{"total":109,"rows":[{"id":"2503.09567","title":"Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models","created":"2025-03-12","cited_by_count":384,"area":"lr"},{"id":"2502.17419","title":"From System 1 to System 2: A Survey of Reasoning Large Language Models","created":"2025-02-24","cited_by_count":320,"area":"lr"},{"id":"2506.07044","title":"Lingshu: A Generalist Foundation Model for Unified Multimodal Medical Understanding and Reasoning","created":"2025-06-08","cited_by_count":230,"area":"lr"},{"id":"2503.24235","title":"A Survey on Test-Time Scaling in Large Language Models: What, How, Where, and How Well?","created":"2025-03-31","cited_by_count":223,"area":"lr"},{"id":"2404.15155","title":"MDAgents: An Adaptive Collaboration of LLMs for Medical Decision-Making","created":"2024-04-22","cited_by_count":163,"area":null},{"id":"2504.00993","title":"MedReason: Eliciting Factual Medical Reasoning Steps in LLMs via Knowledge Graphs","created":"2025-04-01","cited_by_count":110,"area":"lr"},{"id":"2504.00869","title":"m1: Unleash the Potential of Test-Time Scaling for Medical Reasoning with Large Language Models","created":"2025-04-01","cited_by_count":46,"area":"lr"},{"id":"2502.12671","title":"Baichuan-M1: Pushing the Medical Capability of Large Language Models","created":"2025-02-18","cited_by_count":43,"area":null},{"id":"2503.07459","title":"MedicalAgentsBench for Complex Medical Reasoning: Comparing Internalized Reasoning Models versus Externalized Agent-based Frameworks","created":"2025-03-10","cited_by_count":40,"area":"lr"},{"id":"2508.21148","title":"A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers","created":"2025-08-28","cited_by_count":37,"area":"agents"},{"id":"2501.06458","title":"O1 Replication Journey -- Part 3: Inference-time Scaling for Medical Reasoning","created":"2025-01-11","cited_by_count":35,"area":"lr"},{"id":"2409.15277","title":"A Preliminary Study of o1 in Medicine: Are We Closer to an AI Doctor?","created":"2024-09-23","cited_by_count":33,"area":null},{"id":"2411.06469","title":"ClinicalBench: Can LLMs Beat Traditional ML Models in Clinical Prediction?","created":"2024-11-10","cited_by_count":32,"area":null},{"id":"2404.00376","title":"Small Language Models Learn Enhanced Reasoning Skills from Medical Textbooks","created":"2024-03-30","cited_by_count":30,"area":"lr"},{"id":"2411.15640","title":"AfriMed-QA: A Pan-African, Multi-Specialty, Medical Question-Answering Benchmark Dataset","created":"2024-11-23","cited_by_count":26,"area":null},{"id":"2507.07988","title":"Automating Expert-Level Medical Reasoning Evaluation of Large Language Models","created":"2025-07-10","cited_by_count":22,"area":"lr"},{"id":"2505.14107","title":"DiagnosisArena: Benchmarking Diagnostic Reasoning for Large Language Models","created":"2025-05-20","cited_by_count":21,"area":"lr"},{"id":"2505.11462","title":"Disentangling Reasoning and Knowledge in Medical Large Language Models","created":"2025-05-16","cited_by_count":18,"area":"lr"},{"id":"2507.18905","title":"Large language models provide unsafe answers to patient-posed medical questions","created":"2025-07-25","cited_by_count":18,"area":null},{"id":"2510.00526","title":"Beyond Log Likelihood: Probability-Based Objectives for Supervised Fine-Tuning across the Model Capability Continuum","created":"2025-10-01","cited_by_count":18,"area":null},{"id":"2412.01605","title":"Medchain: Bridging the Gap Between LLM Agents and Clinical Practice with Interactive Sequence","created":"2024-12-02","cited_by_count":17,"area":"agents"},{"id":"2502.18274","title":"Citrus: Leveraging Expert Cognitive Pathways in a Medical Language Model for Advanced Medical Decision Support","created":"2025-02-25","cited_by_count":16,"area":"lr"},{"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":"2505.03427","title":"MedArabiQ: Benchmarking Large Language Models on Arabic Medical Tasks","created":"2025-05-06","cited_by_count":15,"area":null},{"id":"2408.01933","title":"DiReCT: Diagnostic Reasoning for Clinical