{"total":313,"rows":[{"id":"2603.24472","title":"Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?","created":"2026-03-25","cited_by_count":103,"area":"lr"},{"id":"2605.02881","title":"MolmoAct2: Action Reasoning Models for Real-world Deployment","created":"2026-05-04","cited_by_count":50,"area":"lr"},{"id":"2602.02994","title":"Video-OPD: Efficient Post-Training of Multimodal Large Language Models for Temporal Video Grounding via On-Policy Distillation","created":"2026-02-03","cited_by_count":36,"area":"lr"},{"id":"2602.02185","title":"Vision-DeepResearch Benchmark: Rethinking Visual and Textual Search for Multimodal Large Language Models","created":"2026-02-02","cited_by_count":34,"area":"lr"},{"id":"2604.13010","title":"Lightning OPD: Efficient Post-Training for Large Reasoning Models with Offline On-Policy Distillation","created":"2026-04-14","cited_by_count":33,"area":"lr"},{"id":"2604.15267","title":"CoopEval: Benchmarking Cooperation-Sustaining Mechanisms and LLM Agents in Social Dilemmas","created":"2026-04-16","cited_by_count":16,"area":"lr"},{"id":"2605.12400","title":"OGLS-SD: On-Policy Self-Distillation with Outcome-Guided Logit Steering for LLM Reasoning","created":"2026-05-12","cited_by_count":16,"area":"lr"},{"id":"2603.06638","title":"HEARTS: Benchmarking LLM Reasoning on Health Time Series","created":"2026-02-25","cited_by_count":11,"area":"lr"},{"id":"2604.04917","title":"Vero: An Open RL Recipe for General Visual Reasoning","created":"2026-04-06","cited_by_count":11,"area":"lr"},{"id":"2606.00206","title":"Quantized Reasoning Models Think They Need to Think Longer, but They Do Not","created":"2026-05-29","cited_by_count":10,"area":"lr"},{"id":"2602.03164","title":"MemCast: Memory-Driven Time Series Forecasting with Experience-Conditioned Reasoning","created":"2026-02-03","cited_by_count":9,"area":"lr"},{"id":"2602.19895","title":"DSDR: Dual-Scale Diversity Regularization for Exploration in LLM Reasoning","created":"2026-02-23","cited_by_count":9,"area":"lr"},{"id":"2604.04902","title":"Are Latent Reasoning Models Easily Interpretable?","created":"2026-04-06","cited_by_count":9,"area":"lr"},{"id":"2605.15458","title":"Video Models Can Reason with Verifiable Rewards","created":"2026-05-14","cited_by_count":9,"area":"lr"},{"id":"2602.00173","title":"Learning Robust Reasoning through Guided Adversarial Self-Play","created":"2026-01-30","cited_by_count":8,"area":"lr"},{"id":"2603.03205","title":"Learning When to Act or Refuse: Guarding Agentic Reasoning Models for Safe Multi-Step Tool Use","created":"2026-03-03","cited_by_count":8,"area":"lr"},{"id":"2603.07539","title":"MAWARITH: A Dataset and Benchmark for Legal Inheritance Reasoning with LLMs","created":"2026-03-08","cited_by_count":8,"area":"lr"},{"id":"2603.07915","title":"Ares: Adaptive Reasoning Effort Selection for Efficient LLM Agents","created":"2026-03-09","cited_by_count":8,"area":"lr"},{"id":"2603.26639","title":"Make Geometry Matter for Spatial Reasoning","created":"2026-03-27","cited_by_count":8,"area":"lr"},{"id":"2603.28590","title":"MonitorBench: A Comprehensive Benchmark for Chain-of-Thought Monitorability in Large Language Models","created":"2026-03-30","cited_by_count":8,"area":"lr"},{"id":"2606.15231","title":"Visual-Seeker: Towards Visual-Native Multimodal Agentic Search via Active Visual Reasoning","created":"2026-06-13","cited_by_count":8,"area":"lr"},{"id":"2602.09463","title":"SpotAgent: Grounding Visual Geo-localization in Large Vision-Language Models through Agentic Reasoning","created":"2026-02-10","cited_by_count":7,"area":"lr"},{"id":"2603.12264","title":"GRADE: Benchmarking Discipline-Informed Reasoning in Image Editing","created":"2026-03-12","cited_by_count":7,"area":"lr"},{"id":"2604.04503","title":"Memory Intelligence Agent","created":"2026-04-06","cited_by_count":7,"area":"lr"},{"id":"2604.08299","title":"SeLaR: Selective Latent Reasoning in Large Language Models","created":"2026-04-09","cited_by_count":7,"area":"lr"},{"id":"2606.01476","title":"OmniOPD: Logit-Free On-Policy Distillation via Speculative