VLM Reasoning

VLM: Vision-Language Model

This field studies how models connect images or video with language to solve tasks involving spatial relations, time, causality, diagrams, and action. Common approaches include chain-of-thought prompting, visual tools and retrieval, structured representations such as scene graphs, and fine-tuning with process-level rewards. Benchmarks increasingly test whether answers and intermediate steps are grounded in visual evidence, including in multi-image, video, scientific, and embodied settings. A central tension is that longer reasoning can help on complex tasks but can also weaken visual grounding, amplify language-based shortcuts, or produce explanations that do not reflect how an answer was reached.

Latest papers

853 papers96 papers in the last four weeks, up 48% on the four weeks before. 0.6% of all new papers.

CARE Drive A Framework for Evaluating Reason-Responsiveness of Vision Language Models in Automated Driving
Feb 17, 2026Lucas Elbert Suryana, Farah Bierenga, Sanne van Buuren +6Reasoning for VLMs VLM Reasoning
Department of Transport & Planning, Faculty of Civil Engineering and Geosciences, Delft University of Technology · Centre for Meaningful Human Control, Delft University of Technology · Faculty of Mechanical Engineering, Delft University of Technology, Delft, The Netherlands +1
On the Out-of-Distribution Generalization of Reasoning in Multimodal LLMs for Simple Visual Planning Tasks
Feb 17, 2026Yannic Neuhaus, Nicolas Flammarion, Matthias Hein +1OOD Generalization Multimodal Reasoning
Tübingen AI Center – University of Tübingen · EPFL · ELLIS Institute Finland – Aalto University
One Agent to Guide Them All: Empowering MLLMs for Vision-and-Language Navigation via Explicit World Representation
Feb 17, 2026Zerui Li, Hongpei Zheng, Fangguo Zhao +5Vision-Language Navigation VLMs for Robotics
Australian Institute for Machine Learning, Adelaide University · The University of Manchester · Zhejiang University +1
EarthSpatialBench: Benchmarking Spatial Reasoning Capabilities of Multimodal LLMs on Earth Imagery
Feb 17, 2026Zelin Xu, Yupu Zhang, Saugat Adhikari +6Spatial Reasoning Benchmarks Geospatial Reasoning Benchmarks
Department of Computer & Information Science & Engineering, University of Florida, Gainesville, FL, USA · Department of Computer Science, Indiana University Bloomington, Bloomington, IN, USA.
MaS-VQA: A Mask-and-Select Framework for Knowledge-Based Visual Question Answering
Feb 17, 2026Xianwei Mao, Kai Ye, Sheng Zhou +4Visual Question Answering Knowledge-Based VQA
Zhejiang University, Hangzhou, China · Alibaba Group, Hangzhou, China
MATEO: A Multimodal Benchmark for Temporal Reasoning and Planning in LVLMs
Feb 16, 2026Gabriel Roccabruna, Olha Khomyn, Giuseppe RiccardiTemporal Reasoning in VLMs VLM Reasoning
Signals and Interactive Systems Lab, University of Trento, Italy
TikArt: Stabilizing Aperture-Guided Fine-Grained Visual Reasoning with Reinforcement Learning
Feb 16, 2026Hao Ding, Zhichuan Yang, Weijie Ge +3VLM Reasoning Multimodal Reasoning
Zhejiang University, Hangzhou, China · Xi’an Jiaotong University, Xi’an, China · Zhejiang University of Science and Technology, Hangzhou, China
Egocentric Bias in Vision-Language Models
Feb 10, 2026Maijunxian Wang, Yijiang Li, Bingyang Wang +6VLM Evaluation Visual Spatial Reasoning
Cognitive Science Program, University of California, Berkeley · Department of Electrical and Computer Engineering, University of California San Diego · School of Computer Science, Georgia Institute of Technology & Emory University +6
Joint Reward Modeling: Internalizing Chain-of-Thought for Efficient Visual Reward Models
Feb 7, 2026Yankai Yang, Yancheng Long, Hongyang Wei +12Reward Modeling Multimodal Reward Modeling
Harbin Institute of Technology, Shenzhen. · Kuaishou Technology.
SPARC: Separating Perception And Reasoning Circuits for Test-time Scaling of VLMs
Feb 6, 2026Niccolo Avogaro, Nayanika Debnath, Li Mi +6Visual Question Answering Efficient VLM Inference
ETH Zürich · IBM Research · MIT-IBM Watson AI Lab.
VRIQ: Benchmarking and Diagnosing the Visual-Reasoning IQ of Vision-Language Models
Feb 5, 2026Tina Khezresmaeilzadeh, Jike Zhong, Konstantinos PsounisVisual Reasoning VLM Reasoning
University of Southern California, Los Angeles, USA
Multimodal Latent Reasoning via Hierarchical Visual Cues Injection
Feb 5, 2026Yiming Zhang, Qiangyu Yan, Borui Jiang +1VLM Reasoning Multimodal Large Language Models
Nanyang Technological University · Huawei Noah’s Ark Lab
MARE: Multimodal Alignment and Reinforcement for Explainable Deepfake Detection via Vision-Language Models
Jan 28, 2026Wenbo Xu, Wei Lu, Xiangyang LuoExplainable Deepfake Detection Deepfake Detection
