{"total":97,"rows":[{"id":"2503.07365","title":"MM-Eureka: Exploring the Frontiers of Multimodal Reasoning with Rule-based Reinforcement Learning","created":"2025-03-10","cited_by_count":303,"area":"lr"},{"id":"2506.15841","title":"MEM1: Learning to Synergize Memory and Reasoning for Efficient Long-Horizon Agents","created":"2025-06-18","cited_by_count":238,"area":"lr"},{"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":"2508.05629","title":"On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification","created":"2025-08-07","cited_by_count":127,"area":"lr"},{"id":"2503.02318","title":"Audio-Reasoner: Improving Reasoning Capability in Large Audio Language Models","created":"2025-03-04","cited_by_count":95,"area":"lr"},{"id":"2505.18822","title":"AdaCtrl: Towards Adaptive and Controllable Reasoning via Difficulty-Aware Budgeting","created":"2025-05-24","cited_by_count":50,"area":"lr"},{"id":"2505.22334","title":"Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start","created":"2025-05-28","cited_by_count":41,"area":"lr"},{"id":"2410.16162","title":"Sparkle: Mastering Basic Spatial Capabilities in Vision Language Models Elicits Generalization to Spatial Reasoning","created":"2024-10-21","cited_by_count":34,"area":"lr"},{"id":"2601.13029","title":"Think3D: Thinking with Space for Spatial Reasoning","created":"2026-01-19","cited_by_count":24,"area":"lr"},{"id":"2508.21048","title":"Veritas: Generalizable Deepfake Detection via Pattern-Aware Reasoning","created":"2025-08-28","cited_by_count":23,"area":"lr"},{"id":"2411.18145","title":"CHOICE: Benchmarking the Remote Sensing Capabilities of Large Vision-Language Models","created":"2024-11-27","cited_by_count":22,"area":"lr"},{"id":"2501.18533","title":"Rethinking Bottlenecks in Safety Fine-Tuning of Vision Language Models","created":"2025-01-30","cited_by_count":21,"area":"lr"},{"id":"2506.12364","title":"MM-R5: MultiModal Reasoning-Enhanced ReRanker via Reinforcement Learning for Document Retrieval","created":"2025-06-14","cited_by_count":21,"area":"lr"},{"id":"2509.25502","title":"Seeing Before Reasoning: A Unified Framework for Generalizable and Explainable Fake Image Detection","created":"2025-09-29","cited_by_count":20,"area":"lr"},{"id":"2505.14582","title":"Can Pruning Improve Reasoning? Revisiting Long-CoT Compression with Capability in Mind for Better Reasoning","created":"2025-05-20","cited_by_count":19,"area":"lr"},{"id":"2508.08039","title":"Audio-Thinker: Guiding Audio Language Model When and How to Think via Reinforcement Learning","created":"2025-08-11","cited_by_count":19,"area":"lr"},{"id":"2512.17312","title":"CodeDance: A Dynamic Tool-integrated MLLM for Executable Visual Reasoning","created":"2025-12-19","cited_by_count":16,"area":"lr"},{"id":"2604.24300","title":"ReVSI: Rebuilding Visual Spatial Intelligence Evaluation for Accurate Assessment of VLM 3D Reasoning","created":"2026-04-27","cited_by_count":15,"area":"lr"},{"id":"2506.09736","title":"Revisiting Visual Understanding in Multimodal Reasoning through a Lens of Image Perturbation","created":"2025-06-11","cited_by_count":14,"area":"lr"},{"id":"2510.07356","title":"ConCuR: Conciseness Makes State-of-the-Art Kernel Generation","created":"2025-10-08","cited_by_count":13,"area":"lr"},{"id":"2507.03483","title":"BMMR: A Large-Scale Bilingual Multimodal Multi-Discipline Reasoning Dataset","created":"2025-07-04","cited_by_count":12,"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":"2506.09958","title":"Kvasir-VQA-x1: A Multimodal Dataset for Medical Reasoning and Robust MedVQA in Gastrointestinal Endoscopy","created":"2025-06-11","cited_by_count":11,"area":"lr"},{"id":"2602.08828","title":"VideoVeritas: AI-Generated Video Detection via Perception Pretext Reinforcement