One Panel Does Not Fit All: Case-Adaptive Multi-Agent Deliberation for Clinical Prediction

• URL: http://arxiv.org/abs/2604.00085v1
• Date: Tue, 31 Mar 2026 18:00:34 GMT
• Title: One Panel Does Not Fit All: Case-Adaptive Multi-Agent Deliberation for Clinical Prediction
• Abstract summary: We propose CAMP (Case-Adaptive Multi-agent Panel), where an attending-physician agent dynamically assembles a specialist panel tailored to each case's diagnostic uncertainty.<n>A hybrid router directs each diagnosis through strong consensus, fallback to the attending physician's judgment, or evidence-based arbitration that weighs argument quality over vote counts.<n> CAMP consistently outperforms strong baselines while consuming fewer tokens than most competing multi-agent methods, with voting records and arbitration traces offering transparent decision audits.
• Score: 10.760929240872564
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models applied to clinical prediction exhibit case-level heterogeneity: simple cases yield consistent outputs, while complex cases produce divergent predictions under minor prompt changes. Existing single-agent strategies sample from one role-conditioned distribution, and multi-agent frameworks use fixed roles with flat majority voting, discarding the diagnostic signal in disagreement. We propose CAMP (Case-Adaptive Multi-agent Panel), where an attending-physician agent dynamically assembles a specialist panel tailored to each case's diagnostic uncertainty. Each specialist evaluates candidates via three-valued voting (KEEP/REFUSE/NEUTRAL), enabling principled abstention outside one's expertise. A hybrid router directs each diagnosis through strong consensus, fallback to the attending physician's judgment, or evidence-based arbitration that weighs argument quality over vote counts. On diagnostic prediction and brief hospital course generation from MIMIC-IV across four LLM backbones, CAMP consistently outperforms strong baselines while consuming fewer tokens than most competing multi-agent methods, with voting records and arbitration traces offering transparent decision audits.

