{"total":140,"rows":[{"id":"2501.05366","title":"Search-o1: Agentic Search-Enhanced Large Reasoning Models","created":"2025-01-09","cited_by_count":433,"area":"lr"},{"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":"2507.17746","title":"Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains","created":"2025-07-23","cited_by_count":366,"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":"2509.08827","title":"A Survey of Reinforcement Learning for Large Reasoning Models","created":"2025-09-10","cited_by_count":180,"area":"lr"},{"id":"2503.23829","title":"Crossing the Reward Bridge: Expanding RL with Verifiable Rewards Across Diverse Domains","created":"2025-03-31","cited_by_count":156,"area":"lr"},{"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":"2504.00050","title":"JudgeLRM: Large Reasoning Models as a Judge","created":"2025-03-31","cited_by_count":78,"area":"lr"},{"id":"2501.11284","title":"RedStar: Does Scaling Long-CoT Data Unlock Better Slow-Reasoning Systems?","created":"2025-01-20","cited_by_count":60,"area":"lr"},{"id":"2509.02208","title":"Baichuan-M2: Scaling Medical Capability with Large Verifier System","created":"2025-09-02","cited_by_count":59,"area":"lr"},{"id":"2507.03019","title":"Look-Back: Implicit Visual Re-focusing in MLLM Reasoning","created":"2025-07-02","cited_by_count":55,"area":"lr"},{"id":"2502.19328","title":"Agentic Reward Modeling: Integrating Human Preferences with Verifiable Correctness Signals for Reliable Reward Systems","created":"2025-02-26","cited_by_count":51,"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":"2506.09942","title":"VerIF: Verification Engineering for Reinforcement Learning in Instruction Following","created":"2025-06-11","cited_by_count":44,"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":"2505.17952","title":"Beyond Distillation: Pushing the Limits of Medical LLM Reasoning with Minimalist Rule-Based RL","created":"2025-05-23","cited_by_count":36,"area":"lr"},{"id":"2502.08127","title":"Fino1: On the Transferability of Reasoning-Enhanced LLMs and Reinforcement Learning to Finance","created":"2025-02-12","cited_by_count":35,"area":"lr"},{"id":"2504.20930","title":"ChestX-Reasoner: Advancing Radiology Foundation Models with Reasoning through Step-by-Step Verification","created":"2025-04-29","cited_by_count":31,"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":"2506.09513","title":"ReasonMed: A 370K Multi-Agent Generated Dataset for Advancing Medical Reasoning","created":"2025-06-11","cited_by_count":27,"area":"lr"},{"id":"2508.02669","title":"MedVLThinker: Simple Baselines for Multimodal Medical Reasoning","created":"2025-08-04","cited_by_count":27,"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":"2506.11474","title":"Med-PRM: Medical Reasoning Models with Stepwise, Guideline-verified Process Rewards","created":"2025-06-13","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":"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":"2508.10848","title":"Psyche-R1: Towards Reliable Psychological LLMs through Unified Empathy, Expertise, and Reasoning","created":"2025-08-14","cited_by_count":20,"area":"lr"},{"id":"2501.09213","title":"FineMedLM-o1: Enhancing Medical Knowledge Reasoning Ability of LLM from Supervised Fine-Tuning to Test-Time Training","created":"2025-01-16","cited_by_count":19,"area":"lr"},{"id":"2505.02665","title":"A Survey of Slow Thinking-based Reasoning LLMs using Reinforced Learning and Inference-time Scaling Law","created":"2025-05-05","cited_by_count":19,"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":"2503.12918","title":"ThinkPatterns-21k: A Systematic Study on the Impact of Thinking Patterns in