{"total":125,"rows":[{"id":"2509.02547","title":"The Landscape of Agentic Reinforcement Learning for LLMs: A Survey","created":"2025-09-02","cited_by_count":205,"area":"agents"},{"id":"2506.23918","title":"Thinking with Images for Multimodal Reasoning: Foundations, Methods, and Future Frontiers","created":"2025-06-30","cited_by_count":199,"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":"2511.05271","title":"DeepEyesV2: Toward Agentic Multimodal Model","created":"2025-11-07","cited_by_count":125,"area":"agents"},{"id":"2507.06448","title":"Perception-Aware Policy Optimization for Multimodal Reasoning","created":"2025-07-08","cited_by_count":99,"area":"lr"},{"id":"2510.08531","title":"SpatialLadder: Progressive Training for Spatial Reasoning in Vision-Language Models","created":"2025-10-09","cited_by_count":90,"area":"lr"},{"id":"2511.21395","title":"Monet: Reasoning in Latent Visual Space Beyond Images and Language","created":"2025-11-26","cited_by_count":82,"area":"lr"},{"id":"2507.07999","title":"Traceable Evidence Enhanced Visual Grounded Reasoning: Evaluation and Methodology","created":"2025-07-10","cited_by_count":69,"area":null},{"id":"2510.18632","title":"Think with 3D: Geometric Imagination Grounded Spatial Reasoning from Limited Views","created":"2025-10-21","cited_by_count":65,"area":"lr"},{"id":"2511.20785","title":"LongVT: Incentivizing \"Thinking with Long Videos\" via Native Tool Calling","created":"2025-11-25","cited_by_count":61,"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":"2510.20579","title":"Open-o3-Video: Grounded Video Reasoning with Explicit Spatio-Temporal Evidence","created":"2025-10-23","cited_by_count":49,"area":"lr"},{"id":"2505.21457","title":"ACTIVE-o3: Empowering MLLMs with Active Perception via Pure Reinforcement Learning","created":"2025-05-27","cited_by_count":43,"area":null},{"id":"2510.09285","title":"Spotlight on Token Perception for Multimodal Reinforcement Learning","created":"2025-10-10","cited_by_count":39,"area":"lr"},{"id":"2511.11007","title":"VisMem: Latent Vision Memory Unlocks Potential of Vision-Language Models","created":"2025-11-14","cited_by_count":37,"area":"mllm"},{"id":"2511.22018","title":"MedEyes: Learning Dynamic Visual Focus for Medical Progressive Diagnosis","created":"2025-11-27","cited_by_count":32,"area":"lr"},{"id":"2511.19900","title":"Agent0-VL: Exploring Self-Evolving Agent for Tool-Integrated Vision-Language Reasoning","created":"2025-11-25","cited_by_count":31,"area":"lr"},{"id":"2510.12712","title":"Beyond Seeing: Evaluating Multimodal LLMs on Tool-Enabled Image Perception, Transformation, and Reasoning","created":"2025-10-14","cited_by_count":29,"area":"lr"},{"id":"2512.12623","title":"Reasoning Within the Mind: Dynamic Multimodal Interleaving in Latent Space","created":"2025-12-14","cited_by_count":28,"area":"lr"},{"id":"2509.24786","title":"LOVE-R1: Advancing Long Video Understanding with an Adaptive Zoom-in Mechanism via Multi-Step Reasoning","created":"2025-09-29","cited_by_count":27,"area":"lr"},{"id":"2508.06259","title":"SIFThinker: Spatially-Aware Image Focus for Visual Reasoning","created":"2025-08-08","cited_by_count":25,"area":"lr"},{"id":"2508.12109","title":"Simple o3: Towards Interleaved Vision-Language Reasoning","created":"2025-08-16","cited_by_count":24,"area":"lr"},{"id":"2601.13029","title":"Think3D: Thinking with Space for Spatial Reasoning","created":"2026-01-19","cited_by_count":24,"area":"lr"},{"id":"2602.13823","title":"Embed-RL: Reinforcement Learning for Reasoning-Driven Multimodal Embeddings","created":"2026-02-14","cited_by_count":24,"area":"lr"},{"id":"2511.19773","title":"Scaling Agentic Reinforcement Learning for Tool-Integrated Reasoning in VLMs","created":"2025-11-24","cited_by_count":17,"area":"lr"},{"id":"2509.26539","title":"Ferret-UI Lite: Lessons from Building Small On-Device GUI Agents","created":"2025-09-30","cited_by_count":16,"area":"agents"},{"id":"2512.03746","title":"Thinking with