School of Computer Science and Engineering, Sun Yat-sen University Guangzhou, Guangdong, China · State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou, Henan, China
R3G: A Reasoning-Retrieval-Reranking Framework for Vision-Centric Answer Generation
Jan 25, 2026Zhuohong Chen, Zhengxian Wu, Zirui Liao +6Multimodal RAG Visual Question Answering
1The Shenzhen International Graduate School, Tsinghua University, China · School of Computer Science and Information Engineering, Hefei University of Technology, China · 2State Key Laboratory of Nuclear Power Safety Technology and Equipment, China
AMVICC: A Novel Benchmark for Cross-Modal Failure Mode Profiling for VLMs and IGMs
Jan 20, 2026Aahana Basappa, Pranay Goel, Anusri Karra +3Reasoning Evaluation Multimodal Large Language Models
Centennial High School, Frisco, Texas, USA · Algoverse AI Research, Palo Alto, Cali- fornia, USA · Lebanon Trail High School, Frisco, Texas, USA +1
SplatReasoner: Enhancing Embodied Reasoning and Grounding by Novel View Synthesis
Jan 19, 2026Kim Yu-Ji, Dahye Lee, Kim Jun-Seong +6VLM Reasoning Visually Grounded Reasoning
POSTECH · KAIST · ETRI +1
Think3D: Thinking with Space for Spatial Reasoning
Jan 19, 2026Zaibin Zhang, Yuhan Wu, Lianjie Jia +103D Spatial Reasoning VLM Reasoning
Dalian University of Technology · University of California San Diego · Independent Researcher +1
CASHEW: Stabilizing Multimodal Reasoning via Iterative Trajectory Aggregation
Jan 12, 2026Chaoyu Li, Fei Tao, Pooyan FazliTest-Time Scaling for VLMs Test-Time Scaling
Arizona State University · NewsBreak
VLM-CAD: VLM-Optimized Collaborative Agent Design Workflow for Analog Circuit Sizing
Jan 12, 2026Guanyuan Pan, Shuai Wang, Yugui Lin +4Bayesian Optimization Electronic Design Automation
Hangzhou Dianzi University, China · SCBC, Guangdong University of Foreign Studies, China · University of Cambridge, United Kingdom
Zoom-IQA: Image Quality Assessment with Reliable Region-Aware Reasoning
Jan 6, 2026Guoqiang Liang, Jianyi Wang, Zhonghua Wu +2VLM Robustness VLM Reasoning
National University of Singapore · S-Lab, Nanyang Technological University, Singapore · SenseTime Research
From Perception to Punchline: Empowering VLM with the Art of In-the-wild Meme
Dec 31, 2025Xueyan Li, Yingyi Xue, Mengjie Jiang +2VLM Reasoning RL for VLMs
Shanghai Artificial Intelligence Laboratory · Fudan University · Columbia Engineering Columbia University +1
MUSON: A Reasoning-oriented Multimodal Dataset for Socially Compliant Navigation in Urban Environments
Dec 28, 2025Zhuonan Liu, Xinyu Zhang, Zishuo Wang +8VLM Evaluation Social Robot Navigation
Graduate School of Information Science and Technology, Hokkaido University, Sapporo, Japan · Graduate School of Computer Science, George Mason University, Fairfax County, Virginia, USA
RePlan: Reasoning-guided Region Planning for Complex Instruction-based Image Editing
Dec 18, 2025Tianyuan Qu, Lei Ke, Xiaohang Zhan +6Text-Guided Image Editing VLM Reasoning
Tencent AI Lab, China · The Chinese University of Hong Kong, China · The Hong Kong University of Science and Technology, China
CoSPlan: Corrective Sequential Planning via Scene Graph Incremental Updates
Dec 11, 2025Shresth Grover, Priyank Pathak, Akash Kumar +1VLM Reasoning Visually Grounded Reasoning
UCF Institute of Artificial Intelligence, University of Central Florida (UCF)
See, Think, Learn: A Self-Taught Multimodal Reasoner
Dec 2, 2025Sourabh Sharma, Sonam Gupta, SadbhawnaSelf-Training VLM Reasoning
Malaviya National Institute of Technology Jaipur · IBM Research
Understanding the Effects of Distractors on Reasoning Vision-Language Models
Nov 26, 2025Jiyun Bae, Hyunjong Ok, Sangwoo Mo +1VLM Reasoning Visual Question Answering
Pohang University of Science and Technology (POSTECH)
Vision-Language Memory for Spatial Reasoning
Nov 25, 2025Zuntao Liu, Yi Du, Taimeng Fu +3Memory-Augmented VLMs Vision-Language Models
Spatial AI & Robotics (SAIR) Lab, University at Buffalo, USA · Stanford University, USA
MonoSR: Open-Vocabulary Spatial Reasoning from Monocular Images
Nov 24, 2025Qirui Wang, Jingyi He, Yining Pan +3Spatial Reasoning Benchmarks Visual Spatial Reasoning
Technical University of Munich, Germany · A*STAR Institute of Advanced Intelligence and Computing, Singapore · Singapore University of Technology and Design, Singapore +1
Thinking Ahead: Foresight Intelligence in MLLMs and World Model
Nov 24, 2025Zhantao Gong, Liaoyuan Fan, Qing Guo +3VLM Evaluation VLM Adaptation
College of Software, Nankai University, China · The University of Hong Kong, China · NKIARI, Shenzhen Futian, China +2
Do Vision-Language Models Understand Visual Persuasiveness? A Diagnosis via Visual Persuasive Factors
Nov 21, 2025Gyuwon Park, Hyounghun KimVLM Evaluation VLM Reasoning
Graduate School of Artificial Intelligence, POSTECH · Department of Computer Science and Engineering, POSTECH

