI Workflow Execution via Compilation, Artifact Binding, and Bounded Local Recovery
BCER agent improves end-to-end reliability of long-horizon MRI workflows via compilation, artifact binding, and bounded local recovery, outperforming reactive baselines especially on long-chain tasks across brain, prostate, and cardiac benchmarks.
-
From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review
A survey consolidating benchmarks, agent frameworks, real-world applications, and protocols for LLM-based autonomous agents into a proposed taxonomy with recommendations for future research.