Learning","created":"2026-02-09","cited_by_count":11,"area":"lr"},{"id":"2605.07177","title":"HyperEyes: Dual-Grained Efficiency-Aware Reinforcement Learning for Parallel Multimodal Search Agents","created":"2026-05-08","cited_by_count":10,"area":"lr"},{"id":"2505.14412","title":"PRL: Prompts from Reinforcement Learning","created":"2025-05-20","cited_by_count":9,"area":"lr"},{"id":"2601.15724","title":"VideoThinker: Building Agentic VideoLLMs with LLM-Guided Tool Reasoning","created":"2026-01-22","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":"2603.05869","title":"PatchCue: Enhancing Vision-Language Model Reasoning with Patch-Based Visual Cues","created":"2026-03-06","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":"2512.02306","title":"OmniGuard: Unified Omni-Modal Guardrails with Deliberate Reasoning","created":"2025-12-02","cited_by_count":7,"area":"lr"},{"id":"2512.19126","title":"AWPO: Enhancing Tool-Use of Large Language Models through Adaptive Integration of Reasoning Rewards","created":"2025-12-22","cited_by_count":7,"area":"lr"},{"id":"2601.05688","title":"SketchVL: Policy Optimization via Fine-Grained Credit Assignment for Chart Understanding and More","created":"2026-01-09","cited_by_count":7,"area":"lr"},{"id":"2605.17672","title":"Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models","created":"2026-05-17","cited_by_count":7,"area":"lr"},{"id":"2506.06727","title":"VisioMath: Benchmarking Figure-based Mathematical Reasoning in LMMs","created":"2025-06-07","cited_by_count":6,"area":"lr"},{"id":"2601.02983","title":"Interpretable All-Type Audio Deepfake Detection with Audio LLMs via Frequency-Time Reinforcement Learning","created":"2026-01-06","cited_by_count":6,"area":"lr"},{"id":"2508.20384","title":"Uncertainty Under the Curve: A Sequence-Level Entropy Area Metric for Reasoning LLM","created":"2025-08-28","cited_by_count":5,"area":"lr"},{"id":"2604.00493","title":"A Reasoning-Enabled Vision-Language Foundation Model for Chest X-ray Interpretation","created":"2026-04-01","cited_by_count":5,"area":"lr"},{"id":"2604.21409","title":"S1-VL: Scientific Multimodal Reasoning Model with Thinking-with-Images","created":"2026-04-23","cited_by_count":5,"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":"2511.18242","title":"EgoVITA: Learning to Plan and Verify for Egocentric Video Reasoning","created":"2025-11-23","cited_by_count":4,"area":"lr"},{"id":"2602.01472","title":"ConPress: Learning Efficient Reasoning from Multi-Question Contextual Pressure","created":"2026-02-01","cited_by_count":4,"area":"lr"},{"id":"2602.09829","title":"Internalizing Multi-Agent Reasoning for Accurate and Efficient LLM-based Recommendation","created":"2026-02-10","cited_by_count":4,"area":"lr"},{"id":"2602.18702","title":"Think with Grounding: Curriculum Reinforced Reasoning with Video Grounding for Long Video Understanding","created":"2026-02-21","cited_by_count":4,"area":"lr"},{"id":"2607.07836","title":"Infinity-Parser2 Technical Report","created":"2026-07-08","cited_by_count":4,"area":"lr"},{"id":"2409.17080","title":"Can Vision Language Models Learn from Visual Demonstrations of Ambiguous Spatial Reasoning?","created":"2024-09-25","cited_by_count":3,"area":"lr"},{"id":"2509.04457","title":"Do MLLMs Really Understand the Charts?","created":"2025-08-27","cited_by_count":3,"area":"lr"},{"id":"2509.17743","title":"VideoPro: Adaptive Program Reasoning for Long Video Understanding","created":"2025-09-22","cited_by_count":3,"area":"lr"},{"id":"2510.04532","title":"More Than Meets the Eye? Uncovering the Reasoning-Planning Disconnect in Training Vision-Language Driving Models","created":"2025-10-06","cited_by_count":3,"area":"lr"},{"id":"2602.04391","title":"Beyond Rejection Sampling: Trajectory Fusion for Scaling Mathematical