Notes via Large Language Models","created":"2024-08-04","cited_by_count":14,"area":"lr"},{"id":"2506.14028","title":"MultiFinBen: Benchmarking Large Language Models for Multilingual and Multimodal Financial Application","created":"2025-06-16","cited_by_count":14,"area":null},{"id":"2404.04067","title":"Does Biomedical Training Lead to Better Medical Performance?","created":"2024-04-05","cited_by_count":13,"area":null},{"id":"2502.00837","title":"Explainability in Practice: A Survey of Explainable NLP Across Various Domains","created":"2025-02-02","cited_by_count":11,"area":null},{"id":"2604.25917","title":"Recursive Multi-Agent Systems","created":"2026-04-28","cited_by_count":10,"area":"agents"},{"id":"2510.11196","title":"Evaluating Reasoning Faithfulness in Medical Vision-Language Models using Multimodal Perturbations","created":"2025-10-13","cited_by_count":9,"area":"lr"},{"id":"2606.05241","title":"Search-Time Contamination in Deep Research Agents: Measuring Performance Inflation in Public Benchmark Evaluation","created":"2026-06-03","cited_by_count":9,"area":"lr"},{"id":"2509.19090","title":"Citrus-V: Advancing Medical Foundation Models with Unified Medical Image Grounding for Clinical Reasoning","created":"2025-09-23","cited_by_count":8,"area":null},{"id":"2603.03292","title":"From Conflict to Consensus: Boosting Medical Reasoning via Multi-Round Agentic RAG","created":"2026-02-06","cited_by_count":7,"area":"lr"},{"id":"2405.14766","title":"Evaluating Large Language Models for Public Health Classification and Extraction Tasks","created":"2024-05-23","cited_by_count":6,"area":null},{"id":"2503.22746","title":"Susceptibility of Large Language Models to User-Driven Factors in Medical Queries","created":"2025-03-26","cited_by_count":6,"area":null},{"id":"2505.23118","title":"Elicit and Enhance: Advancing Multimodal Reasoning in Medical Scenarios","created":"2025-05-29","cited_by_count":6,"area":"lr"},{"id":"2602.12705","title":"MedXIAOHE: A Comprehensive Recipe for Building Medical MLLMs","created":"2026-02-13","cited_by_count":6,"area":"mllm"},{"id":"2605.23932","title":"When Correct Beliefs Collapse: Epistemic Resilience of LLMs under Clinical Pressure","created":"2026-04-23","cited_by_count":6,"area":null},{"id":"2411.09213","title":"Comprehensive and Practical Evaluation of Retrieval-Augmented Generation Systems for Medical Question Answering","created":"2024-11-14","cited_by_count":5,"area":"rag"},{"id":"2505.18452","title":"MedScore: Generalizable Factuality Evaluation of Free-Form Medical Answers by Domain-adapted Claim Decomposition and Verification","created":"2025-05-24","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":"2508.11894","title":"QuarkMed Medical Foundation Model Technical Report","created":"2025-08-16","cited_by_count":5,"area":null},{"id":"2410.16574","title":"How Can We Diagnose and Treat Bias in Large Language Models for Clinical Decision-Making?","created":"2024-10-21","cited_by_count":4,"area":null},{"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":"2505.21657","title":"Explaining Large Language Models with gSMILE","created":"2025-05-27","cited_by_count":4,"area":null},{"id":"2510.13170","title":"Putting on the Thinking Hats: A Survey on Chain of Thought Fine-tuning from the Perspective of Human Reasoning Mechanism","created":"2025-10-15","cited_by_count":4,"area":"lr"},{"id":"2512.10206","title":"CP-Env: Evaluating Large Language Models on Clinical Pathways in a Controllable Hospital Environment","created":"2025-12-11","cited_by_count":4,"area":null},{"id":"2603.26182","title":"ClinicalAgents: Multi-Agent Orchestration for Clinical Decision Making with Dual-Memory","created":"2026-03-27","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":"2604.16506","title":"Medical thinking with multiple images","created":"2026-04-14","cited_by_count":4,"area":"lr"},{"id":"2410.09019","title":"MedMobile: A mobile-sized language model with clinical capabilities","created":"2024-10-11","cited_by_count":3,"area":"lr"},{"id":"2509.15403","title":"Quantifying