LLMs","created":"2025-03-17","cited_by_count":16,"area":"lr"},{"id":"2503.22732","title":"Reasoning Beyond Limits: Advances and Open Problems for LLMs","created":"2025-03-26","cited_by_count":16,"area":"lr"},{"id":"2504.13828","title":"Generative AI Act II: Test Time Scaling Drives Cognition Engineering","created":"2025-04-18","cited_by_count":15,"area":"lr"},{"id":"2505.13778","title":"CoIn: Counting the Invisible Reasoning Tokens in Commercial Opaque LLM APIs","created":"2025-05-19","cited_by_count":14,"area":"lr"},{"id":"2506.02126","title":"Knowledge or Reasoning? A Close Look at How LLMs Think Across Domains","created":"2025-06-02","cited_by_count":14,"area":"lr"},{"id":"2507.13966","title":"Bottom-up Domain-specific Superintelligence: A Reliable Knowledge Graph is What We Need","created":"2025-07-18","cited_by_count":13,"area":"lr"},{"id":"2504.02181","title":"A Survey of Scaling in Large Language Model Reasoning","created":"2025-04-02","cited_by_count":10,"area":"lr"},{"id":"2505.22240","title":"BioHopR: A Benchmark for Multi-Hop, Multi-Answer Reasoning in Biomedical Domain","created":"2025-05-28","cited_by_count":10,"area":"lr"},{"id":"2508.00669","title":"Medical Reasoning in the Era of LLMs: A Systematic Review of Enhancement Techniques and Applications","created":"2025-08-01","cited_by_count":10,"area":"lr"},{"id":"2505.17244","title":"ReasoningShield: Safety Detection over Reasoning Traces of Large Reasoning Models","created":"2025-05-22","cited_by_count":9,"area":"lr"},{"id":"2601.13262","title":"CURE-Med: Curriculum-Informed Reinforcement Learning for Multilingual Medical Reasoning","created":"2026-01-19","cited_by_count":9,"area":"lr"},{"id":"2506.07104","title":"How Far Are We from Optimal Reasoning Efficiency?","created":"2025-06-08","cited_by_count":8,"area":"lr"},{"id":"2506.12307","title":"Med-U1: Incentivizing Unified Medical Reasoning in LLMs via Large-scale Reinforcement Learning","created":"2025-06-14","cited_by_count":8,"area":"lr"},{"id":"2508.07342","title":"PrLM: Learning Explicit Reasoning for Personalized RAG via Contrastive Reward Optimization","created":"2025-08-10","cited_by_count":8,"area":"lr"},{"id":"2504.09421","title":"ClinicalGPT-R1: Pushing reasoning capability of generalist disease diagnosis with large language model","created":"2025-04-13","cited_by_count":7,"area":"lr"},{"id":"2505.21908","title":"Reinforcement Learning for Out-of-Distribution Reasoning in LLMs: An Empirical Study on Diagnosis-Related Group Coding","created":"2025-05-28","cited_by_count":7,"area":"lr"},{"id":"2506.14512","title":"SIRI-Bench: Challenging VLMs' Spatial Intelligence through Complex Reasoning Tasks","created":"2025-06-17","cited_by_count":7,"area":"lr"},{"id":"2508.00912","title":"Predictive Auditing of Hidden Tokens in LLM APIs via Reasoning Length Estimation","created":"2025-07-29","cited_by_count":7,"area":"lr"},{"id":"2512.00601","title":"Clinical-R1: Empowering Large Language Models for Faithful and Comprehensive Reasoning with Clinical Objective Relative Policy Optimization","created":"2025-11-29","cited_by_count":7,"area":"lr"},{"id":"2602.09305","title":"Reward Modeling for Reinforcement Learning-Based LLM Reasoning: Design, Challenges, and Evaluation","created":"2026-02-10","cited_by_count":7,"area":"lr"},{"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":"2502.13723","title":"Direct Value Optimization: Improving Chain-of-Thought Reasoning in LLMs with Refined Values","created":"2025-02-19","cited_by_count":6,"area":"lr"},{"id":"2505.06912","title":"Building a Human-Verified Clinical Reasoning Dataset via a Human LLM Hybrid Pipeline for Trustworthy Medical