AI Paper Atlas

Research map / Large language models / Retrieval and knowledge

MedCoG: Maximizing LLM Inference Density in Medical Reasoning via Meta-Cognitive Regulation

Yu Zhao, Hao Guan, Yongcheng Jing, Ying Zhang, Dacheng Tao

ICML 2026 · Large language models › Retrieval and knowledge · approach: Knowledge-augmented question answering · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add meta-cognition regulation (on-demand strategy selection) instead of always using all three knowledge types (ablation)MedCoG · Hard subsets averageaccuracy: 33.2 -> 37.5Improved
add meta-cognition regulation instead of always using all knowledge types (ablation)MedCoG · IIE per 1k samplesIIE: 0.181 -> 0.438Improved
add KG retrieval to structured CoT (ablation)SCoT (GPT-4o) · MedQA-Hardaccuracy: 41.0 -> 37.0Hurt
add KG retrieval to structured CoT (ablation)SCoT (GPT-4o) · MedQA-Fullaccuracy: 89.55 -> 87.43Hurt
add episodic memory to structured CoT (ablation)SCoT (GPT-4o) · MedQA-Hardaccuracy: 41.0 -> 42.0No clear effect
add both KG and memory to structured CoT (ablation)SCoT (GPT-4o) · MedQA-Hardaccuracy: 41.0 -> 50.0Improved
add memory to KG-augmented SCoT (ablation)SCoT+KG (GPT-4o) · MedQA-Hardaccuracy: 37.0 -> 50.0Improved
replace always-on strategy with oracle strategy selectionMedCoG · MedQA-Hardaccuracy: 50.0 -> 67.0Improved
add per-backbone threshold calibration (ablation)MedCoG monitor GPT-4o-mini · MedQA-Hardaccuracy: 40 -> 50Improved
add per-backbone threshold calibration (ablation)MedCoG monitor o3-mini · MedQA-Hardaccuracy: 44 -> 49Improved
add per-backbone threshold calibration (ablation)MedCoG monitor Gemini-2.0-Flash · MedQA-Hardaccuracy: 48 -> 52Improved
add per-backbone threshold calibration (ablation)MedCoG monitor GPT-4o · MedQA-Hardaccuracy: 52 -> 52No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy