REVIEW 31 cited by
MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoning
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
Large language models (LLMs), despite their remarkable progress across various general domains, encounter significant barriers in medicine and healthcare. This field faces unique challenges such as domain-specific terminologies and reasoning over specialized knowledge. To address these issues, we propose MedAgents, a novel multi-disciplinary collaboration framework for the medical domain. MedAgents leverages LLM-based agents in a role-playing setting that participate in a collaborative multi-round discussion, thereby enhancing LLM proficiency and reasoning capabilities. This training-free framework encompasses five critical steps: gathering domain experts, proposing individual analyses, summarising these analyses into a report, iterating over discussions until a consensus is reached, and ultimately making a decision. Our work focuses on the zero-shot setting, which is applicable in real-world scenarios. Experimental results on nine datasets (MedQA, MedMCQA, PubMedQA, and six subtasks from MMLU) establish that our proposed MedAgents framework excels at mining and harnessing the medical expertise within LLMs, as well as extending its reasoning abilities. Our code can be found at https://github.com/gersteinlab/MedAgents.
Forward citations
Cited by 31 Pith papers
-
eSkinHealth: A Multimodal Dataset for Neglected Tropical Skin Diseases
eSkinHealth is a new West African skin-disease dataset with 5,623 images, 47 conditions, and multimodal annotations including masks, captions, and clinical concepts for AI dermatology research.
-
Aligning Clinical Needs and AI Capabilities: A Survey on LLMs for Medical Reasoning
A dual clinical-computational taxonomy for medical LLM reasoning plus a five-level 5k-sample benchmark showing specialists excel at diagnosis and general models at decision support/dialogue.
-
Optimal-Agent-Selection: State-Aware Routing Framework for Efficient Multi-Agent Collaboration
A state-aware contrastive router that selects the most relevant agent at each step improves multi-agent LLM accuracy by up to 23.8% while using a fraction of the tokens of fixed-pipeline baselines.
-
LLM-Driven Collaborative Model for Untangling Commits via Explicit and Implicit Dependency Reasoning
ColaUntangle, a three-agent LLM consultation framework with PDG-derived explicit and implicit contexts, reports 44% (C#) and 82% (Java) Accuracy_c gains over prior commit untangling baselines.
-
WSI-Agents: A Collaborative Multi-Agent System for Multi-Modal Whole Slide Image Analysis
A route, verify, and summarize agent system uses existing pathology models and a knowledge base to select the best whole-slide image answer.
-
DynamiCare: A Dynamic Multi-Agent Framework for Interactive and Open-Ended Medical Decision-Making
DynamiCare is a multi-agent LLM framework that runs multi-round diagnostic dialogues with a dynamically adjusted specialist team, evaluated on a new 500-patient benchmark built from MIMIC-III.
-
Abstract Counterfactuals for Language Model Agents
Counterfactuals for LM agents computed over a high-level abstraction of the action, instead of its tokens, preserve the observed action's meaning across counterfactual contexts far more often than token-level counterfactuals.
-
Efficient Leave-one-out Approximation in LLM Multi-agent Debate Based on Introspection
IntrospecLOO uses a single extra prompting round to approximate leave-one-out contribution in LLM debates, but the empirical evidence is weak and one case study contradicts the method's claimed behavior.
-
Empowering LLMs in Task-Oriented Dialogues: A Domain-Independent Multi-Agent Framework and Fine-Tuning Strategy
A three-agent domain-independent framework with distribution-balanced DPO training reaches Combined 106.3 on MultiWOZ 2.2 with Qwen2.5-7B, the best score among the compared baselines.
-
YuLan-OneSim: Towards the Next Generation of Social Simulator with Large Language Models
YuLan-OneSim combines natural-language scenario generation, 50 prebuilt simulation scenarios, feedback-driven agent fine-tuning, 100,000-agent scale, and an automated AI social researcher into one social simulation platform.
-
Exploring the Inquiry-Diagnosis Relationship with Advanced Patient Simulators
A dialogue-strategy-trained patient simulator improves realism in AI medical consultations and shows that inquiry quality and diagnostic skill jointly limit diagnostic accuracy.
-
Ultrasound-QBench: Can LLMs Aid in Quality Assessment of Ultrasound Imaging?
A new benchmark evaluates eight multimodal language models on ultrasound image quality assessment, finding near-chance classification accuracy on raw outputs and a proposed Softmax plus Clustering strategy that boosts...
-
MMFactory: A Universal Solution Search Engine for Vision-Language Tasks
MMFactory automatically generates and benchmarks a pool of reusable programmatic vision-language solutions from a few examples, letting users pick one that fits their accuracy and speed constraints.