Verification","created":"2026-05-31","cited_by_count":7,"area":"lr"},{"id":"2606.09669","title":"SpatialWorld: Benchmarking Interactive Spatial Reasoning of Multimodal Agents in Real-World Tasks","created":"2026-06-08","cited_by_count":7,"area":"lr"},{"id":"2601.02918","title":"Zoom-IQA: Image Quality Assessment with Reliable Region-Aware Reasoning","created":"2026-01-06","cited_by_count":6,"area":"lr"},{"id":"2602.09850","title":"Towards Explainable Industrial Anomaly Detection via Knowledge-Guided Latent Reasoning","created":"2026-02-10","cited_by_count":6,"area":"lr"},{"id":"2604.16060","title":"Chain-of-Thought Degrades Visual Spatial Reasoning Capabilities of Multimodal LLMs","created":"2026-04-17","cited_by_count":6,"area":"lr"},{"id":"2604.16256","title":"Do Vision-Language Models Truly Perform Vision Reasoning? A Rigorous Study of the Modality Gap","created":"2026-04-17","cited_by_count":6,"area":"lr"},{"id":"2606.02031","title":"OpenWebRL: Demystifying Online Multi-turn Reinforcement Learning for Visual Web Agents","created":"2026-06-01","cited_by_count":6,"area":"lr"},{"id":"2606.15079","title":"Ling and Ring 2.6 Technical Report: Efficient and Instant Agentic Intelligence at Trillion-Parameter Scale","created":"2026-06-13","cited_by_count":6,"area":"lr"},{"id":"2602.00642","title":"LegalOne: A Family of Foundation Models for Reliable Legal Reasoning","created":"2026-01-31","cited_by_count":5,"area":"lr"},{"id":"2604.04443","title":"DeonticBench: A Benchmark for Reasoning over Rules","created":"2026-04-06","cited_by_count":5,"area":"lr"},{"id":"2605.18549","title":"Monitoring the Internal Monologue: Probe Trajectories Reveal Reasoning Dynamics","created":"2026-05-18","cited_by_count":5,"area":"lr"},{"id":"2605.30002","title":"KairosAgent: Agentic Time Series Forecasting with Fused Semantic Reasoning","created":"2026-05-28","cited_by_count":5,"area":"lr"},{"id":"2606.15378","title":"Rethinking the Role of Efficient Attention in Hybrid Architectures","created":"2026-06-13","cited_by_count":5,"area":"lr"},{"id":"2606.17682","title":"From Trainee to Trainer: LLM-Designed Training Environment for RL with Multi-Agent Reasoning","created":"2026-06-16","cited_by_count":5,"area":"lr"},{"id":"2607.02927","title":"VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning","created":"2026-07-03","cited_by_count":5,"area":"lr"},{"id":"2607.28449","title":"Lightning OPD 2.0: Mitigating Style Bias in Cross-Teacher On-Policy Distillation for Large Reasoning Models","created":"2026-07-30","cited_by_count":5,"area":"lr"},{"id":"2608.01078","title":"Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization","created":"2026-08-02","cited_by_count":5,"area":"lr"},{"id":"2512.19554","title":"CARE What Fails: Contrastive Anchored-REflection for Verifiable Multimodal Reasoning","created":"2025-12-22","cited_by_count":4,"area":"lr"},{"id":"2512.20822","title":"MediEval: A Unified Medical Benchmark for Patient-Contextual and Knowledge-Grounded Reasoning in LLMs","created":"2025-12-23","cited_by_count":4,"area":"lr"},{"id":"2601.22323","title":"Models Under SCOPE: Scalable and Controllable Routing via Pre-hoc Reasoning","created":"2026-01-29","cited_by_count":4,"area":"lr"},{"id":"2602.02561","title":"MathlibLemma: Folklore Lemma Generation and Benchmark for Formal Mathematics","created":"2026-01-30","cited_by_count":4,"area":"lr"},{"id":"2602.18645","title":"Adaptive Time Series Reasoning via Segment Selection","created":"2026-02-20","cited_by_count":4,"area":"lr"},{"id":"2602.21015","title":"From Perception to Action: An Interactive Benchmark for Vision Reasoning","created":"2026-02-24","cited_by_count":4,"area":"lr"},{"id":"2603.01692","title":"Reasoning as Gradient: Scaling MLE Agents Beyond Tree Search","created":"2026-03-02","cited_by_count":4,"area":"lr"},{"id":"2603.14326","title":"ECG-Reasoning-Benchmark: A Benchmark for Evaluating Clinical Reasoning Capabilities in ECG Interpretation","created":"2026-03-15","cited_by_count":4,"area":"lr"},{"id":"2603.23607","title":"Reasoning models do not yet follow