EndoCogniAgent: Closed-Loop Agentic Reasoning with Self-Consistency Validation for Endoscopic Diagnosis

arXiv:2508.07292 · cs.AI, cs.CL, cs.CV · Submitted 2025-08-10 · Read on arXiv

cs.AI, cs.CL, cs.CV

Submitted: 2025-08-10

Updated: 2026-09-22

Comments: 21 pages, 24 figures, 9 tables. Revised version: adds a blinded clinician evaluation, paired statistical significance testing, and extended ablation and generalization analyses. Code and data are available at https://github.com/Tyyds-ai/EndoCogniAgent

Code: https://github.com/Tyyds-ai/EndoCogniAgent

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Consistency — 29× in this paper · explained in 3 episodes
• Benchmark — 18× in this paper · explained in 2 episodes
• Accuracy — 16× in this paper · explained in 1 episode
• Self-consistency — 15× in this paper · explained in 2 episodes
• Grounding — 14× in this paper · explained in 3 episodes
• Visual Grounding — 9× in this paper · explained in 2 episodes
• Verification — 7× in this paper · explained in 2 episodes
• Core — 6× in this paper · explained in 2 episodes
• Foundation Model — 6× in this paper · explained in 3 episodes
• Ablation — 5× in this paper · explained in 1 episode
• Hallucination — 5× in this paper · explained in 3 episodes
• Failure Modes — 4× in this paper · explained in 3 episodes
• Temporal consistency — 4× in this paper · explained in 2 episodes
• Agentic Framework — 3× in this paper · explained in 6 episodes
• Episodic Memory Module — 3× in this paper
• Iterative Refinement — 3× in this paper · explained in 3 episodes
• Agentic Reasoning — 2× in this paper · explained in 1 episode
• Clinical Acceptance Rate — 2× in this paper
• Decoupling — 2× in this paper · explained in 2 episodes
• Foundation Models — 2× in this paper · explained in 7 episodes
• LLM-as-a-Judge — 2× in this paper · explained in 3 episodes
• Perceptual Expert Toolset — 2× in this paper
• Accountability — 1× in this paper · explained in 2 episodes
• Action Space — 1× in this paper · explained in 1 episode
• Adaptability — 1× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Central Decision Unit — 1× in this paper
• Clustering — 1× in this paper · explained in 2 episodes
• Diagnostic Tools — 1× in this paper · explained in 2 episodes
• Effect of Internal Self-Consistency Validation — 1× in this paper
• Embeddings — 1× in this paper · explained in 2 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Generalizability — 1× in this paper · explained in 6 episodes
• Instruction Tuning — 1× in this paper · explained in 2 episodes
• Medical Report Generation — 1× in this paper
• Multi-Agent Framework — 1× in this paper · explained in 3 episodes
• Multimodal Reasoning — 1× in this paper · explained in 5 episodes
• Representation Learning — 1× in this paper · explained in 2 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Segmentation Masks — 1× in this paper · explained in 2 episodes
• Task Decomposition — 1× in this paper · explained in 2 episodes
• Trace — 1× in this paper · explained in 2 episodes
• Vision-language models — 1× in this paper · explained in 2 episodes

Sources

• How Do Medical MLLMs Fail? A Study on Visual Grounding in Medical Images
• MedMMV: A Controllable Multimodal Multi-Agent Framework for Reliable and Verifiable Clinical Reasoning
• AgentEHR: Advancing Autonomous Clinical Decision-Making via Retrospective Summarization
• Why Do Multi-Agent LLM Systems Fail?
• EndoDINO: A Foundation Model for GI Endoscopy
• Frontiers in Intelligent Colonoscopy
• MedHEval: Benchmarking Hallucinations and Mitigation Strategies in Medical Large Vision-Language Models
• MMedAgent: Learning to Use Medical Tools with Multi-modal Agent
• MedOrch: Medical Diagnosis with Tool-Augmented Reasoning Agents for Flexible Extensibility
• MedRAX: Medical Reasoning Agent for Chest X-ray
• CARE: Towards Clinical Accountability in Multi-Modal Medical Reasoning with an Evidence-Grounded Agentic Framework
• MedAgent-Pro: Towards Evidence-based Multi-modal Medical Diagnosis via Reasoning Agentic Workflow
• AgentClinic: a multimodal agent benchmark to evaluate AI in simulated clinical environments
• EndoBench: A Comprehensive Evaluation of Multi-Modal Large Language Models for Endoscopy Analysis
• Universal Medical Image Representation Learning with Compositional Decoders
• Polyp-Gen: Realistic and Diverse Polyp Image Generation for Endoscopic Dataset Expansion
• Self-Consistency Improves Chain of Thought Reasoning in Language Models
• MedMax: Mixed-Modal Instruction Tuning for Training Biomedical Assistants
• Yi: Open Foundation Models by 01.AI
• GPT-4o System Card

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection