{"total":155,"rows":[{"id":"2311.10537","title":"MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoning","created":"2023-11-16","cited_by_count":316,"area":"lr"},{"id":"2412.18925","title":"HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs","created":"2024-12-25","cited_by_count":265,"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":"2310.05492","title":"How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition","created":"2023-10-09","cited_by_count":223,"area":"lr"},{"id":"2406.00922","title":"MediQ: Question-Asking LLMs and a Benchmark for Reliable Interactive Clinical Reasoning","created":"2024-06-03","cited_by_count":154,"area":"lr"},{"id":"2312.04350","title":"CLadder: Assessing Causal Reasoning in Language Models","created":"2023-12-07","cited_by_count":107,"area":"lr"},{"id":"2308.06834","title":"Diagnostic Reasoning Prompts Reveal the Potential for Large Language Model Interpretability in Medicine","created":"2023-08-13","cited_by_count":83,"area":"lr"},{"id":"2404.06511","title":"MoReVQA: Exploring Modular Reasoning Models for Video Question Answering","created":"2024-04-09","cited_by_count":74,"area":"lr"},{"id":"2308.09729","title":"MindMap: Knowledge Graph Prompting Sparks Graph of Thoughts in Large Language Models","created":"2023-08-17","cited_by_count":73,"area":"lr"},{"id":"2503.18968","title":"MedAgent-Pro: Towards Evidence-based Multi-modal Medical Diagnosis via Reasoning Agentic Workflow","created":"2025-03-21","cited_by_count":73,"area":"lr"},{"id":"2311.11797","title":"Igniting Language Intelligence: The Hitchhiker's Guide From Chain-of-Thought Reasoning to Language Agents","created":"2023-11-20","cited_by_count":72,"area":"lr"},{"id":"2305.18395","title":"Knowledge-Augmented Reasoning Distillation for Small Language Models in Knowledge-Intensive Tasks","created":"2023-05-28","cited_by_count":64,"area":"lr"},{"id":"2508.16949","title":"Breaking the Exploration Bottleneck: Rubric-Scaffolded Reinforcement Learning for General LLM Reasoning","created":"2025-08-23","cited_by_count":63,"area":"lr"},{"id":"2310.04959","title":"Towards Better Chain-of-Thought Prompting Strategies: A Survey","created":"2023-10-08","cited_by_count":62,"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":"2405.14365","title":"JiuZhang3.0: Efficiently Improving Mathematical Reasoning by Training Small Data Synthesis Models","created":"2024-05-23","cited_by_count":45,"area":"lr"},{"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":"2505.11733","title":"MedCaseReasoning: Evaluating and learning diagnostic reasoning from clinical case reports","created":"2025-05-16","cited_by_count":36,"area":"lr"},{"id":"2508.08224","title":"Capabilities of GPT-5 on Multimodal Medical Reasoning","created":"2025-08-11","cited_by_count":36,"area":"lr"},{"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":"2401.15269","title":"Improving Medical Reasoning through Retrieval and Self-Reflection with Retrieval-Augmented Large Language Models","created":"2024-01-27","cited_by_count":34,"area":"lr"},{"id":"2410.06238","title":"EVOLvE: Evaluating and Optimizing LLMs For In-Context Exploration","created":"2024-10-08","cited_by_count":34,"area":"lr"},{"id":"2402.17887","title":"JMLR: Joint Medical LLM and Retrieval Training for Enhancing Reasoning and Professional Question Answering Capability","created":"2024-02-27","cited_by_count":32,"area":"lr"},{"id":"2403.04890","title":"Few shot chain-of-thought driven reasoning to prompt LLMs for open ended medical question answering","created":"2024-03-07","cited_by_count":31,"area":"lr"},{"id":"2404.14777","title":"ClinicalAgent: Clinical Trial Multi-Agent System with Large Language Model-based Reasoning","created":"2024-04-23","cited_by_count":31,"area":"lr"},{"id":"2406.13948","title":"CityGPT: Empowering Urban Spatial Cognition of Large Language Models","created":"2024-06-20","cited_by_count":30,"area":"lr"},{"id":"2406.19741","title":"ROS-LLM: A ROS framework for embodied AI with task feedback and structured reasoning","created":"2024-06-28","cited_by_count":27,"area":"lr"},{"id":"2506.20964","title":"Evidence-based diagnostic reasoning with multi-agent copilot for human pathology","created":"2025-06-26","cited_by_count":27,"area":"lr"},{"id":"2509.18314","title":"Exploiting Tree Structure for Credit Assignment in RL Training of LLMs","created":"2025-09-22","cited_by_count":27,"area":"lr"},{"id":"2402.14899","title":"Stop Reasoning! When Multimodal LLM with Chain-of-Thought Reasoning Meets Adversarial Image","created":"2024-02-22","cited_by_count":26,"area":"lr"},{"id":"2404.02935","title":"KnowHalu: Hallucination Detection via Multi-Form Knowledge Based Factual Checking","created":"2024-04-03","cited_by_count":26,"area":"lr"},{"id":"2501.12051","title":"MedS$^3$: Towards Medical Slow Thinking with Self-Evolved Soft Dual-sided Process Supervision","created":"2025-01-21","cited_by_count":24,"area":"lr"},{"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":"2411.01829","title":"Formal Theorem Proving by Rewarding LLMs to Decompose Proofs Hierarchically","created":"2024-11-04","cited_by_count":22,"area":"lr"},{"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":"2305.01505","title":"Beyond Classification: Financial Reasoning in State-of-the-Art Language Models","created":"2023-04-30","cited_by_count":19,"area":"lr"},{"id":"2406.06464","title":"Transforming Wearable Data into Personal Health Insights using Large Language Model Agents","created":"2024-06-10","cited_by_count":19,"area":"lr"},{"id":"2510.25628","title":"EHR-R1: A Reasoning-Enhanced Foundational Language Model for Electronic Health Record Analysis","created":"2025-10-29","cited_by_count":18,"area":"lr"},{"id":"2304.02496","title":"Evaluation of ChatGPT Family of Models for Biomedical Reasoning and Classification","created":"2023-04-05","cited_by_count":17,"area":"lr"},{"id":"2410.12375","title":"PRefLexOR: Preference-based Recursive Language Modeling for Exploratory Optimization of Reasoning and Agentic Thinking","created":"2024-10-16","cited_by_count":17,"area":"lr"},{"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":"2401.15328","title":"Equipping Language Models with Tool Use Capability for Tabular Data Analysis in Finance","created":"2024-01-27","cited_by_count":14,"area":"lr"},{"id":"2403.14255","title":"ERD: A Framework for Improving LLM Reasoning for Cognitive Distortion Classification","created":"2024-03-21","cited_by_count":14,"area":"lr"},{"id":"2402.16631","title":"GenAINet: Enabling Wireless Collective Intelligence via Knowledge Transfer and Reasoning","created":"2024-02-26","cited_by_count":13,"area":"lr"},{"id":"2403.06294","title":"ArgMed-Agents: Explainable Clinical Decision Reasoning with LLM Disscusion via Argumentation Schemes","created":"2024-03-10","cited_by_count":13,"area":"lr"},{"id":"2505.17697","title":"Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models","created":"2025-05-23","cited_by_count":13,"area":"lr"},{"id":"2507.02773","title":"KERAP: A Knowledge-Enhanced Reasoning Approach for Accurate Zero-shot Diagnosis Prediction Using Multi-agent LLMs","created":"2025-07-03","cited_by_count":12,"area":"lr"},{"id":"2510.25588","title":"Standardization of Psychiatric Diagnoses -- Role of Fine-tuned LLM Consortium and OpenAI-gpt-oss Reasoning LLM Enabled Decision Support System","created":"2025-10-29","cited_by_count":12,"area":"lr"},{"id":"2504.18671","title":"Proof-of-TBI -- Fine-Tuned Vision Language Model Consortium and OpenAI-o3 Reasoning LLM-Based Medical Diagnosis Support System for Mild Traumatic Brain Injury (TBI) Prediction","created":"2025-04-25","cited_by_count":11,"area":"lr"},{"id":"2508.15746","title":"End-to-End Agentic RAG System Training for Traceable Diagnostic Reasoning","created":"2025-08-21","cited_by_count":10,"area":"lr"},{"id":"2509.15279","title":"Fleming-R1: Toward Expert-Level