their reasoning in autonomous driving: The KITScenes LongTail Dataset","created":"2026-03-24","cited_by_count":4,"area":"lr"},{"id":"2604.16383","title":"Same Verdict, Different Reasons: LLM-as-a-Judge and Clinician Disagreement on Medical Chatbot Completeness","created":"2026-03-26","cited_by_count":4,"area":"lr"},{"id":"2605.02910","title":"CreativityBench: Evaluating Agent Creative Reasoning via Affordance-Based Tool Repurposing","created":"2026-04-06","cited_by_count":4,"area":"lr"},{"id":"2605.05997","title":"4DThinker: Thinking with 4D Imagery for Dynamic Spatial Understanding","created":"2026-05-07","cited_by_count":4,"area":"lr"},{"id":"2605.09063","title":"Soohak: A Mathematician-Curated Benchmark for Evaluating Research-level Math Capabilities of LLMs","created":"2026-05-09","cited_by_count":4,"area":"lr"},{"id":"2605.12374","title":"Fill the GAP: A Granular Alignment Paradigm for Visual Reasoning in Multimodal Large Language Models","created":"2026-05-12","cited_by_count":4,"area":"lr"},{"id":"2605.18431","title":"Seeing Together: Multi-Robot Cooperative Egocentric Spatial Reasoning with Multimodal Large Language Models","created":"2026-05-18","cited_by_count":4,"area":"lr"},{"id":"2605.19952","title":"Rethinking How to Remember: Beyond Atomic Facts in Lifelong LLM Agent Memory","created":"2026-05-19","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":"2606.08464","title":"TVI-CoT: Text-Visual Interleaved Chain-of-Thought Reasoning for Multimodal Understanding","created":"2026-06-07","cited_by_count":4,"area":"lr"},{"id":"2606.15200","title":"Keep It in Mind: User Centric Continual Spatial Intelligence Reasoning in Egocentric Video Streams","created":"2026-06-13","cited_by_count":4,"area":"lr"},{"id":"2608.20492","title":"Annotations as Rollouts: Efficient and Scalable Reinforcement Learning for Video MLLMs","created":"2026-08-20","cited_by_count":4,"area":"lr"},{"id":"2601.21225","title":"MGSM-Pro: A Simple Strategy for Robust Multilingual Mathematical Reasoning Evaluation","created":"2026-01-29","cited_by_count":3,"area":"lr"},{"id":"2602.02676","title":"AdaptMMBench: Benchmarking Adaptive Multimodal Reasoning for Mode Selection and Reasoning Process","created":"2026-02-02","cited_by_count":3,"area":"lr"},{"id":"2602.03485","title":"Self-Verification Dilemma: Experience-Driven Suppression of Overused Checking in LLM Reasoning","created":"2026-02-03","cited_by_count":3,"area":"lr"},{"id":"2602.22284","title":"BrepCoder: A Unified Multimodal Large Language Model for Multi-task B-rep Reasoning","created":"2026-02-25","cited_by_count":3,"area":"lr"},{"id":"2602.23276","title":"CXReasonAgent: Evidence-Grounded Diagnostic Reasoning Agent for Chest X-rays","created":"2026-02-26","cited_by_count":3,"area":"lr"},{"id":"2603.13800","title":"Beyond Medical Diagnostics: How Medical Multimodal Large Language Models Think in Space","created":"2026-03-14","cited_by_count":3,"area":"lr"},{"id":"2603.16506","title":"VIEW2SPACE: Studying Multi-View Visual Reasoning from Sparse Observations","created":"2026-03-17","cited_by_count":3,"area":"lr"},{"id":"2603.27201","title":"Understanding and Mitigating Hallucinations in Multimodal Chain-of-Thought Models","created":"2026-03-28","cited_by_count":3,"area":"lr"},{"id":"2603.28730","title":"SOLE-R1: Video-Language Reasoning as the Sole Reward for On-Robot Reinforcement Learning","created":"2026-03-30","cited_by_count":3,"area":"lr"},{"id":"2605.08477","title":"Do Agents Need to Plan Step-by-Step? Rethinking Planning Horizon in Data-Centric Tool Calling","created":"2026-05-08","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":"2605.12163","title":"Self-Consistent Latent Reasoning: Long Latent Sequence Reasoning for Vision-Language Model","created":"2026-05-12","cited_by_count":3,"area":"lr"},{"id":"2605.12227","title":"A Recipe for Long-Context Reasoning in Large Language Models via On-Policy Optimization and Distillation","created":"2026-05-12","cited_by_count":3,"area":"lr"},{"id":"2605.15257","title":"Training on Documents About Monitoring Leads to CoT