AI","created":"2025-05-11","cited_by_count":6,"area":"lr"},{"id":"2508.16129","title":"Bridging the Gap in Ophthalmic AI: MM-Retinal-Reason Dataset and OphthaReason Model toward Dynamic Multimodal Reasoning","created":"2025-08-22","cited_by_count":6,"area":"lr"},{"id":"2508.16213","title":"MedOmni-45{\\deg}: A Safety-Performance Benchmark for Reasoning-Oriented LLMs in Medicine","created":"2025-08-22","cited_by_count":6,"area":"lr"},{"id":"2512.11558","title":"DentalGPT: Incentivizing Multimodal Complex Reasoning in Dentistry","created":"2025-12-12","cited_by_count":6,"area":"lr"},{"id":"2601.18496","title":"DEEPMED: Building a Medical DeepResearch Agent via Multi-hop Med-Search Data and Turn-Controlled Agentic Training & Inference","created":"2026-01-26","cited_by_count":6,"area":"lr"},{"id":"2506.19469","title":"Surgery-R1: Advancing Surgical-VQLA with Reasoning Multimodal Large Language Model via Reinforcement Learning","created":"2025-06-24","cited_by_count":5,"area":"lr"},{"id":"2507.20917","title":"MediQAl: A French Medical Question Answering Dataset for Knowledge and Reasoning Evaluation","created":"2025-07-28","cited_by_count":5,"area":"lr"},{"id":"2510.15965","title":"One Token Embedding Is Enough to Deadlock Your Large Reasoning Model","created":"2025-10-12","cited_by_count":5,"area":"lr"},{"id":"2504.09100","title":"A Short Survey on Small Reasoning Models: Training, Inference, Applications and Research Directions","created":"2025-04-12","cited_by_count":4,"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":"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":"2508.10024","title":"RTTC: Reward-Guided Collaborative Test-Time Compute","created":"2025-08-07","cited_by_count":4,"area":"lr"},{"id":"2508.12957","title":"Adaptive Reinforcement for Open-ended Medical Reasoning via Semantic-Guided Reward Collapse Mitigation","created":"2025-08-18","cited_by_count":4,"area":"lr"},{"id":"2512.03838","title":"Training and Evaluation of Guideline-Based Medical Reasoning in LLMs","created":"2025-12-03","cited_by_count":4,"area":"lr"},{"id":"2512.13510","title":"MedCEG: Reinforcing Verifiable Medical Reasoning with Critical Evidence Graph","created":"2025-12-15","cited_by_count":4,"area":"lr"},{"id":"2601.07107","title":"MEDVISTAGYM: A Scalable Training Environment for Thinking with Medical Images via Tool-Integrated Reinforcement Learning","created":"2026-01-12","cited_by_count":4,"area":"lr"},{"id":"2605.26567","title":"MedGuideX: Internalizing Decision Logic from Executable Guidelines into Large Language Models for Clinical Reasoning","created":"2026-05-26","cited_by_count":4,"area":"lr"},{"id":"2505.19195","title":"CardioCoT: Hierarchical Reasoning for Multimodal Survival Analysis","created":"2025-05-25","cited_by_count":3,"area":"lr"},{"id":"2505.19259","title":"Towards Large Reasoning Models for Agriculture","created":"2025-05-25","cited_by_count":3,"area":"lr"},{"id":"2506.13102","title":"Rethinking Test-Time Scaling for Medical AI: Model and Task-Aware Strategies for LLMs and VLMs","created":"2025-06-16","cited_by_count":3,"area":"lr"},{"id":"2508.01450","title":"Towards Efficient Medical Reasoning with Minimal Fine-Tuning Data","created":"2025-08-02","cited_by_count":3,"area":"lr"},{"id":"2508.03733","title":"CX-Mind: A Pioneering Multimodal Large Language Model for Interleaved Reasoning in Chest X-ray via Curriculum-Guided Reinforcement Learning","created":"2025-07-31","cited_by_count":3,"area":"lr"},{"id":"2508.13579","title":"Toward Better EHR Reasoning in LLMs: Reinforcement Learning with Expert Attention Guidance","created":"2025-08-19","cited_by_count":3,"area":"lr"},{"id":"2511.15242","title":"Trustworthy and Fair SkinGPT-R1 for Democratizing