Medical Reasoning via Reinforcement Learning","created":"2025-09-18","cited_by_count":10,"area":"lr"},{"id":"2508.07827","title":"Evaluating Large Language Models as Expert Annotators","created":"2025-08-11","cited_by_count":9,"area":"lr"},{"id":"2510.10278","title":"Simulating Viva Voce Examinations to Evaluate Clinical Reasoning in Large Language Models","created":"2025-10-11","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":"2508.00743","title":"Multi-step retrieval and reasoning improves radiology question answering with large language models","created":"2025-08-01","cited_by_count":7,"area":"lr"},{"id":"2509.24816","title":"KnowGuard: Knowledge-Driven Abstention for Multi-Round Clinical Reasoning","created":"2025-09-29","cited_by_count":7,"area":"lr"},{"id":"2508.12140","title":"Exploring Efficiency Frontiers of Thinking Budget in Medical Reasoning: Scaling Laws between Computational Resources and Reasoning Quality","created":"2025-08-16","cited_by_count":6,"area":"lr"},{"id":"2605.04039","title":"Safety and accuracy follow different scaling laws in clinical large language models","created":"2026-05-05","cited_by_count":6,"area":"lr"},{"id":"2402.07812","title":"Retrieval Augmented Thought Process for Private Data Handling in Healthcare","created":"2024-02-12","cited_by_count":5,"area":"lr"},{"id":"2501.11885","title":"Med-R$^2$: Crafting Trustworthy LLM Physicians via Retrieval and Reasoning of Evidence-Based Medicine","created":"2025-01-21","cited_by_count":5,"area":"lr"},{"id":"2502.20545","title":"SoS1: O1 and R1-Like Reasoning LLMs are Sum-of-Square Solvers","created":"2025-02-27","cited_by_count":5,"area":"lr"},{"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":"2508.10865","title":"Performance of GPT-5 in Brain Tumor MRI Reasoning","created":"2025-08-14","cited_by_count":5,"area":"lr"},{"id":"2509.15557","title":"Reward Hacking Mitigation using Verifiable Composite Rewards","created":"2025-09-19","cited_by_count":5,"area":"lr"},{"id":"2510.08825","title":"Search-on-Graph: Iterative Informed Navigation for Large Language Model Reasoning on Knowledge Graphs","created":"2025-10-09","cited_by_count":5,"area":"lr"},{"id":"2510.24236","title":"Towards Transparent Reasoning: What Drives Faithfulness in Large Language Models?","created":"2025-10-28","cited_by_count":5,"area":"lr"},{"id":"2411.07611","title":"Knowledge-Augmented Multimodal Clinical Rationale Generation for Disease Diagnosis with Small Language Models","created":"2024-11-12","cited_by_count":4,"area":"lr"},{"id":"2503.11348","title":"RESPONSE: Benchmarking the Ability of Language Models to Undertake Commonsense Reasoning in Crisis Situation","created":"2025-03-14","cited_by_count":4,"area":"lr"},{"id":"2504.06581","title":"Right Prediction, Wrong Reasoning: Uncovering LLM Misalignment in RA Disease Diagnosis","created":"2025-04-09","cited_by_count":4,"area":"lr"},{"id":"2506.01252","title":"MTCMB: A Multi-Task Benchmark Framework for Evaluating LLMs on Knowledge, Reasoning, and Safety in Traditional Chinese Medicine","created":"2025-06-02","cited_by_count":4,"area":"lr"},{"id":"2508.15868","title":"CARFT: Boosting LLM Reasoning via Contrastive Learning with Annotated Chain-of-Thought-based Reinforced Fine-Tuning","created":"2025-08-21","cited_by_count":4,"area":"lr"},{"id":"2510.21148","title":"How to Auto-optimize Prompts for Domain Tasks? Adaptive Prompting and Reasoning through Evolutionary Domain Knowledge Adaptation","created":"2025-10-24","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":"2410.18856","title":"Entry-level guide to the use of large language models for medical research","created":"2024-10-24","cited_by_count":3,"area":"lr"},{"id":"2508.07292","title":"EndoCogniAgent: Closed-Loop Agentic Reasoning with Self-Consistency Validation for Endoscopic Diagnosis","created":"2025-08-10","cited_by_count":3,"area":"lr"},{"id":"2508.19980","title":"Evaluating Language Model