{"total":154,"rows":[{"id":"2506.09038","title":"AbstentionBench: Reasoning LLMs Fail on Unanswerable Questions","created":"2025-06-10","cited_by_count":145,"area":"lr"},{"id":"2506.22405","title":"Sequential Diagnosis with Language Models","created":"2025-06-27","cited_by_count":60,"area":null},{"id":"2603.11245","title":"Mind the Sim2Real Gap in User Simulation for Agentic Tasks","created":"2026-03-11","cited_by_count":54,"area":"agents"},{"id":"2508.18847","title":"ConfTuner: Training Large Language Models to Express Their Confidence Verbally","created":"2025-08-26","cited_by_count":39,"area":null},{"id":"2502.13069","title":"Ambig-SWE: Interactive Agents to Overcome Underspecificity in Software Engineering","created":"2025-02-18","cited_by_count":38,"area":"agents"},{"id":"2506.00711","title":"QoQ-Med: Building Multimodal Clinical Foundation Models with Domain-Aware GRPO Training","created":"2025-05-31","cited_by_count":38,"area":"lr"},{"id":"2504.07114","title":"ChatBench: From Static Benchmarks to Human-AI Evaluation","created":"2025-03-22","cited_by_count":34,"area":null},{"id":"2505.17818","title":"PatientSim: A Persona-Driven Simulator for Realistic Doctor-Patient Interactions","created":"2025-05-23","cited_by_count":32,"area":null},{"id":"2409.19487","title":"HealthQ: Unveiling Questioning Capabilities of LLM Chains in Healthcare Conversations","created":"2024-09-28","cited_by_count":31,"area":null},{"id":"2502.04381","title":"Limitations of Large Language Models in Clinical Problem-Solving Arising from Inflexible Reasoning","created":"2025-02-05","cited_by_count":31,"area":"lr"},{"id":"2502.19175","title":"MEDDxAgent: A Unified Modular Agent Framework for Explainable Automatic Differential Diagnosis","created":"2025-02-26","cited_by_count":23,"area":"agents"},{"id":"2506.04405","title":"MedAgentGym: A Scalable Agentic Training Environment for Code-Centric Reasoning in Biomedical Data Science","created":"2025-06-04","cited_by_count":23,"area":"lr"},{"id":"2506.08295","title":"From Passive to Active Reasoning: Can Large Language Models Ask the Right Questions under Incomplete Information?","created":"2025-06-09","cited_by_count":23,"area":"lr"},{"id":"2504.13861","title":"3MDBench: Medical Multimodal Multi-agent Dialogue Benchmark","created":"2025-03-26","cited_by_count":16,"area":"mllm"},{"id":"2504.11373","title":"Cancer-Myth: Evaluating Large Language Models on Patient Questions with False Presuppositions","created":"2025-04-15","cited_by_count":15,"area":null},{"id":"2506.13474","title":"Language Agents for Hypothesis-driven Clinical Decision Making with Reinforcement Learning","created":"2025-06-16","cited_by_count":15,"area":"agents"},{"id":"2606.28733","title":"Agentic Abstention: Do Agents Know When to Stop Instead of Act?","created":"2026-06-27","cited_by_count":15,"area":"agents"},{"id":"2604.17073","title":"Abstain-R1: Calibrated Abstention and Post-Refusal Clarification via Verifiable RL","created":"2026-04-18","cited_by_count":14,"area":"lr"},{"id":"2508.13514","title":"ProMed: Shapley Information Gain Guided Reinforcement Learning for Proactive Medical LLMs","created":"2025-08-19","cited_by_count":13,"area":null},{"id":"2601.03023","title":"MedDialogRubrics: A Comprehensive Benchmark and Evaluation Framework for Multi-turn Medical Consultations in Large Language Models","created":"2026-01-06","cited_by_count":12,"area":null},{"id":"2509.16584","title":"From Scores to Steps: Diagnosing and Improving LLM Performance in Evidence-Based Medical Calculations","created":"2025-09-20","cited_by_count":11,"area":null},{"id":"2601.05503","title":"Over-Searching in Search-Augmented Large Language Models","created":"2026-01-09","cited_by_count":11,"area":null},{"id":"2503.17509","title":"Follow-up Question Generation For Enhanced Patient-Provider Conversations","created":"2025-03-21","cited_by_count":10,"area":null},{"id":"2509.24958","title":"The Dialogue That Heals: A Comprehensive Evaluation of Doctor Agents' Inquiry Capability","created":"2025-09-29","cited_by_count":10,"area":"agents"},{"id":"2511.21322","title":"TALES: A Taxonomy and Analysis of Cultural Representations in LLM-generated Stories","created":"2025-11-26","cited_by_count":10,"area":null},{"id":"2602.06286","title":"When