Cover Image

Reasoning via Video: The First Evaluation of Video Models' Reasoning Abilities through Maze-Solving Tasks

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yang, Cheng, Wan, Haiyuan, Peng, Yiran, Cheng, Xin, Yu, Zhaoyang, Zhang, Jiayi, Yu, Junchi, Yu, Xinlei, Zheng, Xiawu, Zhou, Dongzhan, Wu, Chenglin
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

DeepResearch Arena: The First Exam of LLMs' Research Abilities via Seminar-Grounded Tasks
by: Wan, Haiyuan, et al.
Published: (2025)

From What to Why: A Multi-Agent System for Evidence-based Chemical Reaction Condition Reasoning
by: Yang, Cheng, et al.
Published: (2025)

Video Models Reason Early: Exploiting Plan Commitment for Maze Solving
by: Newman, Kaleb, et al.
Published: (2026)

Scaling Physical Reasoning with the PHYSICS Dataset
by: Zheng, Shenghe, et al.
Published: (2025)

VideoREPA: Learning Physics for Video Generation through Relational Alignment with Foundation Models
by: Zhang, Xiangdong, et al.
Published: (2025)

Benchmarking Abstract and Reasoning Abilities Through A Theoretical Perspective
by: Ma, Qingchuan, et al.
Published: (2025)

Evaluating the Logical Reasoning Abilities of Large Reasoning Models
by: Liu, Hanmeng, et al.
Published: (2025)

Unveiling the Compositional Ability Gap in Vision-Language Reasoning Model
by: Li, Tianle, et al.
Published: (2025)

VideoCogQA: A Controllable Benchmark for Evaluating Cognitive Abilities in Video-Language Models
by: Li, Chenglin, et al.
Published: (2024)

Learning Video Representations without Natural Videos
by: Yu, Xueyang, et al.
Published: (2024)

ReasonAgain: Using Extractable Symbolic Programs to Evaluate Mathematical Reasoning
by: Yu, Xiaodong, et al.
Published: (2024)

VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos
by: Wang, Ziyang, et al.
Published: (2024)

SocialMaze: A Benchmark for Evaluating Social Reasoning in Large Language Models
by: Xu, Zixiang, et al.
Published: (2025)

P1-VL: Bridging Visual Perception and Scientific Reasoning in Physics Olympiads
by: Luo, Yun, et al.
Published: (2026)

AutoLogi: Automated Generation of Logic Puzzles for Evaluating Reasoning Abilities of Large Language Models
by: Zhu, Qin, et al.
Published: (2025)

Finding Libraries in the Video Maze.
by: Sessions, Judith A., et al.
Published: (1981)

Beyond Static Tools: Test-Time Tool Evolution for Scientific Reasoning
by: Lu, Jiaxuan, et al.
Published: (2026)

SketchThinker-R1: Towards Efficient Sketch-Style Reasoning in Large Multimodal Models
by: Zhang, Ruiyang, et al.
Published: (2026)

Can Knowledge-Graph-based Retrieval Augmented Generation Really Retrieve What You Need?
by: Yu, Junchi, et al.
Published: (2025)

ARCHE: A Novel Task to Evaluate LLMs on Latent Reasoning Chain Extraction
by: Li, Pengze, et al.
Published: (2025)

Video Evidence to Reasoning Efficient Video Understanding via Explicit Evidence Grounding
by: Huang, Yanxiang, et al.
Published: (2026)

Video-ToC: Video Tree-of-Cue Reasoning
by: Tan, Qizhong, et al.
Published: (2026)

VideoForest: Person-Anchored Hierarchical Reasoning for Cross-Video Question Answering
by: Meng, Yiran, et al.
Published: (2025)

Grounding Video Reasoning in Physical Signals
by: Osmanli, Alibay, et al.
Published: (2026)

TiViBench: Benchmarking Think-in-Video Reasoning for Video Generative Models
by: Chen, Harold Haodong, et al.
Published: (2025)

Thinking with Drafts: Speculative Temporal Reasoning for Efficient Long Video Understanding
by: Hu, Pengfei, et al.
Published: (2025)

Video Models Start to Solve Chess, Maze, Sudoku, Mental Rotation, and Raven' Matrices
by: Deng, Hokin
Published: (2025)

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization
by: Cheng, Junhao, et al.
Published: (2026)

HiPhO: How Far Are (M)LLMs from Humans in the Latest High School Physics Olympiad Benchmark?
by: Yu, Fangchen, et al.
Published: (2025)

VideoRFT: Incentivizing Video Reasoning Capability in MLLMs via Reinforced Fine-Tuning
by: Wang, Qi, et al.
Published: (2025)

Thought Propagation: An Analogical Approach to Complex Reasoning with Large Language Models
by: Yu, Junchi, et al.
Published: (2023)

Transformers Use Causal World Models in Maze-Solving Tasks
by: Spies, Alex F., et al.
Published: (2024)

Skyra: AI-Generated Video Detection via Grounded Artifact Reasoning
by: Li, Yifei, et al.
Published: (2025)

VideoPro: Adaptive Program Reasoning for Long Video Understanding
by: Li, Chenglin, et al.
Published: (2025)

VideoARM: Agentic Reasoning over Hierarchical Memory for Long-Form Video Understanding
by: Yin, Yufei, et al.
Published: (2025)

How Multimodal LLMs Solve Image Tasks: A Lens on Visual Grounding, Task Reasoning, and Answer Decoding
by: Yu, Zhuoran, et al.
Published: (2025)

VideoThinker: Building Agentic VideoLLMs with LLM-Guided Tool Reasoning
by: Li, Chenglin, et al.
Published: (2026)

Instance Brownian Bridge as Texts for Open-vocabulary Video Instance Segmentation
by: Cheng, Zesen, et al.
Published: (2024)

Scientists' First Exam: Probing Cognitive Abilities of MLLM via Perception, Understanding, and Reasoning
by: Zhou, Yuhao, et al.
Published: (2025)

Motion-aware Latent Diffusion Models for Video Frame Interpolation
by: Huang, Zhilin, et al.
Published: (2024)