Reasoning about Confidential Information","created":"2025-08-27","cited_by_count":3,"area":"lr"},{"id":"2510.11985","title":"CGBench: Benchmarking Language Model Scientific Reasoning for Clinical Genetics Research","created":"2025-10-13","cited_by_count":3,"area":"lr"},{"id":"2511.05747","title":"CoT-X: An Adaptive Framework for Cross-Model Chain-of-Thought Transfer and Optimization","created":"2025-11-07","cited_by_count":3,"area":"lr"},{"id":"2602.06359","title":"Training Data Selection with Gradient Orthogonality for Efficient Domain Adaptation","created":"2026-02-06","cited_by_count":3,"area":"lr"},{"id":"2602.20094","title":"CausalFlip: A Benchmark for LLM Causal Judgment Beyond Semantic Matching","created":"2026-02-23","cited_by_count":3,"area":"lr"},{"id":"2309.08969","title":"Rethinking STS and NLI in Large Language Models","created":"2023-09-16","cited_by_count":2,"area":"lr"},{"id":"2412.15748","title":"Critique of Impure Reason: Unveiling the reasoning behaviour of medical Large Language Models","created":"2024-12-20","cited_by_count":2,"area":"lr"},{"id":"2507.03460","title":"Multi-Agent Reasoning for Cardiovascular Imaging Phenotype Analysis","created":"2025-07-04","cited_by_count":2,"area":"lr"},{"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":"2603.06271","title":"Agentic retrieval-augmented reasoning reshapes collective reliability under model variability in radiology question answering","created":"2026-03-06","cited_by_count":2,"area":"lr"},{"id":"2605.09675","title":"CodeClinic: Evaluating Automation of Coding Skills for Clinical Reasoning Agents","created":"2026-05-10","cited_by_count":2,"area":"lr"},{"id":"2605.12361","title":"MedHopQA: A Disease-Centered Multi-Hop Reasoning Benchmark and Evaluation Framework for LLM-Based Biomedical Question Answering","created":"2026-05-12","cited_by_count":2,"area":"lr"},{"id":"2605.17894","title":"Evaluating Cognitive Age Alignment in Interactive AI Agents","created":"2026-05-18","cited_by_count":2,"area":"lr"},{"id":"2606.31825","title":"Breaking Failure Cascades: Step-Aware Reinforcement Learning for Medical Multimodal Reasoning","created":"2026-06-30","cited_by_count":2,"area":"lr"},{"id":"2503.04153","title":"KidneyTalk-open: No-code Deployment of a Private Large Language Model with Medical Documentation-Enhanced Knowledge Database for Kidney Disease","created":"2025-03-06","cited_by_count":1,"area":"lr"},{"id":"2510.03349","title":"AgentCaster: Reasoning-Guided Tornado Forecasting","created":"2025-10-02","cited_by_count":1,"area":"lr"},{"id":"2511.06418","title":"How Well Do LLMs Understand Drug Mechanisms? A Knowledge + Reasoning Evaluation Dataset","created":"2025-11-09","cited_by_count":1,"area":"lr"},{"id":"2512.05365","title":"MCP-AI: Protocol-Driven Intelligence Framework for Autonomous Reasoning in Healthcare","created":"2025-12-05","cited_by_count":1,"area":"lr"},{"id":"2512.21583","title":"A Medical Multimodal Diagnostic Framework Integrating Vision-Language Models and Logic Tree Reasoning","created":"2025-12-25","cited_by_count":1,"area":"lr"},{"id":"2601.04891","title":"Scaling Vision Language Models for Pharmaceutical Long Form Video Reasoning on Industrial GenAI Platform","created":"2026-01-08","cited_by_count":1,"area":"lr"},{"id":"2602.01779","title":"LingLanMiDian: Systematic Evaluation of LLMs on TCM Knowledge and Clinical Reasoning","created":"2026-02-02","cited_by_count":1,"area":"lr"},{"id":"2602.10282","title":"Linear-LLM-SCM: Benchmarking LLMs for Coefficient Elicitation in Linear-Gaussian Causal Models","created":"2026-02-10","cited_by_count":1,"area":"lr"},{"id":"2602.14044","title":"Context Shapes LLMs Retrieval-Augmented Fact-Checking Effectiveness","created":"2026-02-15","cited_by_count":1,"area":"lr"},{"id":"2603.10143","title":"Reason and Verify: A Framework for Faithful Retrieval-Augmented Generation","created":"2026-03-10","cited_by_count":1,"area":"lr"}],"next_cursor":"100"}