{"total":62,"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":"2505.21374","title":"Video-Holmes: Can MLLM Think Like Holmes for Complex Video Reasoning?","created":"2025-05-27","cited_by_count":118,"area":"lr"},{"id":"2505.12434","title":"VideoRFT: Incentivizing Video Reasoning Capability in MLLMs via Reinforced Fine-Tuning","created":"2025-05-18","cited_by_count":93,"area":"lr"},{"id":"2505.04921","title":"Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Models","created":"2025-05-08","cited_by_count":90,"area":"lr"},{"id":"2506.07464","title":"DeepVideo-R1: Video Reinforcement Fine-Tuning via Difficulty-aware Regressive GRPO","created":"2025-06-09","cited_by_count":61,"area":"lr"},{"id":"2506.01300","title":"ReAgent-V: A Reward-Driven Multi-Agent Framework for Video Understanding","created":"2025-06-02","cited_by_count":50,"area":"agents"},{"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":"2504.21277","title":"Reinforced MLLM: A Survey on RL-Based Reasoning in Multimodal Large Language Models","created":"2025-04-30","cited_by_count":44,"area":"lr"},{"id":"2507.21848","title":"EDGE-GRPO: Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity","created":"2025-07-29","cited_by_count":41,"area":"lr"},{"id":"2509.16679","title":"Reinforcement Learning Meets Large Language Models: A Survey of Advancements and Applications Across the LLM Lifecycle","created":"2025-09-20","cited_by_count":35,"area":null},{"id":"2506.09839","title":"OctoNav: Towards Generalist Embodied Navigation","created":"2025-06-11","cited_by_count":34,"area":"lr"},{"id":"2507.06485","title":"Video-RTS: Rethinking Reinforcement Learning and Test-Time Scaling for Efficient and Enhanced Video Reasoning","created":"2025-07-09","cited_by_count":33,"area":"lr"},{"id":"2506.10821","title":"VideoExplorer: Think With Videos For Agentic Long-Video Understanding","created":"2025-06-12","cited_by_count":29,"area":null},{"id":"2505.19877","title":"Vad-R1: Towards Video Anomaly Reasoning via Perception-to-Cognition Chain-of-Thought","created":"2025-05-26","cited_by_count":24,"area":"lr"},{"id":"2508.06206","title":"Affordance-R1: Reinforcement Learning for Generalizable Affordance Reasoning in Multimodal Large Language Model","created":"2025-08-08","cited_by_count":23,"area":"lr"},{"id":"2601.05175","title":"VideoAuto-R1: Video Auto Reasoning via Thinking Once, Answering Twice","created":"2026-01-08","cited_by_count":21,"area":"lr"},{"id":"2512.04540","title":"VideoMem: Enhancing Ultra-Long Video Understanding via Adaptive Memory Management","created":"2025-12-04","cited_by_count":19,"area":"mllm"},{"id":"2506.01371","title":"SVQA-R1: Reinforcing Spatial Reasoning in MLLMs via View-Consistent Reward Optimization","created":"2025-06-02","cited_by_count":16,"area":"lr"},{"id":"2510.06077","title":"When Thinking Drifts: Evidential Grounding for Robust Video Reasoning","created":"2025-10-07","cited_by_count":16,"area":null},{"id":"2509.18056","title":"TempSamp-R1: Effective Temporal Sampling with Reinforcement Fine-Tuning for Video LLMs","created":"2025-09-22","cited_by_count":15,"area":"mllm"},{"id":"2505.02686","title":"Sailing by the Stars: A Survey on Reward Models and Learning Strategies for Learning from Rewards","created":"2025-05-05","cited_by_count":14,"area":"lr"},{"id":"2505.18536","title":"Reinforcement Fine-Tuning Powers Reasoning Capability of Multimodal Large Language Models","created":"2025-05-24","cited_by_count":14,"area":"lr"},{"id":"2506.08817","title":"Video-CoT: A Comprehensive Dataset for Spatiotemporal Understanding of Videos Based on Chain-of-Thought","created":"2025-06-10","cited_by_count":14,"area":"lr"},{"id":"2506.09079","title":"VidBridge-R1: Bridging QA and Captioning for RL-based Video Understanding Models with Intermediate Proxy Tasks","created":"2025-06-10","cited_by_count":14,"area":"mllm"},{"id":"2505.20715","title":"MUSEG: Reinforcing Video Temporal Understanding via Timestamp-Aware Multi-Segment Grounding","created":"2025-05-27","cited_by_count":12,"area":"mllm"},{"id":"2602.15329","title":"EventMemAgent: Hierarchical Event-Centric Memory for Online Video Understanding with Adaptive Tool Use","created":"2026-02-17","cited_by_count":12,"area":null},{"id":"2507.00748","title":"Improving the Reasoning of Multi-Image Grounding in MLLMs via Reinforcement Learning","created":"2025-07-01","cited_by_count":11,"area":"lr"},{"id":"2512.18671","title":"SmartSight: Mitigating Hallucination in Video-LLMs Without Compromising Video Understanding via Temporal Attention Collapse","created":"2025-12-21","cited_by_count":9,"area":null},{"id":"2506.07971","title":"CyberV: Cybernetics for Test-time Scaling in Video Understanding","created":"2025-06-09","cited_by_count":8,"area":"lr"},{"id":"2509.21113","title":"MOSS-ChatV: Reinforcement Learning with Process Reasoning Reward for Video Temporal Reasoning","created":"2025-09-25","cited_by_count":8,"area":"lr"},{"id":"2510.05034","title":"Video-LMM Post-Training: A Deep Dive into Video Reasoning with