Learning When to Trust Medical Knowledge: Regression-Safe Routing for Clinical Reasoning

cs.AI

Submitted: 2026-10-14

Updated: 2026-10-14

Comments: 19 pages, 8 figures, including supplementary material

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

Sources

• RAGRouter-Bench: A Dataset and Benchmark for Adaptive RAG Routing
• MedReason: Eliciting Factual Medical Reasoning Steps in LLMs via Knowledge Graphs
• From Conflict to Consensus: Boosting Medical Reasoning via Multi-Round Agentic RAG
• Certifiably Robust RAG against Retrieval Corruption
• Corrective Retrieval Augmented Generation

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