Constructing and Evaluating Clinical Reasoning Trajectories for Medical Agent

arXiv:2609.05090 · cs.AI · Submitted 2026-09-04 · Read on arXiv

cs.AI

Submitted: 2026-09-04

Updated: 2026-10-15

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

Terminology

• Hallucination — 2× in this paper · explained in 3 episodes

Sources

• MedReflect: Teaching Medical LLMs to Self-Improve via Reflective Correction
• Med-REFL: Medical Reasoning Enhancement via Self-Corrected Fine-grained Reflection
• Can Large Language Models Self-Correct in Medical Question Answering? An Exploratory Study
• Benchmarking Multi-turn Medical Diagnosis: Hold, Lure, and Self-Correction
• A Survey of Large Language Models in Medicine: Progress, Application, and Challenge
• CliniCARE-Bench: Clinical Calibrated Audit of Medical Reasoning in EHR

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
• Agents' Last Exam
• 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