Large Multimodal Models","created":"2025-10-06","cited_by_count":8,"area":"lr"},{"id":"2511.11113","title":"VIDEOP2R: Video Understanding from Perception to Reasoning","created":"2025-11-14","cited_by_count":8,"area":"lr"},{"id":"2512.03963","title":"TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning","created":"2025-12-03","cited_by_count":8,"area":"mllm"},{"id":"2511.13054","title":"ViSS-R1: Self-Supervised Reinforcement Video Reasoning","created":"2025-11-17","cited_by_count":6,"area":"lr"},{"id":"2510.15440","title":"Select Less, Reason More: Prioritizing Evidence Purity for Video Reasoning","created":"2025-10-17","cited_by_count":5,"area":"lr"},{"id":"2510.26113","title":"EgoExo-Con: Exploring View-Invariant Video Temporal Understanding","created":"2025-10-30","cited_by_count":5,"area":null},{"id":"2604.01600","title":"MM-ReCoder: Advancing Chart-to-Code Generation with Reinforcement Learning and Self-Correction","created":"2026-04-02","cited_by_count":5,"area":"mllm"},{"id":"2604.00267","title":"Omni-MMSI: Toward Identity-attributed Social Interaction Understanding","created":"2026-03-31","cited_by_count":4,"area":null},{"id":"2601.00887","title":"VideoCuRL: Video Curriculum Reinforcement Learning with Orthogonal Difficulty Decomposition","created":"2025-12-31","cited_by_count":3,"area":"lr"},{"id":"2604.16243","title":"Find, Fix, Reason: Context Repair for Video Reasoning","created":"2026-04-17","cited_by_count":3,"area":"mllm"},{"id":"2510.17045","title":"Video Reasoning without Training","created":"2025-10-19","cited_by_count":2,"area":"lr"},{"id":"2603.17693","title":"Learning Transferable Temporal Primitives for Video Reasoning via Synthetic Videos","created":"2026-03-18","cited_by_count":2,"area":"lr"},{"id":"2604.04379","title":"Reinforce to Learn, Elect to Reason: A Dual Paradigm for Video Reasoning","created":"2026-04-06","cited_by_count":2,"area":"mllm"},{"id":"2605.01324","title":"Beyond Perceptual Shortcuts: Causal-Inspired Debiasing Optimization for Generalizable Video Reasoning in Lightweight MLLMs","created":"2026-05-02","cited_by_count":2,"area":"lr"},{"id":"2511.12365","title":"Constructing and Interpreting Digital Twin Representations for Visual Reasoning via Reinforcement Learning","created":"2025-11-15","cited_by_count":1,"area":"lr"},{"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":"2603.18656","title":"Balanced Thinking: Improving Chain of Thought Training in Vision Language Models","created":"2026-03-19","cited_by_count":1,"area":"lr"},{"id":"2604.20473","title":"Video-ToC: Video Tree-of-Cue Reasoning","created":"2026-04-22","cited_by_count":1,"area":"lr"},{"id":"2606.18441","title":"Reasoning as Intersection: Consensus-Frame Alignment for Visual Focus in Video-MLLMs","created":"2026-06-16","cited_by_count":1,"area":"lr"},{"id":"2608.07417","title":"I Seek You in Videos: Identity-Conditioned Queries for Person-Centric Video Reasoning","created":"2026-08-07","cited_by_count":1,"area":"lr"},{"id":"2508.12387","title":"ReaLM: Reflection-Enhanced Autonomous Reasoning with Small Language Models","created":"2025-08-17","cited_by_count":0,"area":"lr"},{"id":"2511.18463","title":"Decoupling Perception from Reasoning for Hallucination-Resistant Video Understanding","created":"2025-11-23","cited_by_count":0,"area":"lr"},{"id":"2604.00696","title":"TTA-Vid: Generalized Test-Time Adaptation for Video Reasoning","created":"2026-04-01","cited_by_count":0,"area":"lr"},{"id":"2604.04415","title":"STEER: Structured Event Evidence for Video Reasoning via Multi-Objective Reinforcement Learning","created":"2026-04-06","cited_by_count":0,"area":"lr"},{"id":"2605.04733","title":"Reward-Decomposed Reinforcement Learning for Immersive Video Role-Playing","created":"2026-05-06","cited_by_count":0,"area":"lr"},{"id":"2605.10445","title":"Uni-Synergy: Bridging Understanding and Generation for Personalized Reasoning via Co-operative Reinforcement Learning","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.23216","title":"CaST-Bench: Benchmarking Causal Chain-Grounded Spatio-Temporal Reasoning for Video Question Answering","created":"2026-05-22","cited_by_count":0,"area":"lr"},{"id":"2606.11209","title":"ProcessThinker: Enhancing Multi-modal Large Language Models Reasoning via Rollout-based Process Reward","created":"2026-04-23","cited_by_count":0,"area":"lr"},{"id":"2606.19927","title":"CARE: Competence-Aware Reward Shaping for Adaptive Reasoning Length in Video-MLLMs","created":"2026-06-18","cited_by_count":0,"area":"lr"},{"id":"2606.22870","title":"VideoLatent: Video-Language Learning via Latent Self-Forcing","created":"2026-06-22","cited_by_count":0,"area":"lr"},{"id":"2608.26684","title":"Reason in the Words You Speak: Idiolectal Paraphrasing Off-Policy Traces for Reasoning Distillation in VideoLLMs","created":"2026-08-27","cited_by_count":0,"area":"lr"},{"id":"2610.18535","title":"Meta-Video: Efficient Standardized Evaluation for Video Understanding","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}