Programming Vision: Towards a Unified View for Thinking with Images","created":"2025-12-03","cited_by_count":15,"area":"lr"},{"id":"2601.12626","title":"Linear Mechanisms for Spatiotemporal Reasoning in Vision Language Models","created":"2026-01-18","cited_by_count":14,"area":"lr"},{"id":"2508.03100","title":"AVATAR: Reinforcement Learning to See, Hear, and Reason Over Video","created":"2025-08-05","cited_by_count":12,"area":"lr"},{"id":"2602.05847","title":"OmniVideo-R1: Reinforcing Audio-visual Reasoning with Query Intention and Modality Attention","created":"2026-02-05","cited_by_count":11,"area":"lr"},{"id":"2606.25319","title":"V-Zero: Answer-Label-Free On-Policy Distillation with Contrastive Evidence Gating for Fine-Grained Visual Reasoning","created":"2026-06-24","cited_by_count":11,"area":"lr"},{"id":"2509.10345","title":"Towards Understanding Visual Grounding in Visual Language Models","created":"2025-09-12","cited_by_count":10,"area":"mllm"},{"id":"2509.20912","title":"DeFacto: Counterfactual Thinking with Images for Enforcing Evidence-Grounded and Faithful Reasoning","created":"2025-09-25","cited_by_count":10,"area":"lr"},{"id":"2510.06871","title":"SaFeR-VLM: Toward Safety-aware Fine-grained Reasoning in Multimodal Models","created":"2025-10-08","cited_by_count":10,"area":"lr"},{"id":"2508.08189","title":"Reinforcement Learning for Large Model: A Survey","created":"2025-08-11","cited_by_count":9,"area":"deeprl"},{"id":"2509.21854","title":"Perception-Consistency Multimodal Large Language Models Reasoning via Caption-Regularized Policy Optimization","created":"2025-09-26","cited_by_count":9,"area":"lr"},{"id":"2603.22847","title":"Rethinking Token-Level Policy Optimization for Multimodal Chain-of-Thought","created":"2026-03-24","cited_by_count":9,"area":"lr"},{"id":"2603.28618","title":"Seeing with You: Perception-Reasoning Coevolution for Multimodal Reasoning","created":"2026-03-30","cited_by_count":9,"area":"lr"},{"id":"2508.04175","title":"AD-FM: Multimodal LLMs for Anomaly Detection via Multi-Stage Reasoning and Fine-Grained Reward Optimization","created":"2025-08-06","cited_by_count":8,"area":"lr"},{"id":"2510.20812","title":"Small Drafts, Big Verdict: Information-Intensive Visual Reasoning via Speculation","created":"2025-10-23","cited_by_count":8,"area":"lr"},{"id":"2511.22586","title":"Revisiting the Necessity of Lengthy Chain-of-Thought in Vision-centric Reasoning Generalization","created":"2025-11-27","cited_by_count":8,"area":"lr"},{"id":"2506.09557","title":"Evidence-Grounded Trustworthy Multimodal Reasoning and Evaluation Benchmark in Complex Urban Scenes","created":"2025-06-11","cited_by_count":7,"area":"lr"},{"id":"2509.22746","title":"Mixture-of-Visual-Thoughts: Exploring Context-Adaptive Reasoning Mode Selection for General Visual Reasoning","created":"2025-09-26","cited_by_count":7,"area":"lr"},{"id":"2602.02465","title":"MentisOculi: Revealing the Limits of Reasoning with Mental Imagery","created":"2026-02-02","cited_by_count":7,"area":"lr"},{"id":"2602.04094","title":"VideoBrain: Learning Adaptive Frame Sampling for Long Video Understanding","created":"2026-02-04","cited_by_count":7,"area":"mllm"},{"id":"2602.08346","title":"What, Whether and How? Unveiling Process Reward Models for Thinking with Images Reasoning","created":"2026-02-09","cited_by_count":7,"area":"lr"},{"id":"2603.19039","title":"TerraScope: Pixel-Grounded Visual Reasoning for Earth Observation","created":"2026-03-19","cited_by_count":7,"area":"lr"},{"id":"2604.06079","title":"Scientific Graphics Program Synthesis via Dual Self-Consistency Reinforcement Learning","created":"2026-04-07","cited_by_count":6,"area":"lr"},{"id":"2511.12908","title":"DeepSport: A Multimodal Large Language Model for Comprehensive Sports Video Reasoning via Agentic Reinforcement Learning","created":"2025-11-17","cited_by_count":5,"area":"lr"},{"id":"2512.05513","title":"Know-Show: Benchmarking Video-Language Models on Spatio-Temporal Grounded