Uncertainty in Natural Language Explanations of Large Language Models for Question Answering","created":"2025-09-18","cited_by_count":3,"area":null},{"id":"2512.10195","title":"AutoMedic: An Automated Evaluation Framework for Clinical Conversational Agents with Medical Dataset Grounding","created":"2025-12-11","cited_by_count":3,"area":"agents"},{"id":"2601.09876","title":"Patient-Similarity Cohort Reasoning in Clinical Text-to-SQL","created":"2026-01-14","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":"2602.01714","title":"MedAraBench: Large-Scale Arabic Medical Question Answering Dataset and Benchmark","created":"2026-02-02","cited_by_count":3,"area":null},{"id":"2603.18773","title":"Automatic Configuration of LLM Post-Training Pipelines","created":"2026-03-19","cited_by_count":3,"area":null},{"id":"2605.28819","title":"PEFT-Arena: Understanding Parameter-Efficient Finetuning from a Stability-Plasticity Perspective","created":"2026-05-27","cited_by_count":3,"area":null},{"id":"2410.13259","title":"From Babbling to Fluency: Evaluating the Evolution of Language Models in Terms of Human Language Acquisition","created":"2024-10-17","cited_by_count":2,"area":null},{"id":"2505.18283","title":"TAGS: A Test-Time Generalist-Specialist Framework with Retrieval-Augmented Reasoning and Verification","created":"2025-05-23","cited_by_count":2,"area":"lr"},{"id":"2505.21503","title":"Silence is Not Consensus: Disrupting Agreement Bias in Multi-Agent LLMs via Catfish Agent for Clinical Decision Making","created":"2025-05-27","cited_by_count":2,"area":"agents"},{"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":"2509.16360","title":"RephQA: Evaluating Readability of Large Language Models in Public Health Question Answering","created":"2025-09-19","cited_by_count":2,"area":"lr"},{"id":"2509.22713","title":"RAR$^2$: Retrieval-Augmented Medical Reasoning via Thought-Driven Retrieval","created":"2025-09-24","cited_by_count":2,"area":"lr"},{"id":"2605.01011","title":"CLEAR: Revealing How Noise and Ambiguity Degrade Reliability in LLMs for Medicine","created":"2026-05-01","cited_by_count":2,"area":null},{"id":"2608.24570","title":"EviDx: Evidence-Aware Active Diagnosis with Scaffolded LLM Agents","created":"2026-08-25","cited_by_count":2,"area":"agents"},{"id":"2503.02365","title":"EchoQA: A Large Collection of Instruction Tuning Data for Echocardiogram Reports","created":"2025-03-04","cited_by_count":1,"area":null},{"id":"2506.00095","title":"ClinBench-HPB: A Clinical Benchmark for Evaluating LLMs in Hepato-Pancreato-Biliary Diseases","created":"2025-05-30","cited_by_count":1,"area":null},{"id":"2506.00612","title":"Enhancing Clinical Multiple-Choice Questions Benchmarks with Knowledge Graph Guided Distractor Generation","created":"2025-05-31","cited_by_count":1,"area":null},{"id":"2507.12261","title":"Infherno: End-to-end Agent-based FHIR Resource Synthesis from Free-form Clinical Notes","created":"2025-07-16","cited_by_count":1,"area":"agents"},{"id":"2508.08115","title":"TeamMedAgents: Pareto-Efficient Multi-Agent Medical Reasoning Through Teamwork Theory","created":"2025-08-11","cited_by_count":1,"area":"lr"},{"id":"2510.10415","title":"CQA-Eval: Designing Reliable Evaluations of Multi-paragraph Clinical QA under Resource Constraints","created":"2025-10-12","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":"2604.09482","title":"Process Reward Agents for Steering Knowledge-Intensive Reasoning","created":"2026-04-10","cited_by_count":1,"area":"rag"},{"id":"2606.07853","title":"Beyond English benchmarks: clinical llm evaluation in Brazilian Portuguese","created":"2026-06-05","cited_by_count":1,"area":null},{"id":"2606.26797","title":"Reasoning Quality Emerges Early: Data Curation for Reasoning Models","created":"2026-06-25","cited_by_count":1,"area":"lr"},{"id":"2409.19177","title":"Evidence Is All You Need: Ordering Imaging Studies via Language Model Alignment with the ACR Appropriateness