Agents Say One Thing and Do Another: Validating Elicited Beliefs from LLMs","created":"2026-02-06","cited_by_count":10,"area":"agents"},{"id":"2510.10390","title":"RefusalBench: Generative Evaluation of Selective Refusal in Grounded Language Models","created":"2025-10-12","cited_by_count":9,"area":"rag"},{"id":"2501.09484","title":"Exploring the Inquiry-Diagnosis Relationship with Advanced Patient Simulators","created":"2025-01-16","cited_by_count":8,"area":null},{"id":"2601.22964","title":"EvoClinician: A Self-Evolving Agent for Multi-Turn Medical Diagnosis via Test-Time Evolutionary Learning","created":"2026-01-30","cited_by_count":8,"area":null},{"id":"2602.24188","title":"MT-PingEval: Evaluating Multi-Turn Collaboration with Private Information Games","created":"2026-02-27","cited_by_count":8,"area":null},{"id":"2603.02216","title":"ATPO: Adaptive Tree Policy Optimization for Multi-Turn Medical Dialogue","created":"2026-02-10","cited_by_count":8,"area":null},{"id":"2507.03279","title":"Conformal Information Pursuit for Interactively Guiding Large Language Models","created":"2025-07-04","cited_by_count":7,"area":null},{"id":"2509.24816","title":"KnowGuard: Knowledge-Driven Abstention for Multi-Round Clinical Reasoning","created":"2025-09-29","cited_by_count":7,"area":"lr"},{"id":"2512.24181","title":"MedKGI: Iterative Differential Diagnosis with Medical Knowledge Graphs and Information-Guided Inquiring","created":"2025-12-30","cited_by_count":7,"area":null},{"id":"2412.11388","title":"INTERACT: Enabling Interactive, Question-Driven Learning in Large Language Models","created":"2024-12-16","cited_by_count":6,"area":null},{"id":"2501.15056","title":"Feedback-Aware Monte Carlo Tree Search for Efficient Information Seeking in Goal-Oriented Conversations","created":"2025-01-25","cited_by_count":6,"area":null},{"id":"2506.17336","title":"PPMI: Privacy-Preserving LLM Interaction with Socratic Chain-of-Thought Reasoning and Homomorphically Encrypted Vector Databases","created":"2025-06-19","cited_by_count":6,"area":"lr"},{"id":"2510.25744","title":"Completion $\\neq$ Collaboration: Scaling Collaborative Effort with Agents","created":"2025-10-29","cited_by_count":6,"area":null},{"id":"2511.20490","title":"MTBBench: A Multimodal Sequential Clinical Decision-Making Benchmark in Oncology","created":"2025-11-25","cited_by_count":6,"area":"lr"},{"id":"2601.21257","title":"MoCo: A One-Stop Shop for Model Collaboration Research","created":"2026-01-29","cited_by_count":6,"area":null},{"id":"2504.00016","title":"Medical Reasoning in LLMs: An In-Depth Analysis of DeepSeek R1","created":"2025-03-27","cited_by_count":5,"area":"lr"},{"id":"2504.16273","title":"From Promising Capability to Pervasive Bias: Assessing Large Language Models for Emergency Department Triage","created":"2025-04-22","cited_by_count":5,"area":null},{"id":"2505.24040","title":"MedPAIR: Measuring Physicians and AI Relevance Alignment in Medical Question Answering","created":"2025-05-29","cited_by_count":5,"area":null},{"id":"2506.21532","title":"\"What's Up, Doc?\": Analyzing How Users Seek Health Information in Large-Scale Conversational AI Datasets","created":"2025-06-26","cited_by_count":5,"area":null},{"id":"2507.10445","title":"Referential ambiguity and clarification requests: comparing human and LLM behaviour","created":"2025-07-14","cited_by_count":5,"area":null},{"id":"2508.11894","title":"QuarkMed Medical Foundation Model Technical Report","created":"2025-08-16","cited_by_count":5,"area":null},{"id":"2511.11500","title":"Honesty over Accuracy: Trustworthy Language Models through Reinforced Hesitation","created":"2025-11-14","cited_by_count":5,"area":null},{"id":"2605.06915","title":"LLMs are not (consistently) Bayesian: Quantifying internal (in)consistencies of LLMs' probabilistic beliefs","created":"2026-05-07","cited_by_count":5,"area":null},{"id":"2501.02026","title":"Recursive Decomposition of Logical Thoughts: Framework for Superior Reasoning and Knowledge Propagation in Large Language Models","created":"2025-01-03","cited_by_count":4,"area":"lr"},{"id":"2501.17860","title":"Dialogue is Better Than Monologue: Instructing Medical LLMs via Strategical Conversations","created":"2025-01-29","cited_by_count":4,"area":null},{"id":"2504.11571","title":"GraphicBench: A Planning Benchmark for Graphic Design with Language Agents","created":"2025-04-15","cited_by_count":4,"area":"agents"},{"id":"2604.04325","title":"Benchmarking Multi-turn Medical Diagnosis: Hold, Lure, and Self-Correction","created":"2026-04-06","cited_by_count":4,"area":null},{"id":"2604.06846","title":"MedDialBench: Benchmarking LLM Diagnostic Robustness under Parametric Adversarial Patient Behaviors","created":"2026-04-08","cited_by_count":4,"area":null},{"id":"2606.03416","title":"MeDxAgent: Multi-Agent Consultation for Interactive Medical Diagnosis","created":"2026-06-02","cited_by_count":4,"area":"agents"},{"id":"2503.16463","title":"Improving Interactive Diagnostic Ability of a Large Language Model Agent Through Clinical Experience Learning","created":"2025-02-24","cited_by_count":3,"area":"agents"},{"id":"2506.00308","title":"MythTriage: Scalable Detection of Opioid Use Disorder Myths on a Video-Sharing Platform","created":"2025-05-30","cited_by_count":3,"area":null},{"id":"2509.14998","title":"A Knowledge-driven Adaptive Collaboration of LLMs for Enhancing Medical Decision-making","created":"2025-09-18","cited_by_count":3,"area":null},{"id":"2509.17044","title":"AgriDoctor: A Multimodal Intelligent Assistant for Agriculture","created":"2025-09-21","cited_by_count":3,"area":null},{"id":"2601.19773","title":"Strong Reasoning Isn't Enough: Evaluating Evidence Elicitation in Interactive Diagnosis","created":"2026-01-27","cited_by_count":3,"area":null},{"id":"2602.15012","title":"Cold-Start Personalization via Training-Free Priors from Structured World Models","created":"2026-02-16","cited_by_count":3,"area":"wm"},{"id":"2603.05909","title":"InfoGatherer: Principled Information Seeking via Evidence Retrieval and Strategic Questioning","created":"2026-03-06","cited_by_count":3,"area":null},{"id":"2605.07305","title":"MedAction: Towards Active Multi-turn Clinical Diagnostic LLMs","created":"2026-05-08","cited_by_count":3,"area":null},{"id":"2605.12446","title":"ORCE: Order-Aware Alignment of Verbalized Confidence in Large Language Models","created":"2026-05-12","cited_by_count":3,"area":null},{"id":"2606.11702","title":"MedCTA: A Benchmark for Clinical Tool Agents","created":"2026-06-10","cited_by_count":3,"area":null},{"id":"2608.05583","title":"The Judgment-Consequence Gap: LLM Moral Reasoning in Healthcare Decisions","created":"2026-08-06","cited_by_count":3,"area":null},{"id":"2502.17715","title":"Bridging Information Gaps with Comprehensive Answers: Improving the Diversity and Informativeness of Follow-Up Questions","created":"2025-02-24","cited_by_count":2,"area":"distill"},{"id":"2504.15918","title":"Ask2Loc: Learning to Locate Instructional Visual Answers by Asking Questions","created":"2025-04-22","cited_by_count":2,"area":null},{"id":"2505.18630","title":"DDO: Dual-Decision Optimization for LLM-Based Medical Consultation via Multi-Agent Collaboration","created":"2025-05-24","cited_by_count":2,"area":"lr"},{"id":"2505.19667","title":"LeCoDe: A Benchmark Dataset for Interactive Legal Consultation Dialogue Evaluation","created":"2025-05-26","cited_by_count":2,"area":null},{"id":"2506.00079","title":"Who Gets the Kidney? Human-AI Alignment, Indecision, and Moral Values","created":"2025-05-30","cited_by_count":2,"area":"alignment"},{"id":"2507.02616","title":"DynamiCare: A Dynamic Multi-Agent Framework for Interactive and Open-Ended Medical Decision-Making","created":"2025-07-03","cited_by_count":2,"area":"agents"},{"id":"2509.11078","title":"Patient-Zero: Scaling Synthetic Patient Agents to Real-World Distributions without Real Patient Data","created":"2025-09-14","cited_by_count":2,"area":"agents"},{"id":"2601.17916","title":"UniPACT: A Multimodal Framework for Prognostic Question Answering on Raw ECG and Structured EHR","created":"2026-01-25","cited_by_count":2,"area":null},{"id":"2602.07905","title":"MedCoG: Maximizing LLM Inference Density in Medical Reasoning via Meta-Cognitive Regulation","created":"2026-02-08","cited_by_count":2,"area":"lr"},{"id":"2602.14564","title":"Assessing Large Language Models for Medical QA: Zero-Shot and LLM-as-a-Judge Evaluation","created":"2026-02-16","cited_by_count":2,"area":null},{"id":"2603.01252","title":"Linking