Reasoning","created":"2025-12-05","cited_by_count":5,"area":"lr"},{"id":"2512.23592","title":"Same or Not? Enhancing Visual Perception in Vision-Language Models","created":"2025-12-29","cited_by_count":5,"area":"mllm"},{"id":"2603.14117","title":"Improving Visual Reasoning with Iterative Evidence Refinement","created":"2026-03-14","cited_by_count":5,"area":"lr"},{"id":"2606.08708","title":"PRPO: Perception-Reinforced Policy Optimization via Token-Level Dynamic Advantage Reshaping","created":"2026-06-07","cited_by_count":5,"area":"lr"},{"id":"2510.04225","title":"Locate-Then-Examine: Grounded Region Reasoning Improves Detection of AI-Generated Images","created":"2025-10-05","cited_by_count":4,"area":"lr"},{"id":"2512.08889","title":"No Labels, No Problem: Training Visual Reasoners with Multimodal Verifiers","created":"2025-12-09","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":"2603.01607","title":"CARE: Towards Clinical Accountability in Multi-Modal Medical Reasoning with an Evidence-Grounded Agentic Framework","created":"2026-03-02","cited_by_count":4,"area":"lr"},{"id":"2603.14935","title":"Video-CoE: Reinforcing Video Event Prediction via Chain of Events","created":"2026-03-16","cited_by_count":4,"area":null},{"id":"2603.18856","title":"Motion-o: Trajectory-Grounded Video Reasoning","created":"2026-03-19","cited_by_count":4,"area":"lr"},{"id":"2604.12896","title":"Don't Show Pixels, Show Cues: Unlocking Visual Tool Reasoning in Language Models via Perception Programs","created":"2026-04-14","cited_by_count":4,"area":"lr"},{"id":"2606.22565","title":"Look Light, Think Heavy: What Multimodal Chain-of-Thought Reasoning Can and Cannot Do","created":"2026-06-21","cited_by_count":4,"area":"lr"},{"id":"2601.00215","title":"Disentangling Perception and Reasoning in Multimodal LLMs via Reward Design","created":"2026-01-01","cited_by_count":3,"area":"lr"},{"id":"2601.16400","title":"Clarify or Answer: Reinforcement Learning for Agentic VQA with Context Under-specification","created":"2026-01-23","cited_by_count":3,"area":"agents"},{"id":"2602.11909","title":"Echo: Towards Advanced Audio Comprehension via Audio-Interleaved Reasoning","created":"2026-02-12","cited_by_count":3,"area":"lr"},{"id":"2602.19058","title":"Do LLMs and VLMs Share Neurons for Inference? Evidence and Mechanisms of Cross-Modal Transfer","created":"2026-02-22","cited_by_count":3,"area":"mllm"},{"id":"2603.06032","title":"StruVis: Enhancing Reasoning-based Text-to-Image Generation via Thinking with Structured Vision","created":"2026-03-06","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":"2604.21079","title":"Foveated Reasoning: Stateful, Action-based Visual Focusing for Vision-Language Models","created":"2026-04-22","cited_by_count":3,"area":"lr"},{"id":"2605.19342","title":"Semantic-Enriched Latent Visual Reasoning","created":"2026-05-19","cited_by_count":3,"area":"lr"},{"id":"2605.30307","title":"Grounded 3D-Aware Spatial Vision-Language Modeling","created":"2026-05-28","cited_by_count":3,"area":"mllm"},{"id":"2607.01191","title":"Perceive-to-Reason: Decoupling Perception and Reasoning for Fine-Grained Visual Reasoning","created":"2026-07-01","cited_by_count":3,"area":"lr"},{"id":"2607.04423","title":"Transferability Between Understanding and Generation in Unified Multimodal Models","created":"2026-07-05","cited_by_count":3,"area":null},{"id":"2608.09682","title":"Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning","created":"2026-08-10","cited_by_count":3,"area":"lr"},{"id":"2508.14405","title":"CTA-Flux: Integrating Chinese Cultural Semantics into High-Quality English Text-to-Image Communities","created":"2025-08-20","cited_by_count":2,"area":null},{"id":"2511.18305","title":"DiVE-k: Differential Visual Reasoning for Fine-grained Image Recognition","created":"2025-11-23","cited_by_count":2,"area":"lr"},{"id":"2512.15940","title":"R4: Retrieval-Augmented Reasoning for Vision-Language Models in 4D Spatio-Temporal