-
SurgBox: Agent-Driven Operating Room Sandbox with Surgery Copilot
An LLM-based surgical sandbox with a role-playing Surgery Copilot achieves 88% route and plan accuracy on 128 pituitary adenoma surgery records, but its claimed cognitive-load benefit is unmeasured.
-
VILA-M3: Enhancing Vision-Language Models with Medical Expert Knowledge
A four-stage training recipe plus on-demand expert-model feedback lets a small open-source VLM beat much larger medical VLMs on several VQA, classification, and report generation benchmarks.
-
A Large Language Model-based Multi-Agent Framework for Analog Circuits' Sizing Relationships Extraction
An LLM multi-agent framework extracts sizing relationships from analog circuit papers to prune the optimizer's search space, reporting 2.32 to 26.6 times faster sizing and higher pass rates on three circuits.
-
Silence is Not Consensus: Disrupting Agreement Bias in Multi-Agent LLMs via Catfish Agent for Clinical Decision Making
A "catfish" agent that injects structured dissent into multi-agent LLM teams improves clinical question-answering accuracy by reducing premature consensus.
-
TAGS: A Test-Time Generalist-Specialist Framework with Retrieval-Augmented Reasoning and Verification
Without any parameter updates, a retrieval-augmented generalist-specialist agent pair with consistency-based verification raises accuracy on 862 hard medical QA questions for GPT-4o, DeepSeek-R1, and Qwen2.5-7B.
-
KABB: Knowledge-Aware Bayesian Bandits for Dynamic Expert Coordination in Multi-Agent Systems
A knowledge-aware Bayesian bandit that selects specialist LLM experts per task is reported to beat Mixture-of-Agents on AlpacaEval 2.0 and MT-Bench while using fewer models.
-
Balancing Knowledge Delivery and Emotional Comfort in Healthcare Conversational Systems
Fine-tuning a 1B medical chatbot on LLM-rewritten emotional dialogues improves its emotion scores with only small changes in n-gram overlap with the original medical responses.
-
AI Agent Behavioral Science
AI agents should be studied as behavioral entities shaped by context and interaction, not only as trained models.
-
MRGAgents: A Multi-Agent Framework for Improved Medical Report Generation with Med-LVLMs
MRGAgents fine-tunes one agent per chest X-ray disease and merges their sentences, reporting higher text metrics, but its evaluation uses oracle disease sentences and is not end-to-end.
-
Toward Inclusive Educational AI: Auditing Frontier LLMs through a Multiplexity Lens
Multi-agent prompting makes LLM answers mention a roughly equal share of eight cultures, but the measurement and the multi-agent design make the reported 98% balance largely self-fulfilling.
-
LLM-MedQA: Enhancing Medical Question Answering through Case Studies in Large Language Models
A multi-agent Llama-3.1-70B system generates supportive clinical cases before voting and reports 77.2% accuracy on a 300-question MedQA sample, about 7% relative above zero-shot baselines.
-
Enhancing LLMs for Impression Generation in Radiology Reports through a Multi-Agent System
A multi-agent system combining report retrieval, impression generation, and consistency review improves automated radiology impression writing over a single LLM, though the built-in reviewer misses some error types.
-
From Individual to Society: A Survey on Social Simulation Driven by Large Language Model-based Agents
A structured survey that categorizes LLM-based social simulation into individual, scenario, and society simulation, with associated methods, benchmarks, and observed trends.
-
Towards Next-Generation Medical Agent: How o1 is Reshaping Decision-Making in Medical Scenarios
Replacing GPT-4 with o1-preview as the backbone of CoD, MedAgents, and AgentClinic improves mean diagnostic accuracy on several medical benchmarks, with higher runtime and mixed results on simple agent roles.
-
From Voting to Agent Collaboration: Answer-Type-Aware LLM Pipelines for BioASQ 14b
A question-type-specific LLM ensemble and multi-agent pipeline achieved competitive results on BioASQ 14b Task B, including first place in the factoid subtask of Batch 4.
-
A Multimodal Multi-Agent Framework for Radiology Report Generation
A five-agent retrieval-augmented pipeline for radiology report generation outperforms a single LLaVA-Med baseline on IU X-ray, but the comparison is limited to one weak baseline with no ablations and no statistical tests.
-
KIMAs: A Configurable Knowledge Integrated Multi-Agent System
A configurable multi-agent RAG system that rewrites queries from conversation context, routes to knowledge sources by embedding centroids, and generates answers with separately produced citations, shown in three indus...
-
Advanced Machine Learning Techniques for Social Support Detection on Social Media
A model-scan on an existing social support dataset whose claimed macro F1 improvements are contradicted by its own tables.
Discussion (0). Continue with ORCID to comment.