CDEG: Learning Decision-Critical Evidence for Long-Horizon Diagnostic Agents
cs.AI
Submitted: 2026-08-24
Updated: 2026-10-14
Comments: 9 pages, 5 figures
Code: https://github.com/abhinand5/MedEmbed
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Benchmarking Multi-turn Medical Diagnosis: Hold, Lure, and Self-Correction
- MedExAgent: Training LLM Agents to Ask, Examine, and Diagnose in Noisy Clinical Environments
- GSEM: Graph-based Self-Evolving Memory for Experience Augmented Clinical Reasoning
- MedAction: Towards Active Multi-turn Clinical Diagnostic LLMs
- Joint Optimization of Reasoning and Dual-Memory for Self-Learning Diagnostic Agent
- Strong Reasoning Isn't Enough: Evaluating Evidence Elicitation in Interactive Diagnosis
- Evolving Interactive Diagnostic Agents in a Virtual Clinical Environment
- Emulating Clinician Cognition via Self-Evolving Deep Clinical Research
- MeDxAgent: Multi-Agent Consultation for Interactive Medical Diagnosis
- Evo-MedAgent: Beyond One-Shot Diagnosis with Agents That Remember, Reflect, and Improve
- Improving Clinical Diagnosis with Counterfactual Multi-Agent Reasoning
- Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models
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