Obfuscation","created":"2026-05-14","cited_by_count":3,"area":"lr"},{"id":"2605.18162","title":"Self-Evolving Spatial Reasoning in Vision Language Models via Geometric Logic Consistency","created":"2026-05-18","cited_by_count":3,"area":"lr"},{"id":"2606.16222","title":"Latent Thought Flow: Efficient Latent Reasoning in Large Language Models","created":"2026-06-15","cited_by_count":3,"area":"lr"},{"id":"2606.17412","title":"Enhancing Pathological VLMs with Cross-scale Reasoning","created":"2026-06-16","cited_by_count":3,"area":"lr"},{"id":"2606.23557","title":"Dense Reward for Multi-View 3D Reasoning with Global Maps and Local Views","created":"2026-06-22","cited_by_count":3,"area":"lr"},{"id":"2606.25325","title":"Omni-Perception Policy Optimization for Multimodal Emotion Reasoning","created":"2026-06-24","cited_by_count":3,"area":"lr"},{"id":"2606.31986","title":"CoLT: Teaching Multi-Modal Models to Think with Chain of Latent Thoughts","created":"2026-06-30","cited_by_count":3,"area":"lr"},{"id":"2601.17593","title":"From Chains to DAGs: Probing the Graph Structure of Reasoning in LLMs","created":"2026-01-24","cited_by_count":2,"area":"lr"},{"id":"2602.03468","title":"IntentRL: Training Proactive User-intent Agents for Open-ended Deep Research via Reinforcement Learning","created":"2026-02-03","cited_by_count":2,"area":"lr"},{"id":"2602.11980","title":"Spatial Chain-of-Thought: Bridging Understanding and Generation Models for Spatial Reasoning Generation","created":"2026-02-12","cited_by_count":2,"area":"lr"},{"id":"2602.14189","title":"Knowing When Not to Answer: Abstention-Aware Scientific Reasoning","created":"2026-02-15","cited_by_count":2,"area":"lr"},{"id":"2602.14200","title":"TS-Haystack: A Multi-Task Retrieval Benchmark for Long-Context Time-Series Reasoning","created":"2026-02-15","cited_by_count":2,"area":"lr"},{"id":"2603.00409","title":"SSR: Pushing the Limit of Spatial Intelligence with Structured Scene Reasoning","created":"2026-02-28","cited_by_count":2,"area":"lr"},{"id":"2603.03790","title":"T2S-Bench & Structure-of-Thought: Benchmarking and Prompting Comprehensive Text-to-Structure Reasoning","created":"2026-03-04","cited_by_count":2,"area":"lr"},{"id":"2603.12430","title":"Surg-R1: A Hierarchical Reasoning Foundation Model for Scalable and Interpretable Surgical Decision Support with Multi-Center Clinical Validation","created":"2026-03-12","cited_by_count":2,"area":"lr"},{"id":"2603.17368","title":"Towards Safer Large Reasoning Models by Promoting Safety Decision-Making before Chain-of-Thought Generation","created":"2026-03-18","cited_by_count":2,"area":"lr"},{"id":"2603.19539","title":"FDARxBench: Benchmarking Regulatory and Clinical Reasoning on FDA Generic Drug Assessment","created":"2026-03-20","cited_by_count":2,"area":"lr"},{"id":"2603.20209","title":"Children's Intelligence Tests Pose Challenges for MLLMs? KidGym: A 2D Grid-Based Reasoning Benchmark for MLLMs","created":"2026-03-02","cited_by_count":2,"area":"lr"},{"id":"2603.25412","title":"Beyond Content Safety: Real-Time Monitoring for Reasoning Vulnerabilities in Large Language Models","created":"2026-03-26","cited_by_count":2,"area":"lr"},{"id":"2603.25823","title":"ViGoR-Bench: How Far Are Visual Generative Models From Zero-Shot Visual Reasoners?","created":"2026-03-26","cited_by_count":2,"area":"lr"},{"id":"2603.29085","title":"PAR$^2$-RAG: Planned Active Retrieval and Reasoning for Multi-Hop Question Answering","created":"2026-03-30","cited_by_count":2,"area":"lr"},{"id":"2604.01634","title":"CRIT: Graph-Based Automatic Data Synthesis to Enhance Cross-Modal Multi-Hop Reasoning","created":"2026-04-02","cited_by_count":2,"area":"lr"},{"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":"2604.08983","title":"AssemLM: A Spatial Reasoning Multimodal Large Language Model for Robotic Assembly","created":"2026-04-10","cited_by_count":2,"area":"lr"},{"id":"2605.00969","title":"MedMosaic: A Challenging Large Scale Benchmark of Diverse Medical Audio","created":"2026-05-01","cited_by_count":2,"area":"lr"}],"next_cursor":"100"}