Knowledge to Care: Knowledge Graph-Augmented Medical Follow-Up Question Generation","created":"2026-03-01","cited_by_count":2,"area":null},{"id":"2604.05116","title":"Uncertainty-Guided Latent Diagnostic Trajectory Learning for Sequential Clinical Diagnosis","created":"2026-04-06","cited_by_count":2,"area":"agents"},{"id":"2604.07549","title":"EMSDialog: Synthetic Multi-person Emergency Medical Service Dialogue Generation from Electronic Patient Care Reports via Multi-LLM Agents","created":"2026-04-08","cited_by_count":2,"area":null},{"id":"2604.08788","title":"MedConceal: A Benchmark for Clinical Hidden-Concern Reasoning Under Partial Observability","created":"2026-04-09","cited_by_count":2,"area":"lr"},{"id":"2605.28070","title":"Bridging the Detection-to-Abstention Gap in Reasoning Models under Insufficient Information","created":"2026-05-27","cited_by_count":2,"area":"lr"},{"id":"2605.29473","title":"Inform, Coach, Relate, Listen: Auditing LLM Caregiving Support Roles","created":"2026-05-28","cited_by_count":2,"area":null},{"id":"2605.30637","title":"EHRBench: An Automated and Reliable EHR-based Benchmark for Clinical Decision Making with LLMs","created":"2026-05-28","cited_by_count":2,"area":null},{"id":"2607.03426","title":"Amortising Bayesian Experimental Design for Sequential Information Gathering in LLMs","created":"2026-07-03","cited_by_count":2,"area":"lr"},{"id":"2502.15027","title":"InterFeedback: Unveiling Interactive Intelligence of Large Multimodal Models via Human Feedback","created":"2025-02-20","cited_by_count":1,"area":"mllm"},{"id":"2505.21757","title":"BehaviorSFT: Behavioral Token Conditioning for Clinical Agents Across the Proactivity Spectrum","created":"2025-05-27","cited_by_count":1,"area":"agents"},{"id":"2509.19593","title":"GuessingGame: Measuring the Informativeness of Open-Ended Questions in Large Language Models","created":"2025-09-23","cited_by_count":1,"area":null},{"id":"2510.10461","title":"MedCoAct: Confidence-Aware Multi-Agent Collaboration for Complete Clinical Decision","created":"2025-10-12","cited_by_count":1,"area":"agents"},{"id":"2510.18659","title":"Sherlock Your Queries: Learning to Ask the Right Questions for Dialogue-Based Retrieval","created":"2025-10-21","cited_by_count":1,"area":null},{"id":"2510.20001","title":"Beyond MedQA: Towards Real-world Clinical Decision Making in the Era of LLMs","created":"2025-10-22","cited_by_count":1,"area":null},{"id":"2511.11883","title":"ClinStructor: AI-Powered Structuring of Unstructured Clinical Texts","created":"2025-11-14","cited_by_count":1,"area":null},{"id":"2511.22130","title":"Benchmarking In-context Experiential Learning Through Repeated Product Recommendations","created":"2025-11-27","cited_by_count":1,"area":null},{"id":"2601.10945","title":"PatientVLM Meets DocVLM: Pre-Consultation Dialogue Between Vision-Language Models for Efficient Diagnosis","created":"2026-01-16","cited_by_count":1,"area":"mllm"},{"id":"2601.21551","title":"Note2Chat: Improving LLMs for Multi-Turn Clinical History Taking Using Medical Notes","created":"2026-01-29","cited_by_count":1,"area":null},{"id":"2601.22648","title":"UCPO: Uncertainty-Aware Policy Optimization","created":"2026-01-30","cited_by_count":1,"area":null},{"id":"2602.01708","title":"Game of Thought: Robust Information Seeking with Large Language Models Using Game Theory","created":"2026-02-02","cited_by_count":1,"area":"lr"},{"id":"2604.05397","title":"Confidence Should Be Calibrated More Than One Turn Deep","created":"2026-04-07","cited_by_count":1,"area":null},{"id":"2606.18668","title":"EARS: Explanatory Abstention for Reliable Sub-Agent Modeling in Large-scale Multi-Agent Systems","created":"2026-06-17","cited_by_count":1,"area":"agents"},{"id":"2607.08257","title":"MentalHospital: A Virtual Environment for Evaluating Psychiatric Clinical Encounters","created":"2026-07-09","cited_by_count":1,"area":null},{"id":"2607.13036","title":"Ask Before You Diagnose: Safe-Psych, a Sequential Evaluation Benchmark for LLMs in Psychiatry","created":"2026-05-06","cited_by_count":1,"area":null},{"id":"2608.01361","title":"High-Stakes Decisions with Language Models: Insights from Emergency Triage","created":"2026-08-02","cited_by_count":1,"area":null}],"next_cursor":"100"}