The paper introduces PRISM, a framework that separates belief estimation from action selection to handle irregular state transitions in online medical consultations. By maintaining a posterior belief over consultation states, PRISM improves clinical decision accuracy by 22.40 percentage points and response quality by 5.51 BERTScore_F1 points compared to leading LLMs and clinical agents. Ablation studies confirm that oracle state information further enhances response quality across baselines.
arXiv:2609.24480v1 Announce Type: cross Abstract: Deploying Large Language Models (LLMs) in healthcare requires robust performance across two complementary dimensions - diagnostic reasoning: the conv...
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.
arXiv:2607. 18999v1 Announce Type: cross Abstract: Multi-turn medical consultation agents must decide what to ask, adapt to patient responses, and determine when the collected evidence is sufficient.
ConsultMind is an uncertainty‑aware framework that automates diagnostic consultation by updating disorder posteriors after each patient response and using posterior uncertainty to guide inquiry and diagnosis. It builds on AutoDisym, a pipeline that constructs a Disorder–Symptom Bayesian Network (DSBN) from diagnostic knowledge and clinical narratives. Across psychiatry, respiratory medicine, fever clinics, and public datasets, AutoDisym produces high‑quality DSBNs and ConsultMind improves diagnostic accuracy and explanation quality, achieving up to 22.15‑point gains in Top‑1 accuracy and 37.89‑point gains in Top‑3 accuracy.
arXiv:2610.17426v1 Announce Type: cross Abstract: Clinical decision-making is a sequential process of information collection, clinical inference, and forecasting under partial observability, often wi...
arXiv:2509. 02594v3 Announce Type: replace-cross Abstract: Evaluating large language models (LLMs) on their ability to generate high-quality, accurate, situationally aware answers to clinical questions requires going beyond conventional benchmarks to assess how these systems behave in complex, high-stakes clinical scenarios.
GPAgentBench-2K is a new benchmark that evaluates large language model agents in primary‑care clinical decision‑making using a constrained Markov Decision Process (CMDP). It is built from expert‑validated records of real GP encounters and includes six foundational clinical actions, a workflow prior, and safety‑informed abstention as an outcome. Testing 16 state‑of‑the‑art LLMs shows that performance drops as the action space grows and that even the best models violate safety constraints in more than half of high‑risk cases, highlighting a gap between clinical quality and safety.
The paper introduces a de‑identified corpus of 33 in‑person cognitive assessment conversations, comprising 8,250 utterances annotated for three speaker roles and 56 dialogue acts. The authors benchmark large language models on fine‑grained dialogue‑act classification and next‑patient‑utterance generation, finding that instruction tuning and reasoning‑aware fine‑tuning improve performance but that models still struggle with closely related dialogue acts. The corpus and benchmark are presented as tools to measure interaction structure in cognitive assessments and to support future research on conversational markers, clinician education, and validated simulated patients.
arXiv:2606. 08938v1 Announce Type: cross Abstract: Clinical diagnosis requires flexible use of multiple reasoning paradigms under incomplete patient information.
arXiv:2512.08029v4 Announce Type: replace Abstract: Clinical decision-making in oncology requires forecasting how disease evolves under treatment, yet most AI systems remain static predictors that ca...
The paper introduces the first benchmark for evaluating confidence estimation in large language models during multi‑turn medical consultations, combining three types of medical data and an information sufficiency gradient to capture how confidence and correctness evolve as evidence accumulates. Experiments with 27 methods reveal that token‑level and consistency‑level confidence approaches are limited by medical data, and that medical reasoning must be judged on both diagnostic accuracy and information completeness. Building on these findings, the authors propose MedConf, a retrieval‑augmented, linguistically grounded self‑assessment framework that aligns patient information with supporting, missing, and contradictory relations, producing interpretable confidence estimates that outperform existing methods across multiple datasets and LLMs.
arXiv:2608. 03731v1 Announce Type: new Abstract: Patient-facing medical LLMs and agents increasingly answer symptom questions before clinician contact, where the key safety question is what action the user should take next.