{"total":53,"rows":[{"id":"2502.21321","title":"LLM Post-Training: A Deep Dive into Reasoning Large Language Models","created":"2025-02-28","cited_by_count":135,"area":"lr"},{"id":"2503.20752","title":"Reason-RFT: Reinforcement Fine-Tuning for Visual Reasoning of Vision Language Models","created":"2025-03-26","cited_by_count":99,"area":"lr"},{"id":"2501.12368","title":"InternLM-XComposer2.5-Reward: A Simple Yet Effective Multi-Modal Reward Model","created":"2025-01-21","cited_by_count":74,"area":"lr"},{"id":"2503.19990","title":"LEGO-Puzzles: How Good Are MLLMs at Multi-Step Spatial Reasoning?","created":"2025-03-25","cited_by_count":49,"area":"lr"},{"id":"2508.02095","title":"VLM4D: Towards Spatiotemporal Awareness in Vision Language Models","created":"2025-08-04","cited_by_count":46,"area":"lr"},{"id":"2505.20289","title":"VisualToolAgent (VisTA): A Reinforcement Learning Framework for Visual Tool Selection","created":"2025-05-26","cited_by_count":34,"area":"lr"},{"id":"2503.13399","title":"MicroVQA: A Multimodal Reasoning Benchmark for Microscopy-Based Scientific Research","created":"2025-03-17","cited_by_count":32,"area":"lr"},{"id":"2506.04034","title":"Rex-Thinker: Grounded Object Referring via Chain-of-Thought Reasoning","created":"2025-06-04","cited_by_count":26,"area":"lr"},{"id":"2505.15804","title":"STAR-R1: Spatial TrAnsformation Reasoning by Reinforcing Multimodal LLMs","created":"2025-05-21","cited_by_count":21,"area":"lr"},{"id":"2410.12381","title":"HumanEval-V: Benchmarking High-Level Visual Reasoning with Complex Diagrams in Coding Tasks","created":"2024-10-16","cited_by_count":20,"area":"lr"},{"id":"2505.24876","title":"Agent-X: Evaluating Deep Multimodal Reasoning in Vision-Centric Agentic Tasks","created":"2025-05-30","cited_by_count":19,"area":"lr"},{"id":"2501.13042","title":"Does Table Source Matter? Benchmarking and Improving Multimodal Scientific Table Understanding and Reasoning","created":"2025-01-22","cited_by_count":15,"area":"lr"},{"id":"2501.02669","title":"Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs?","created":"2025-01-05","cited_by_count":14,"area":"lr"},{"id":"2503.20084","title":"Can Multi-modal (reasoning) LLMs work as deepfake detectors?","created":"2025-03-25","cited_by_count":14,"area":"lr"},{"id":"2509.25916","title":"VLM-FO1: Bridging the Gap Between High-Level Reasoning and Fine-Grained Perception in VLMs","created":"2025-09-30","cited_by_count":13,"area":"lr"},{"id":"2502.11176","title":"LogiDynamics: Unraveling the Dynamics of Inductive, Abductive and Deductive Logical Inferences in LLM Reasoning","created":"2025-02-16","cited_by_count":12,"area":"lr"},{"id":"2507.21619","title":"EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPO","created":"2025-07-29","cited_by_count":12,"area":"lr"},{"id":"2508.04043","title":"VisualTrans: A Benchmark for Real-World Visual Transformation Reasoning","created":"2025-08-06","cited_by_count":12,"area":"lr"},{"id":"2503.11089","title":"EmbodiedVSR: Dynamic Scene Graph-Guided Chain-of-Thought Reasoning for Visual Spatial Tasks","created":"2025-03-14","cited_by_count":10,"area":"lr"},{"id":"2504.00043","title":"CrossWordBench: Evaluating the Reasoning Capabilities of LLMs and LVLMs with Controllable Puzzle Generation","created":"2025-03-30","cited_by_count":10,"area":"lr"},{"id":"2511.23478","title":"Video-R2: Reinforcing Consistent and Grounded Reasoning in Multimodal Language Models","created":"2025-11-28","cited_by_count":10,"area":"lr"},{"id":"2412.00151","title":"DLaVA: Document Language and Vision Assistant for Answer Localization with Enhanced Interpretability and Trustworthiness","created":"2024-11-29","cited_by_count":8,"area":"lr"},{"id":"2505.13403","title":"MR. Judge: Multimodal Reasoner as a Judge","created":"2025-05-19","cited_by_count":7,"area":"lr"},{"id":"2510.04514","title":"ChartAgent: A Multimodal Agent for Visually Grounded Reasoning in Complex Chart Question Answering","created":"2025-10-06","cited_by_count":7,"area":"lr"},{"id":"2603.09095","title":"Reading, Not Thinking: Understanding and Bridging the Modality Gap When Text Becomes Pixels in Multimodal LLMs","created":"2026-03-10","cited_by_count":7,"area":"lr"},{"id":"2505.18087","title":"CXReasonBench: A Benchmark for Evaluating Structured Diagnostic Reasoning in Chest X-rays","created":"2025-05-23","cited_by_count":6,"area":"lr"},{"id":"2601.14691","title":"Gaming the Judge: