{"total":33,"rows":[{"id":"2502.17419","title":"From System 1 to System 2: A Survey of Reasoning Large Language Models","created":"2025-02-24","cited_by_count":320,"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":"2502.11271","title":"OctoTools: An Agentic Framework with Extensible Tools for Complex Reasoning","created":"2025-02-16","cited_by_count":69,"area":"lr"},{"id":"2503.16188","title":"Think or Not Think: A Study of Explicit Thinking in Rule-Based Visual Reinforcement Fine-Tuning","created":"2025-03-20","cited_by_count":44,"area":"lr"},{"id":"2511.04570","title":"Thinking with Video: Video Generation as a Promising Multimodal Reasoning Paradigm","created":"2025-11-06","cited_by_count":42,"area":"lr"},{"id":"2511.16334","title":"OpenMMReasoner: Pushing the Frontiers for Multimodal Reasoning with an Open and General Recipe","created":"2025-11-20","cited_by_count":37,"area":"lr"},{"id":"2507.05255","title":"Open Vision Reasoner: Transferring Linguistic Cognitive Behavior for Visual Reasoning","created":"2025-07-07","cited_by_count":34,"area":"lr"},{"id":"2505.21327","title":"MME-Reasoning: A Comprehensive Benchmark for Logical Reasoning in MLLMs","created":"2025-05-27","cited_by_count":33,"area":"lr"},{"id":"2505.18129","title":"One RL to See Them All: Visual Triple Unified Reinforcement Learning","created":"2025-05-23","cited_by_count":30,"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":"2501.04671","title":"Retrieval-Based Interleaved Visual Chain-of-Thought in Real-World Driving Scenarios","created":"2025-01-08","cited_by_count":16,"area":"lr"},{"id":"2509.23250","title":"Training Vision-Language Process Reward Models for Test-Time Scaling in Multimodal Reasoning: Key Insights and Lessons Learned","created":"2025-09-27","cited_by_count":13,"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":"2506.06211","title":"PuzzleWorld: A Benchmark for Multimodal, Open-Ended Reasoning in Puzzlehunts","created":"2025-06-06","cited_by_count":8,"area":"lr"},{"id":"2506.14512","title":"SIRI-Bench: Challenging VLMs' Spatial Intelligence through Complex Reasoning Tasks","created":"2025-06-17","cited_by_count":7,"area":"lr"},{"id":"2602.01541","title":"Toward Cognitive Supersensing in Multimodal Large Language Model","created":"2026-02-02","cited_by_count":7,"area":"lr"},{"id":"2602.16742","title":"DeepVision-103K: A Visually Diverse, Broad-Coverage, and Verifiable Mathematical Dataset for Multimodal Reasoning","created":"2026-02-18","cited_by_count":6,"area":"lr"},{"id":"2502.01081","title":"The Jumping Reasoning Curve? Tracking the Evolution of Reasoning Performance in GPT-[n] and o-[n] Models on Multimodal Puzzles","created":"2025-02-03","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":"2504.01324","title":"On Data Synthesis and Post-training for Visual Abstract Reasoning","created":"2025-04-02","cited_by_count":3,"area":"lr"},{"id":"2506.22992","title":"MARBLE: A Hard Benchmark for Multimodal Spatial Reasoning and Planning","created":"2025-06-28","cited_by_count":3,"area":"lr"},{"id":"2606.01599","title":"TRON: Targeted Rule-Verifiable Online Environments for Visual Reasoning RL","created":"2026-06-01","cited_by_count":3,"area":"lr"},{"id":"2511.02280","title":"SAIL-RL: Guiding MLLMs in When and How to Think via Dual-Reward RL Tuning","created":"2025-11-04","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":"2607.19790","title":"Trace: A Taxonomy-Guided Environment for Multidomain Visual Reasoning","created":"2026-07-22","cited_by_count":1,"area":"lr"},{"id":"2610.01352","title":"MMVistaReason: Toward Open-Data and Post-Training Recipes for Multimodal Reasoning","created":"2026-10-01","cited_by_count":1,"area":"lr"},{"id":"2606.00148","title":"StemBind: When MLLMs Get Lost Between Rules and Instances in Abstract Visual Reasoning","created":"2026-05-29","cited_by_count":0,"area":"lr"},{"id":"2606.14795","title":"Position: The Systemic Lack of Agency in Visual Reasoning","created":"2026-06-11","cited_by_count":0,"area":"lr"},{"id":"2607.08572","title":"Switch-Reasoner: Learn When to Think in Multitask Mixtures via Reinforcement Learning","created":"2026-07-09","cited_by_count":0,"area":"lr"},{"id":"2608.12781","title":"Beyond Correctness: Benchmarking and Aligning Response Behaviors in Hybrid-Thinking MLLMs","created":"2026-08-13","cited_by_count":0,"area":"lr"},{"id":"2609.34769","title":"LongPuzzleBench: Evaluating GUI Agents on Long-Horizon Visual Puzzles","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2610.13184","title":"AdaC-GRPO: Towards Mastering Long-Horizon Visual Sudoku Puzzles via Adaptive Curriculum Learning","created":"2026-10-09","cited_by_count":0,"area":"lr"},{"id":"2610.14403","title":"VisualCoding: Learning Executable Skills for Reliable Visual Reasoning","created":"2026-10-09","cited_by_count":0,"area":"lr"}],"next_cursor":null}