Reasoning","created":"2026-02-04","cited_by_count":3,"area":"lr"},{"id":"2603.10757","title":"CodePercept: Code-Grounded Visual STEM Perception for MLLMs","created":"2026-03-11","cited_by_count":3,"area":"lr"},{"id":"2604.24339","title":"See Further, Think Deeper: Advancing VLM's Reasoning Ability with Low-level Visual Cues and Reflection","created":"2026-04-27","cited_by_count":3,"area":"lr"},{"id":"2502.14908","title":"SegSub: Evaluating Robustness to Knowledge Conflicts and Hallucinations in Vision-Language Models","created":"2025-02-19","cited_by_count":2,"area":"lr"},{"id":"2504.01789","title":"OpenThaiGPT 1.6 and R1: Thai-Centric Open Source and Reasoning Large Language Models","created":"2025-04-02","cited_by_count":2,"area":"lr"},{"id":"2508.12628","title":"Creative4U: MLLMs-based Advertising Creative Image Selector with Comparative Reasoning","created":"2025-08-18","cited_by_count":2,"area":"lr"},{"id":"2508.16514","title":"FLAMES: Improving LLM Math Reasoning via a Fine-Grained Analysis of the Data Synthesis Pipeline","created":"2025-08-22","cited_by_count":2,"area":"lr"},{"id":"2510.09211","title":"DICE: Structured Reasoning in LLMs through SLM-Guided Chain-of-Thought Correction","created":"2025-10-10","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":"2511.03408","title":"Efficient Reasoning via Thought-Training and Thought-Free Inference","created":"2025-11-05","cited_by_count":2,"area":"lr"},{"id":"2601.18197","title":"GAIA: A Data Flywheel System for Training GUI Test-Time Scaling Critic Models","created":"2026-01-26","cited_by_count":2,"area":"lr"},{"id":"2605.09906","title":"Separate First, Fuse Later: Mitigating Cross-Modal Interference in Audio-Visual LLMs Reasoning with Modality-Specific Chain-of-Thought","created":"2026-05-11","cited_by_count":2,"area":"lr"},{"id":"2605.27190","title":"Learning When to Think While Listening in Large Audio-Language Models","created":"2026-05-26","cited_by_count":2,"area":"lr"},{"id":"2605.27255","title":"Pair-In, Pair-Out: Latent Multi-Token Prediction for Efficient LLMs","created":"2026-05-26","cited_by_count":2,"area":"lr"},{"id":"2606.02041","title":"SentGuard: Sentence-Level Streaming Guardrails for Large Language Models","created":"2026-06-01","cited_by_count":2,"area":"lr"},{"id":"2606.08952","title":"AlloSpatial: Agentic Harness Framework for Spatial Reasoning in Foundation Models","created":"2026-06-08","cited_by_count":2,"area":"lr"},{"id":"2507.21924","title":"MMAT-1M: A Large Reasoning Dataset for Multimodal Agent Tuning","created":"2025-07-29","cited_by_count":1,"area":"lr"},{"id":"2509.21960","title":"Think Smart, Not Hard: Difficulty Adaptive Reasoning for Large Audio Language Models","created":"2025-09-26","cited_by_count":1,"area":"lr"},{"id":"2511.10055","title":"Physical Plausibility Reasoning via HCM-GRPO: Empowering Compact Model for Superior Performance","created":"2025-11-13","cited_by_count":1,"area":"lr"},{"id":"2511.10279","title":"PROPA: Toward Process-level Optimization in Visual Reasoning via Reinforcement Learning","created":"2025-11-13","cited_by_count":1,"area":"lr"},{"id":"2604.16893","title":"EasyVideoR1: Easier RL for Video Understanding","created":"2026-04-18","cited_by_count":1,"area":"lr"},{"id":"2605.07872","title":"Video Understanding Reward Modeling: A Robust Benchmark and Performant Reward Models","created":"2026-05-08","cited_by_count":1,"area":"lr"},{"id":"2606.00755","title":"Internalize the Temperature: On-Policy Self-Distillation as Policy Reheater for Reinforcement Learning","created":"2026-05-30","cited_by_count":1,"area":"lr"},{"id":"2606.02842","title":"Spectral-Progressive Thought Flow for Lightweight Multimodal Reasoning","created":"2026-06-01","cited_by_count":1,"area":"lr"},{"id":"2606.11719","title":"Ouroboros-Spatial: Closing the Data-Model Loop for Spatial