Feb 17, 2026J/K move · Enter open · S save

CARE Drive A Framework for Evaluating Reason-Responsiveness of Vision Language Models in Automated Driving

Lucas Elbert Suryana, Farah Bierenga, Sanne van Buuren, Pepijn Kooij+5

Department of Transport & Planning, Faculty of Civil Engineering and Geosciences, Delft University of Technology · Centre for Meaningful Human Control, Delft University of Technology · Faculty of Mechanical Engineering, Delft University of Technology, Delft, The Netherlands+1

Reasoning for VLMs VLM Reasoning VLMs for Autonomous Driving Counterfactual Evaluation of VLMs

Open paper AskPDF arXiv

Foundation models, including vision language models, are increasingly used in automated driving to interpret scenes, recommend actions, and generate natural language explanations. However, existing evaluation methods primarily assess outcome based performance, such as safety and trajectory accuracy, without determining whether model decisions reflect human relevant considerations. As a result, it remains unclear whether explanations produced by such models correspond to genuine reason responsive decision making or merely post hoc rationalizations. This limitation is especially significant in safety critical domains because it can create false confidence. To address this gap, we propose CARE Drive, Context Aware Reasons Evaluation for Driving, a model agnostic framework for evaluating reason responsiveness in vision language models applied to automated driving. CARE Drive compares baseline and reason augmented model decisions under controlled contextual variation to assess whether human reasons causally influence decision behavior. The framework employs a two stage evaluation process. Prompt calibration ensures stable outputs. Systematic contextual perturbation then measures decision sensitivity to human reasons such as safety margins, social pressure, and efficiency constraints. We demonstrate CARE Drive in a cyclist overtaking scenario involving competing normative considerations. Results show that explicit human reasons significantly influence model decisions, improving alignment with expert recommended behavior. However, responsiveness varies across contextual factors, indicating uneven sensitivity to different types of reasons. These findings provide empirical evidence that reason responsiveness in foundation models can be systematically evaluated without modifying model parameters.