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

• URL: http://arxiv.org/abs/2602.07905v1
• Date: Sun, 08 Feb 2026 10:54:04 GMT
• Title: MedCoG: Maximizing LLM Inference Density in Medical Reasoning via Meta-Cognitive Regulation
• Abstract summary: Large Language Models (LLMs) have shown strong potential in complex medical reasoning yet face diminishing gains under inference scaling laws.<n>We propose MedCoG, a Medical Meta-Cognition Agent with Knowledge Graph, where the meta-cognitive assessments of task complexity, familiarity, and knowledge density dynamically regulate utilization of procedural, episodic, and factual knowledge.<n>Experiments demonstrate the effectiveness and efficiency of MedCoG on five hard sets of medical benchmarks, yielding 5.5x inference density.
• Score: 50.42633168081233
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large Language Models (LLMs) have shown strong potential in complex medical reasoning yet face diminishing gains under inference scaling laws. While existing studies augment LLMs with various knowledge types, it remains unclear how effectively the additional costs translate into accuracy. In this paper, we explore how meta-cognition of LLMs, i.e., their self-awareness of their own knowledge states, can regulate the reasoning process. Specifically, we propose MedCoG, a Medical Meta-Cognition Agent with Knowledge Graph, where the meta-cognitive assessments of task complexity, familiarity, and knowledge density dynamically regulate utilization of procedural, episodic, and factual knowledge. The LLM-centric on-demand reasoning aims to mitigate scaling laws by (1) reducing costs via avoiding indiscriminate scaling, (2) improving accuracy via filtering out distractive knowledge. To validate this, we empirically characterize the scaling curve and introduce inference density to quantify inference efficiency, defined as the ratio of theoretically effective cost to actual cost. Experiments demonstrate the effectiveness and efficiency of MedCoG on five hard sets of medical benchmarks, yielding 5.5x inference density. Furthermore, the Oracle study highlights the significant potential of meta-cognitive regulation.

Related papers

• Eliciting Medical Reasoning with Knowledge-enhanced Data Synthesis: A Semi-Supervised Reinforcement Learning Approach [62.0906177191353]
  Existing approaches distill chain-of-thought reasoning traces from large proprietary models via supervised fine-tuning, then conduct reinforcement learning (RL)<n>We propose MedSSR, a Medical Knowledge-enhanced data Synthesis and Semi-supervised Reinforcement learning framework.<n>Our framework first employs rare disease knowledge to synthesize distribution-controllable reasoning questions.<n>We then utilize the policy model itself to generate high-quality pseudo-labels. This enables a two-stage, intrinsic-to-extrinsic training paradigm: self-supervised RL on the pseudo-labeled data, followed by supervised RL on the human-annotated real data
  arXiv  Detail & Related papers  (2026-04-13T14:37:38Z)
• Scientific Knowledge-driven Decoding Constraints Improving the Reliability of LLMs [16.040771132830145]
  Large language models (LLMs) have shown strong knowledge reserves and task-solving capabilities, but still face the challenge of severe hallucination.<n>We propose textbfSciDC, an LLM generation method that integrate subject-specific knowledge with strong constraints.
  arXiv  Detail & Related papers  (2026-04-08T02:38:22Z)
• Assessing Automated Fact-Checking for Medical LLM Responses with Knowledge Graphs [12.287636586297756]
  The recent proliferation of large language models (LLMs) holds the potential to revolutionize healthcare.<n>This paper investigates the reliability and viability of using medical knowledge graphs (KGs) for the automated factuality evaluation of LLM-generated responses.<n>We introduce FAITH, a framework designed to probe the strengths and limitations of this KG-based approach.
  arXiv  Detail & Related papers  (2025-11-16T22:58:22Z)
• Structured Outputs Enable General-Purpose LLMs to be Medical Experts [50.02627258858336]
  Large language models (LLMs) often struggle with open-ended medical questions.<n>We propose a novel approach utilizing structured medical reasoning.<n>Our approach achieves the highest Factuality Score of 85.8, surpassing fine-tuned models.
  arXiv  Detail & Related papers  (2025-03-05T05:24:55Z)
• Fact or Guesswork? Evaluating Large Language Models' Medical Knowledge with Structured One-Hop Judgments [108.55277188617035]
  Large language models (LLMs) have been widely adopted in various downstream task domains, but their abilities to directly recall and apply factual medical knowledge remains under-explored.<n>We introduce the Medical Knowledge Judgment dataset (MKJ), a dataset derived from the Unified Medical Language System (UMLS), a comprehensive repository of standardized vocabularies and knowledge graphs.<n>Through a binary classification framework, MKJ evaluates LLMs' grasp of fundamental medical facts by having them assess the validity of concise, one-hop statements.
  arXiv  Detail & Related papers  (2025-02-20T05:27:51Z)
• GIVE: Structured Reasoning of Large Language Models with Knowledge Graph Inspired Veracity Extrapolation [108.2008975785364]
  Graph Inspired Veracity Extrapolation (GIVE) is a novel reasoning method that merges parametric and non-parametric memories to improve accurate reasoning with minimal external input.<n>GIVE guides the LLM agent to select the most pertinent expert data (observe), engage in query-specific divergent thinking (reflect), and then synthesize this information to produce the final output (speak)
  arXiv  Detail & Related papers  (2024-10-11T03:05:06Z)
• Reasoning-Enhanced Healthcare Predictions with Knowledge Graph Community Retrieval [61.70489848327436]
  KARE is a novel framework that integrates knowledge graph (KG) community-level retrieval with large language models (LLMs) reasoning.<n>Extensive experiments demonstrate that KARE outperforms leading models by up to 10.8-15.0% on MIMIC-III and 12.6-12.7% on MIMIC-IV for mortality and readmission predictions.
  arXiv  Detail & Related papers  (2024-10-06T18:46:28Z)
• Metacognitive Myopia in Large Language Models [0.0]
  Large Language Models (LLMs) exhibit potentially harmful biases that reinforce culturally inherent stereotypes, cloud moral judgments, or amplify positive evaluations of majority groups. We propose metacognitive myopia as a cognitive-ecological framework that can account for a conglomerate of established and emerging LLM biases. Our theoretical framework posits that a lack of the two components of metacognition, monitoring and control, causes five symptoms of metacognitive myopia in LLMs.
  arXiv  Detail & Related papers  (2024-08-10T14:43:57Z)
• HyKGE: A Hypothesis Knowledge Graph Enhanced Framework for Accurate and Reliable Medical LLMs Responses [20.635793525894872]
  We develop a Hypothesis Knowledge Graph Enhanced (HyKGE) framework to improve the accuracy and reliability of Large Language Models (LLMs) Specifically, HyKGE explores the zero-shot capability and the rich knowledge of LLMs with Hypothesis Outputs to extend feasible exploration directions in the KGs. Experiments on two Chinese medical multiple-choice question datasets and one Chinese open-domain medical Q&A dataset with two LLM turbos demonstrate the superiority of HyKGE in terms of accuracy and explainability.
  arXiv  Detail & Related papers  (2023-12-26T04:49:56Z)
• Self-Verification Improves Few-Shot Clinical Information Extraction [73.6905567014859]
  Large language models (LLMs) have shown the potential to accelerate clinical curation via few-shot in-context learning. They still struggle with issues regarding accuracy and interpretability, especially in mission-critical domains such as health. Here, we explore a general mitigation framework using self-verification, which leverages the LLM to provide provenance for its own extraction and check its own outputs.
  arXiv  Detail & Related papers  (2023-05-30T22:05:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.