Unfaithful Chain-of-Thought Can Undermine Agent Evaluation","created":"2026-01-21","cited_by_count":6,"area":"lr"},{"id":"2602.20901","title":"SpatiaLQA: A Benchmark for Evaluating Spatial Logical Reasoning in Vision-Language Models","created":"2026-02-24","cited_by_count":6,"area":"lr"},{"id":"2502.16428","title":"Visual Reasoning Evaluation of Grok, Deepseek Janus, Gemini, Qwen, Mistral, and ChatGPT","created":"2025-02-23","cited_by_count":5,"area":"lr"},{"id":"2509.26272","title":"PRPO: Paragraph-level Policy Optimization for Vision-Language Deepfake Detection","created":"2025-09-30","cited_by_count":5,"area":"lr"},{"id":"2504.01700","title":"Reasoning LLMs for User-Aware Multimodal Conversational Agents","created":"2025-04-02","cited_by_count":4,"area":"lr"},{"id":"2506.06856","title":"Vision-EKIPL: External Knowledge-Infused Policy Learning for Visual Reasoning","created":"2025-06-07","cited_by_count":4,"area":"lr"},{"id":"2508.10287","title":"JRDB-Reasoning: A Difficulty-Graded Benchmark for Visual Reasoning in Robotics","created":"2025-08-14","cited_by_count":3,"area":"lr"},{"id":"2510.15040","title":"Composition-Grounded Data Synthesis for Visual Reasoning","created":"2025-10-16","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":"2508.15690","title":"GRAFT: GRaPH and Table Reasoning for Textual Alignment -- A Benchmark for Structured Instruction Following and Visual Reasoning","created":"2025-08-21","cited_by_count":2,"area":"lr"},{"id":"2602.10551","title":"C^2ROPE: Causal Continuous Rotary Positional Encoding for 3D Large Multimodal-Models Reasoning","created":"2026-02-11","cited_by_count":2,"area":"lr"},{"id":"2606.31257","title":"Decodable Is Not Grounded: A Vision-Ablation Arbiter for VLM Spatial Reasoning","created":"2026-06-30","cited_by_count":2,"area":"lr"},{"id":"2508.00323","title":"Oedipus and the Sphinx: Benchmarking and Improving Visual Language Models for Complex Graphic Reasoning","created":"2025-08-01","cited_by_count":1,"area":"lr"},{"id":"2512.06663","title":"CoT4Det: A Chain-of-Thought Framework for Perception-Oriented Vision-Language Tasks","created":"2025-12-07","cited_by_count":1,"area":"lr"},{"id":"2603.02438","title":"ORCA: Orchestrated Reasoning with Collaborative Agents for Document Visual Question Answering","created":"2026-03-02","cited_by_count":1,"area":"lr"},{"id":"2605.27932","title":"When Think-with-Image Meets Safety: What Determines Multimodal Jailbreak Robustness?","created":"2026-05-27","cited_by_count":1,"area":"lr"},{"id":"2605.30713","title":"Diversity Matters: Revisiting Test-Time Compute in Vision-Language Models","created":"2026-05-29","cited_by_count":1,"area":"lr"},{"id":"2501.11833","title":"Is your LLM trapped in a Mental Set? Investigative study on how mental sets affect the reasoning capabilities of LLMs","created":"2025-01-21","cited_by_count":0,"area":"lr"},{"id":"2503.01064","title":"Scientific Reasoning: Assessment of Multimodal Generative LLMs","created":"2025-03-03","cited_by_count":0,"area":"lr"},{"id":"2509.16654","title":"Are VLMs Ready for Lane Topology Awareness in Autonomous Driving?","created":"2025-09-20","cited_by_count":0,"area":"lr"},{"id":"2512.09092","title":"Explaining the Unseen: Multimodal Vision-Language Reasoning for Situational Awareness in Underground Mining Disasters","created":"2025-12-09","cited_by_count":0,"area":"lr"},{"id":"2601.17489","title":"SpatialMath: Spatial Comprehension-Infused Symbolic Reasoning for Mathematical Problem-Solving","created":"2026-01-24","cited_by_count":0,"area":"lr"},{"id":"2602.12892","title":"RADAR: Revealing Asymmetric Development of Abilities in MLLM Pre-training","created":"2026-02-13","cited_by_count":0,"area":"lr"},{"id":"2603.17333","title":"Grid Spatial Understanding: A Dataset for Textual Spatial Reasoning over Grids, Embodied Settings, and Coordinate Structures","created":"2026-03-18","cited_by_count":0,"area":"lr"},{"id":"2604.02007","title":"Apriel-Reasoner: RL Post-Training for General-Purpose and Efficient Reasoning","created":"2026-04-02","cited_by_count":0,"area":"lr"},{"id":"2607.06445","title":"Analysis-by-Proxy: Localization Signals in VLMs Operating as Condition Encoders","created":"2026-07-07","cited_by_count":0,"area":"lr"},{"id":"2609.30979","title":"CCRV-Bench: Constraint-Based Evaluation of Causal Reasoning in Vision-Language Models","created":"2026-09-25","cited_by_count":0,"area":"lr"}],"next_cursor":null}