Space","created":"2025-12-17","cited_by_count":2,"area":"lr"},{"id":"2602.18763","title":"TAG: Thinking with Action Unit Grounding for Facial Expression Recognition","created":"2026-02-21","cited_by_count":2,"area":"lr"},{"id":"2605.07019","title":"LensVLM: Selective Context Expansion for Compressed Visual Representation of Text","created":"2026-05-07","cited_by_count":2,"area":"mllm"},{"id":"2606.11740","title":"UniReason-Med: A Shared Grounded Reasoning Interface for 2D-to-3D Transfer in Medical VQA","created":"2026-06-10","cited_by_count":2,"area":null},{"id":"2606.16122","title":"Thinking with Visual Grounding","created":"2026-06-15","cited_by_count":2,"area":"lr"},{"id":"2607.00881","title":"OmniView-Space: Reinforcing Spatial Reasoning via Multi-Perspective Spatial Mapping","created":"2026-07-01","cited_by_count":2,"area":"lr"},{"id":"2510.03727","title":"Bridging the Gap Between Multimodal Foundation Models and World Models","created":"2025-10-04","cited_by_count":1,"area":"wm"},{"id":"2512.06726","title":"The Role of Entropy in Visual Grounding: Analysis and Optimization","created":"2025-12-07","cited_by_count":1,"area":"mllm"},{"id":"2601.06498","title":"Spec-o3: A Tool-Augmented Vision-Language Agent for Rare Celestial Object Candidate Vetting via Automated Spectral Inspection","created":"2026-01-10","cited_by_count":1,"area":"agents"},{"id":"2602.05829","title":"Weaver: End-to-End Agentic System Training for Video Interleaved Reasoning","created":"2026-02-05","cited_by_count":1,"area":"lr"},{"id":"2602.08211","title":"Chain-of-Caption: Training-free improvement of multimodal large language model on referring expression comprehension","created":"2026-02-09","cited_by_count":1,"area":"mllm"},{"id":"2602.21497","title":"See It, Say It, Sorted: An Iterative Training-Free Framework for Visually-Grounded Multimodal Reasoning in LVLMs","created":"2026-02-25","cited_by_count":1,"area":"lr"},{"id":"2603.07394","title":"AQuA: Toward Strategic Response Generation for Ambiguous Visual Questions","created":"2026-03-08","cited_by_count":1,"area":"mllm"},{"id":"2603.13054","title":"Topo-R1: Detecting Topological Anomalies via Vision-Language Models","created":"2026-03-13","cited_by_count":1,"area":"mllm"},{"id":"2604.04733","title":"Discovering Failure Modes in Vision-Language Models using RL","created":"2026-04-06","cited_by_count":1,"area":"lr"},{"id":"2604.11025","title":"Test-time Scaling over Perception: Resolving the Grounding Paradox in Thinking with Images","created":"2026-04-13","cited_by_count":1,"area":"lr"},{"id":"2606.07436","title":"Skill-3D: Evolving Scene-Aware Skills for Agentic 3D Spatial Reasoning","created":"2026-06-05","cited_by_count":1,"area":"lr"},{"id":"2606.13156","title":"Iterative Visual Thinking and the Self-Correction Mirage in VLM Grounding","created":"2026-06-11","cited_by_count":1,"area":"lr"},{"id":"2606.24292","title":"ActiveScope: Actively Seeking and Correcting Perception for MLLMs","created":"2026-06-23","cited_by_count":1,"area":"mllm"},{"id":"2607.05716","title":"Scene Graph Thinking: Reinforcing Structured Visual Reasoning for Multimodal Large Language Models","created":"2026-07-07","cited_by_count":1,"area":"lr"},{"id":"2608.08907","title":"ToolVision: Learning When and How to Use Visual Tools with Capability-Aligned Supervision","created":"2026-08-09","cited_by_count":1,"area":null},{"id":"2506.04562","title":"Handle-based Mesh Deformation Guided By Vision Language Model","created":"2025-06-05","cited_by_count":0,"area":"mllm"},{"id":"2509.25811","title":"Logo-VGR: Visual Grounded Reasoning for Open-world Logo Recognition","created":"2025-09-30","cited_by_count":0,"area":"lr"},{"id":"2511.08172","title":"An Efficient Training Pipeline for Reasoning Graphical User Interface Agents","created":"2025-11-11","cited_by_count":0,"area":"lr"},{"id":"2601.11425","title":"PubMed-OCR: PMC Open Access OCR Annotations","created":"2026-01-16","cited_by_count":0,"area":null}],"next_cursor":"100"}