arXiv AI

Hx2Dx: From Anamnesis to Diagnosis - A Multimodal Arena for Conversational Clinical Reasoning in LLMs

The paper introduces Hx2Dx ARENA, an interactive benchmark of 1,000 clinical cases from the New England Journal of Medicine that simulates the full diagnostic process from initial presentation through history taking, physical examination, and diagnostic workup. It evaluates open- and closed‑source large language models (LLMs) in this setting, finding that performance drops compared to static evaluations where the entire case is provided upfront. The study highlights that LLMs can reason accurately once relevant data are available, but struggle with hypothesis‑driven information gathering—specifically, deciding what questions to ask to build a complete clinical picture.

arXiv AI
Aug 18

DiagnosisArena: Benchmarking Diagnostic Reasoning for Large Language Models

arXiv:2505. 14107v5 Announce Type: replace-cross Abstract: The emergence of groundbreaking large language models capable of performing complex reasoning tasks holds significant promise for addressing various scientific challenges, including those arising in complex clinical scenarios.

By Yakun Zhu, Zhongzhen Huang, Linjie Mu, Yutong Huang, Wei Nie, Jiaji Liu, Shaoting Zhang, Pengfei Liu, Xiaofan Zhang
arXiv Computation and Language
Sep 1

MedConceal: A Benchmark for Clinical Hidden-Concern Reasoning Under Partial Observability

MedConceal is a new benchmark for evaluating medical dialogue systems on hidden‑concern reasoning under partial observability. It features 300 curated cases and 600 clinician‑LLM interactions, using an interactive patient simulator that hides latent concerns and tracks their revelation and resolution through theory‑grounded communication signals. The benchmark assesses both confirmation (surfacing hidden concerns) and intervention (addressing the primary concern), revealing that current models excel on different metrics while human clinicians still outperform them on intervention success.

By Yikun Han, Joey Chan, Jingyuan Chen, Mengting Ai, Simo Du, Yue Guo
arXiv AI
Aug 3

Reasoning in Real World Clinical Care: Why Large Language Models Are Not Yet Safe for Autonomous Clinical Decision Support

arXiv:2607. 28677v1 Announce Type: new Abstract: LLM now pass medical licensing examinations and, in curated cases, can rival physicians at diagnostic reasoning.

By Shayndhan Sivanathan, Shravan Nageswaran, Mehdi Zadem, Ryaan Sultan, Nicolas von Mallinckrodt, Max Solovyev, Alexey Matyushkin, Sumon Sadhu, Gabriele C DeLuca, Sanjeeva Jeyaretna, James Hillis, Manoj Ramachandran, Prakash Jayakumar
arXiv AI
Aug 26

EviDx: Evidence-Aware Active Diagnosis with Scaffolded LLM Agents

EviDx is a new framework for evidence-aware active diagnosis that pairs patient-specific diagnostic environments with a clinical scaffold and an observer-guided runtime harness. The framework constructs interactive environments from raw clinical cases, organizes role-specialized agents and evidence tools, and regulates diagnostic termination by tracking uncertainty and evidence coverage. Experiments demonstrate that EviDx improves diagnostic performance and process stability while revealing model-dependent capability boundaries.

By Lihang Zeng, Shaoting Zhang, Xiaofan Zhang
arXiv AI
Sep 7

A Structured Debate-Mixture-of-Agents Framework for Complex Clinical Diagnostic Decision Support

The paper introduces Debate-Mixture-of-Agents (DMoA), a multi‑agent framework that structures role‑based interactions to mimic iterative diagnostic reasoning in clinical settings. Evaluated on 297 rare disease cases and 1,719 challenging cases, DMoA outperformed a GPT‑4o baseline, improving most likely diagnosis accuracy by 10.21 percentage points and safety rate by 11.36 percentage points. Ablation studies and further analyses revealed that these gains stem from the structured workflow rather than merely adding more models or longer outputs, and that performance benefits are influenced by the chosen structure, base model strength, and token budget.

By Chang Xia, Leilei Ouyang, Huimin Wang, Yong Zhao, Kang Li
arXiv AI
Jun 17

AIPatient Arena: EHR-grounded evaluation of large language models in end-to-end clinical consultation workflows

arXiv:2606. 17474v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly considered for use in clinical consultation tasks, yet most medical evaluations remain static, single-turn, or narrowly outcome-based, limiting their ability to reflect the sequential, uncertain, and interactive nature of real-world care.

By Jiahui Niu, Huizi Yu, Wenkong Wang, Guangxin Dai, Jingxian He, Xiang Li, Zhiying Liang, Xinxin Lin, Kent CY So, Bryan YP Yan, Yun Kwok Wing, Yanqiu Xing, Xin Ma, Lizhou Fan
arXiv Computation and Language
Aug 27

MTDiag: A Multi-Turn Diagnostic Dataset Towards Clinically Meaningful LLM Evaluation

MTDiag is a newly released multi-turn diagnostic dialogue dataset designed to evaluate large language models (LLMs) in clinically meaningful ways. It is built from DDXPlus, MIMIC-IV, and AJCR case reports, covering both common emergency department presentations and rare conditions, and normalizes cases into a canonical schema using UMLS concept identifiers and ICD-10 codes. The dataset includes a UserLM‑8B utterance‑generation pipeline and physician‑validated natural‑language utterances, and introduces clinical knowledge‑grounded metrics that go beyond simple diagnostic accuracy for multi‑turn differential diagnosis tasks.

By Pia Chouayfati, Alexander M. Fichtl, Miriam Ansch\"utz, George Doumat, Georg Groh