Reasoning","created":"2026-06-10","cited_by_count":1,"area":"lr"},{"id":"2607.08960","title":"Eluna: An Agentic LLM System for Automating Warehouse Operations with Reasoning and Task Execution","created":"2026-07-09","cited_by_count":1,"area":"lr"},{"id":"2607.28595","title":"Beacon: Knowing When and How to Perform Agentic Visual Reasoning","created":"2026-07-30","cited_by_count":1,"area":"lr"},{"id":"2510.26474","title":"Counteracting Matthew Effect in Self-Improvement of LVLMs through Head-Tail Re-balancing","created":"2025-10-30","cited_by_count":0,"area":"lr"},{"id":"2511.06722","title":"Revisiting the Data Sampling in Multimodal Post-training from a Difficulty-Distinguish View","created":"2025-11-10","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":"2601.08010","title":"CASHEW: Stabilizing Multimodal Reasoning via Iterative Trajectory Aggregation","created":"2026-01-12","cited_by_count":0,"area":"lr"},{"id":"2601.09285","title":"Enhancing Spatial Reasoning in Large Language Models for Metal-Organic Frameworks Structure Prediction","created":"2026-01-14","cited_by_count":0,"area":"lr"},{"id":"2603.12788","title":"Think and Answer ME: Benchmarking and Exploring Multi-Entity Reasoning Grounding in Remote Sensing","created":"2026-03-13","cited_by_count":0,"area":"lr"},{"id":"2605.19663","title":"Pseudocode-Guided Structured Reasoning for Automating Reliable Inference in Vision-Language Models","created":"2026-05-19","cited_by_count":0,"area":"lr"},{"id":"2605.26520","title":"InterSketch: An Interleaved Reasoning Model with Self-correcting Visual Sketch and Stepwise Reward","created":"2026-05-26","cited_by_count":0,"area":"lr"},{"id":"2606.15872","title":"SciOrch: Learning to Orchestrate Expert LLMs for Solving Frontier Multimodal Scientific Reasoning Tasks","created":"2026-06-14","cited_by_count":0,"area":"lr"},{"id":"2607.16322","title":"GMoT: Gated Motion-Aware Tokenization for Fine-Grained Micro-Gesture Video Reasoning with Multimodal LLMs","created":"2026-07-15","cited_by_count":0,"area":"lr"},{"id":"2607.16603","title":"NOWJ@COLIEE 2026: Adaptive Pipelines for Legal Retrieval and Reasoning","created":"2026-07-18","cited_by_count":0,"area":"lr"},{"id":"2607.23075","title":"Traceable LLM Reasoning for Fake-Order Fraud Detection","created":"2026-07-25","cited_by_count":0,"area":"lr"},{"id":"2608.02217","title":"VC-Tooler: Learning Compositional and Adaptive Visual Tool Use","created":"2026-08-03","cited_by_count":0,"area":"lr"},{"id":"2608.10954","title":"Evidence-Grounded Trustworthy Multimodal Reasoning and Evaluation Benchmark in Complex Urban Scenes","created":"2026-08-11","cited_by_count":0,"area":"lr"},{"id":"2608.20814","title":"Enhancing Localized Reasoning for Long Video Understanding via Efficient Segment-to-Video Supervision","created":"2026-08-21","cited_by_count":0,"area":"lr"},{"id":"2608.26141","title":"AdaThinking-E: One-Token Entropy Regulation for Adaptive Thinking","created":"2026-06-26","cited_by_count":0,"area":"lr"},{"id":"2608.29120","title":"HEAR Who Said What: Unlocking Speaker-Attributed Reasoning via Counterfactual Voice Grounding","created":"2026-08-29","cited_by_count":0,"area":"lr"},{"id":"2609.21675","title":"DRT: Dense Reasoning Trace for Efficient and Grounded Multimodal Reasoning","created":"2026-09-18","cited_by_count":0,"area":"lr"},{"id":"2609.26536","title":"Transcribe, Translate, and Optimize: Joint Reward Learning for Speech Translation","created":"2026-09-22","cited_by_count":0,"area":"lr"},{"id":"2609.33290","title":"Calibration, Not Answer Selection: Distilling Internal Confidence in Reasoning Models","created":"2026-09-27","cited_by_count":0,"area":"lr"},{"id":"2610.17043","title":"Neos: Learning to Interleave Search and Visual Reasoning","created":"2026-10-12","cited_by_count":0,"area":"lr"}],"next_cursor":null}