Dermatological Reasoning across Diverse Ethnicities","created":"2025-11-19","cited_by_count":3,"area":"lr"},{"id":"2601.19061","title":"Thought-Transfer: Indirect Targeted Poisoning Attacks on Chain-of-Thought Reasoning Models","created":"2026-01-27","cited_by_count":3,"area":"lr"},{"id":"2601.20221","title":"Scaling Medical Reasoning Verification via Tool-Integrated Reinforcement Learning","created":"2026-01-28","cited_by_count":3,"area":"lr"},{"id":"2605.09584","title":"CLR-voyance: Reinforcing Open-Ended Reasoning for Inpatient Clinical Decision Support with Outcome-Aware Rubrics","created":"2026-05-10","cited_by_count":3,"area":"lr"},{"id":"2605.24998","title":"Better, Faster: Harnessing Self-Improvement in Large Reasoning Models","created":"2026-05-24","cited_by_count":3,"area":"lr"},{"id":"2504.18942","title":"LawFlow: Collecting and Simulating Lawyers' Thought Processes on Business Formation Case Studies","created":"2025-04-26","cited_by_count":2,"area":"lr"},{"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":"2505.23867","title":"InfiMed: Low-Resource Medical MLLMs with Advancing Understanding and Reasoning","created":"2025-05-29","cited_by_count":2,"area":"lr"},{"id":"2507.03001","title":"Evaluating Hierarchical Clinical Document Classification Using Reasoning-Based LLMs","created":"2025-07-02","cited_by_count":2,"area":"lr"},{"id":"2509.20866","title":"On the Robustness of Answer Formats in Medical Reasoning Models","created":"2025-09-25","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":"2509.24560","title":"AdaThink-Med: Optimizing Inference-Time Compute for Medical Reasoning via Uncertainty Quantification","created":"2025-09-29","cited_by_count":2,"area":"lr"},{"id":"2510.18303","title":"Proactive Reasoning-with-Retrieval Framework for Medical Multimodal Large Language Models","created":"2025-10-21","cited_by_count":2,"area":"lr"},{"id":"2510.20059","title":"Enhancing Reasoning Skills in Small Persian Medical Language Models Can Outperform Large-Scale Data Training","created":"2025-10-22","cited_by_count":2,"area":"lr"},{"id":"2510.25860","title":"Through the Judge's Eyes: Inferred Thinking Traces Improve Reliability of LLM Raters","created":"2025-10-29","cited_by_count":2,"area":"lr"},{"id":"2511.06380","title":"What Makes Reasoning Invalid: Echo Reflection Mitigation for Large Language Models","created":"2025-11-09","cited_by_count":2,"area":"lr"},{"id":"2511.08024","title":"Knowledge-Augmented Long-CoT Generation for Complex Biomolecular Reasoning","created":"2025-11-11","cited_by_count":2,"area":"lr"},{"id":"2601.03018","title":"Dementia-R1: Reinforced Pretraining and Reasoning from Unstructured Clinical Notes for Real-World Dementia Prognosis","created":"2026-01-06","cited_by_count":2,"area":"lr"},{"id":"2601.20649","title":"P2S: Probabilistic Process Supervision for General-Domain Reasoning Question Answering","created":"2026-01-28","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":"2604.17282","title":"MedPRMBench: A Fine-grained Benchmark for Process Reward Models in Medical Reasoning","created":"2026-04-19","cited_by_count":2,"area":"lr"},{"id":"2605.24902","title":"When Reasoning Hurts: Source-Aware Evaluation of Frontier LLMs for Clinical SOAP Note Generation","created":"2026-05-24","cited_by_count":2,"area":"lr"},{"id":"2504.02404","title":"AnesSuite: A Comprehensive Benchmark and Dataset Suite for Anesthesiology Reasoning in LLMs","created":"2025-04-03","cited_by_count":1,"area":"lr"},{"id":"2504.02885","title":"Med-R2: Perception and Reflection-driven Complex Reasoning for Medical Report Generation","created":"2025-04-02","cited_by_count":1,"area":"lr"}],"next_cursor":"100"}