{"total":37,"rows":[{"id":"2410.10762","title":"AFlow: Automating Agentic Workflow Generation","created":"2024-10-14","cited_by_count":432,"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":"2505.20347","title":"SeRL: Self-Play Reinforcement Learning for Large Language Models with Limited Data","created":"2025-05-25","cited_by_count":51,"area":"lr"},{"id":"2502.19655","title":"Med-RLVR: Emerging Medical Reasoning from a 3B base model via reinforcement Learning","created":"2025-02-27","cited_by_count":40,"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":"2505.03981","title":"X-Reasoner: Towards Generalizable Reasoning Across Modalities and Domains","created":"2025-05-06","cited_by_count":31,"area":"lr"},{"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":"2412.10849","title":"Superhuman performance of a large language model on the reasoning tasks of a physician","created":"2024-12-14","cited_by_count":28,"area":"lr"},{"id":"2502.07143","title":"Ask Patients with Patience: Enabling LLMs for Human-Centric Medical Dialogue with Grounded Reasoning","created":"2025-02-11","cited_by_count":19,"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":"2505.07889","title":"BioProBench: A Corpus and Benchmark for Biological Protocol Reasoning in Autonomous Science","created":"2025-05-11","cited_by_count":16,"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":"2504.06771","title":"AI, Help Me Think$\\unicode{x2014}$but for Myself: Assisting People in Complex Decision-Making by Providing Different Kinds of Cognitive Support","created":"2025-04-09","cited_by_count":12,"area":"lr"},{"id":"2407.13578","title":"How Reliable are LLMs as Knowledge Bases? Re-thinking Facutality and Consistency","created":"2024-07-18","cited_by_count":10,"area":"lr"},{"id":"2403.00878","title":"Crimson: Empowering Strategic Reasoning in Cybersecurity through Large Language Models","created":"2024-03-01","cited_by_count":8,"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":"2504.18080","title":"Stabilizing Reasoning in Medical LLMs with Continued Pretraining and Reasoning Preference Optimization","created":"2025-04-25","cited_by_count":4,"area":"lr"},{"id":"2512.09636","title":"MiraMind: Benchmarking Reliable Mental Health Reasoning beyond Answer Accuracy","created":"2025-12-10","cited_by_count":4,"area":"lr"},{"id":"2604.08559","title":"Medical Reasoning with Large Language Models: A Survey and MR-Bench","created":"2026-03-17","cited_by_count":4,"area":"lr"},{"id":"2409.11783","title":"Development and bilingual evaluation of Japanese medical large language model within reasonably low computational resources","created":"2024-09-18","cited_by_count":3,"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":"2510.11985","title":"CGBench: Benchmarking Language Model Scientific Reasoning for Clinical Genetics Research","created":"2025-10-13","cited_by_count":3,"area":"lr"},{"id":"2505.02722","title":"Enhancing LLMs' Clinical Reasoning with Real-World Data from a Nationwide Sepsis Registry","created":"2025-05-05","cited_by_count":2,"area":"lr"},{"id":"2512.10430","title":"T-pro 2.0: An Efficient Russian Hybrid-Reasoning Model and Playground","created":"2025-12-11","cited_by_count":2,"area":"lr"},{"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":"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":"2603.27335","title":"PubMed Reasoner: Dynamic Reasoning-based Retrieval for Evidence-Grounded Biomedical Question Answering","created":"2026-03-28","cited_by_count":1,"area":"lr"},{"id":"2605.31410","title":"FAM-Bench: A Multimodal Benchmark for Condition-Aware Food-as-Medicine Reasoning","created":"2026-05-29","cited_by_count":1,"area":"lr"},{"id":"2507.04142","title":"Dissecting Clinical Reasoning in Language Models: A Comparative Study of Prompts and Model Adaptation Strategies","created":"2025-07-05","cited_by_count":0,"area":"lr"},{"id":"2601.12842","title":"SCULPT: Constraint-Guided Pruned MCTS that Carves Efficient Paths for Mathematical Reasoning","created":"2026-01-19","cited_by_count":0,"area":"lr"},{"id":"2602.00491","title":"From Knowledge to Inference: Formalizing Specialized Public Health Reasoning on GlobalHealthAtlas","created":"2026-01-31","cited_by_count":0,"area":"lr"},{"id":"2607.01440","title":"FaithMed: Training LLMs For Faithful Evidence-Based Medical Reasoning","created":"2026-07-01","cited_by_count":0,"area":"lr"},{"id":"2607.02983","title":"Reinforcement Learning for Evidence-Seeking Diagnostic Reasoning with Large Language Models","created":"2026-07-03","cited_by_count":0,"area":"lr"},{"id":"2607.22555","title":"DeepLens Diagnosis Agent: Agentic Workflow Design Lets a Small Reasoning Model Compete with Frontier LLMs","created":"2026-05-19","cited_by_count":0,"area":"lr"},{"id":"2609.32817","title":"Right Answer, Wrong Reason: Accuracy, Consistency, and Consensus Are Misleading Indicators of LLM Faithfulness in Clinical Decision Support","created":"2026-09-26","cited_by_count":0,"area":"lr"},{"id":"2610.07787","title":"OOPMAS: Object-Oriented Multi-Agent Systems for Query-Level Workflow Generation","created":"2026-10-06","cited_by_count":0,"area":"lr"}],"next_cursor":null}