Criteria","created":"2024-09-27","cited_by_count":0,"area":"alignment"},{"id":"2410.12868","title":"IMAS: A Comprehensive Agentic Approach to Rural Healthcare Delivery","created":"2024-10-13","cited_by_count":0,"area":null},{"id":"2507.15275","title":"ChiMed 2.0: Advancing Chinese Medical Dataset in Facilitating Large Language Modeling","created":"2025-07-21","cited_by_count":0,"area":"alignment"},{"id":"2508.09719","title":"Improving ARDS Diagnosis Through Context-Aware Concept Bottleneck Models","created":"2025-08-13","cited_by_count":0,"area":null},{"id":"2510.12217","title":"HALF: Harm-Aware LLM Fairness Evaluation Aligned with Deployment","created":"2025-10-14","cited_by_count":0,"area":null},{"id":"2510.18691","title":"Investigating LLM Capabilities on Long Context Comprehension for Medical Question Answering","created":"2025-10-21","cited_by_count":0,"area":null},{"id":"2512.21515","title":"Perplexity-Aware Data Scaling Law: Perplexity Landscapes Predict Performance for Continual Pre-training","created":"2025-12-25","cited_by_count":0,"area":null},{"id":"2601.15674","title":"What Patients Really Ask: Exploring the Effect of False Assumptions in Patient Information Seeking","created":"2026-01-22","cited_by_count":0,"area":null},{"id":"2602.11460","title":"ADRD-Bench: A Preliminary LLM Benchmark for Alzheimer's Disease and Related Dementias","created":"2026-02-12","cited_by_count":0,"area":null},{"id":"2603.00842","title":"MedGPT-oss: Training a General-Purpose Vision-Language Model for Biomedicine","created":"2026-03-01","cited_by_count":0,"area":"mllm"},{"id":"2603.11394","title":"Stop Listening to Me! How Multi-turn Conversations Can Degrade LLM Reliability","created":"2026-03-12","cited_by_count":0,"area":null},{"id":"2603.29893","title":"Perfecting Human-AI Interaction at Clinical Scale. Turning Production Signals into Safer, More Human Conversations","created":"2026-02-09","cited_by_count":0,"area":null},{"id":"2604.06262","title":"From Exposure to Internalization: Dual-Stream Calibration for In-context Clinical Reasoning","created":"2026-04-07","cited_by_count":0,"area":null},{"id":"2604.06650","title":"A Parameter-Efficient Transfer Learning Approach through Multitask Prompt Distillation and Decomposition for Clinical NLP","created":"2026-04-08","cited_by_count":0,"area":null},{"id":"2604.14306","title":"EuropeMedQA Study Protocol: A Multilingual, Multimodal Medical Examination Dataset for Language Model Evaluation","created":"2026-04-15","cited_by_count":0,"area":null},{"id":"2604.17928","title":"HEALing Entropy Collapse: Enhancing Exploration in Few-Shot RLVR via Hybrid-Domain Entropy Dynamics Alignment","created":"2026-04-20","cited_by_count":0,"area":"lr"},{"id":"2605.06177","title":"BioMedArena: An Open-source Toolkit for Building and Evaluating Biomedical Deep Research Agents","created":"2026-05-07","cited_by_count":0,"area":"agents"},{"id":"2605.09492","title":"APCD: Adaptive Path-Contrastive Decoding for Reliable Large Language Model Generation","created":"2026-05-10","cited_by_count":0,"area":null},{"id":"2605.09661","title":"MedMeta: A Benchmark for LLMs in Synthesizing Meta-Analysis Conclusion from Medical Studies","created":"2026-05-10","cited_by_count":0,"area":"rag"},{"id":"2605.30599","title":"AMNESIA: A Large Scale Medical Unlearning Benchmark Suite with Disease-Informed Analysis","created":"2026-05-28","cited_by_count":0,"area":"safety"},{"id":"2606.09883","title":"TD-Grokking: Learning from Zero-Reward Problems by Training-Time Decomposition","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2606.11189","title":"A Unifying Lens on Supervised Fine-Tuning Through Target Distribution Design","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2608.14598","title":"Position: Medical AI Neglects Real Treatment Outcomes","created":"2026-06-28","cited_by_count":0,"area":null},{"id":"2608.29453","title":"AI Can Be Easily Persuaded in Clinical Decision Making","created":"2026-08-29","cited_by_count":0,"area":null}],"next_cursor":"100"}