Related papers

• Concept-Grounded Reasoning with Prompt-Driven Localization for Interpretable Structured Report Generation [66.62662330558906]
  CORAL is a multimodal framework that integrates spatial grounding and concept-level supervision into a unified reasoning process.<n>CORAL employs a prompt-driven medical segmentation model to localize lesions and predicts multi-class clinical attributes through a Concept Bottleneck module.<n>Experiments on BUS-CoT and IU X-ray datasets demonstrate consistent improvements in diagnostic accuracy, concept consistency, and report quality over strong general-purpose and medical MLLMs.
  arXiv  Detail & Related papers  (2026-09-14T10:21:23Z)
• MedRoundsQA: A Persona and Difficulty Aware Evaluation for Multi-Turn Medical Consultations [37.085079820080644]
  Medical benchmarks are dominated by single-turn, multiple-choice clinical cases that poorly reflect real consultations.<n>We introduce MedRoundsQA, a multi-turn diagnostic benchmark derived from 1,387 board-exam cases across 17 specialties.
  arXiv  Detail & Related papers  (2026-09-11T13:41:53Z)
• Social Chain of Thought: A Multi-Agent Architecture Grounded in Medical Differential Diagnosis Methodology [21.116270925609477]
  Medical diagnostic reasoning is a high-impact use case for LLMs.<n>OpenAI reports that more than 5% of ChatGPT messages globally are healthcare-related.<n>We introduce Social Chain of Thought (SCoT),a multi-round pipeline for medical differential diagnosis.
  arXiv  Detail & Related papers  (2026-08-11T20:38:03Z)
• PACT: Learning Diverse Diagnostic Strategies via Privileged Synthesis and Branch Consensus [31.605826007992167]
  We propose textbfPACT (Periodic Anchor Consensus Training), a framework that couples supervised multi-paradigm dialogue synthesis with consensus-based Branch training.<n>At the data level, textbfDPS (Doctor-Patient-Supervisor) uses complete electronic medical records (EMRs) for quality control while keeping the doctor agent restricted to patient-visible information.<n>Experiments show that PACT achieves state-of-the-art performance among compared proprietary, medical-specialized, and task-adapted baselines on diagnostic outcome and consultation-process metrics.
  arXiv  Detail & Related papers  (2026-06-08T02:34:12Z)
• UltrasoundAgents: Hierarchical Multi-Agent Evidence-Chain Reasoning for Breast Ultrasound Diagnosis [14.027321451902734]
  We propose a hierarchical multi-agent framework, termed UltrasoundAgents.<n>A main agent localizes the lesion in the full image and triggers a crop-and-zoom operation.<n>A sub-agent analyzes the local view and predicts four clinically relevant attributes, namely echogenicity pattern, calcification, boundary type, and edge morphology.<n>The main agent then integrates these structured attributes to perform evidence-based reasoning and output the BI-RADS category and the malignancy prediction, while producing reviewable intermediate evidence.
  arXiv  Detail & Related papers  (2026-03-11T15:03:52Z)
• Do Mixed-Vendor Multi-Agent LLMs Improve Clinical Diagnosis? [6.913124180936944]
  Multi-agent large language model (LLM) systems have emerged as a promising approach for clinical diagnosis.<n>We investigate the impact of vendor diversity by comparing Single-LLM, Single-Vendor, and Mixed-Vendor Multi-Agent Conversation (MAC) frameworks.
  arXiv  Detail & Related papers  (2026-02-14T18:42:58Z)
• MMedExpert-R1: Strengthening Multimodal Medical Reasoning via Domain-Specific Adaptation and Clinical Guideline Reinforcement [63.82954136824963]
  Medical Vision-Language Models excel at perception tasks with complex clinical reasoning required in real-world scenarios.<n>We propose a novel reasoning MedVLM that addresses these challenges through domain-specific adaptation and guideline reinforcement.
  arXiv  Detail & Related papers  (2026-01-16T02:32:07Z)
• Learning from Disagreement: A Group Decision Simulation Framework for Robust Medical Image Segmentation [19.530108661940258]
  Medical image segmentation annotation suffers from inter-rater variability (IRV)<n>Standard approaches that simply average expert labels are flawed, as they discard the valuable clinical uncertainty revealed in disagreements.<n>We introduce a fundamentally new approach with our group decision simulation framework, which works by mimicking the collaborative decision-making process of a clinical panel.
  arXiv  Detail & Related papers  (2025-10-12T05:57:48Z)
• MedMMV: A Controllable Multimodal Multi-Agent Framework for Reliable and Verifiable Clinical Reasoning [35.97057940590796]
  We introduce MedMMV, a controllable multi-agent framework for reliable and verifiable clinical reasoning.<n>On six medical benchmarks, MedMMV improves accuracy by up to 12.7% and, more critically, demonstrates superior reliability.
  arXiv  Detail & Related papers  (2025-09-29T05:51:25Z)
• Radiomic fingerprints for knee MR images assessment [39.11295870085984]
  Existing radiomic approaches use a fixed set of radiomic features, selected at the population level and applied uniformly to all patients.<n>While interpretable, these signatures are often too constrained to represent individual pathological variations.<n>We propose a novel radiomic fingerprint framework, in which a radiomic feature set (the fingerprint) is dynamically constructed for each patient, selected by a DL model.<n>Unlike the existing radiomic signatures, our fingerprints are derived on a per-patient basis by predicting the feature relevance in a large radiomic feature pool, and selecting only those that are predictive of clinical conditions for individual patients.
  arXiv  Detail & Related papers  (2025-06-25T10:39:22Z)
• Silence is Not Consensus: Disrupting Agreement Bias in Multi-Agent LLMs via Catfish Agent for Clinical Decision Making [80.94208848596215]
  We present a new concept called Catfish Agent, a role-specialized LLM designed to inject structured dissent and counter silent agreement.<n>Inspired by the catfish effect'' in organizational psychology, the Catfish Agent is designed to challenge emerging consensus to stimulate deeper reasoning.
  arXiv  Detail & Related papers  (2025-05-27T17:59:50Z)
• XAI for In-hospital Mortality Prediction via Multimodal ICU Data [57.73357047856416]
  We propose an efficient, explainable AI solution for predicting in-hospital mortality via multimodal ICU data. We employ multimodal learning in our framework, which can receive heterogeneous inputs from clinical data and make decisions. Our framework can be easily transferred to other clinical tasks, which facilitates the discovery of crucial factors in healthcare research.
  arXiv  Detail & Related papers  (2023-12-29T14:28:04Z)
• Ambiguous Medical Image Segmentation using Diffusion Models [60.378180265885945]
  We introduce a single diffusion model-based approach that produces multiple plausible outputs by learning a distribution over group insights. Our proposed model generates a distribution of segmentation masks by leveraging the inherent sampling process of diffusion. Comprehensive results show that our proposed approach outperforms existing state-of-the-art ambiguous segmentation networks.
  arXiv  Detail & Related papers  (2023-04-10T17:58:22Z)
• Semi-Supervised Variational Reasoning for Medical Dialogue Generation [70.838542865384]
  Two key characteristics are relevant for medical dialogue generation: patient states and physician actions. We propose an end-to-end variational reasoning approach to medical dialogue generation. A physician policy network composed of an action-classifier and two reasoning detectors is proposed for augmented reasoning ability.
  arXiv  Detail & Related papers  (2021-05-13T04:14:35Z)

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.