Probing the effectiveness of World Models for Spatial Reasoning through Test-time Scaling
MILA – Quebec AI Institute(魁北克人工智能研究所);Polytechnique Montréal(蒙特利尔理工学院);MIT CSAIL(麻省理工学院计算机科学与人工智能实验室);Institute for Machine Learning, Johannes Kepler University Linz(林茨约瑟夫·夫兰克大学机器学习研究所);Nankai University(南开大学)
Vision-Language Models (VLMs) remain limited in spatial reasoning tasks that require multi-view understanding and embodied perspective shifts. Recent approaches such as MindJourney attempt to mitigate this gap through test-time scaling where a world model imagines action-conditioned trajectories and a heuristic verifier selects helpful views from such trajectories. In this work, we systematically examine how such test-time verifiers behave across benchmarks, uncovering both their promise and their pitfalls. Our uncertainty-based analyses show that MindJourney's verifier provides little meaningful calibration, and that random scoring often reduces answer entropy equally well, thus exposing systematic action biases and unreliable reward signals. To mitigate these, we introduce a Verification through Spatial Assertions (ViSA) framework that grounds the test-time reward in verifiable, frame-anchored micro-claims. This principled verifier consistently improves spatial reasoning on the SAT-Real benchmark and corrects trajectory-selection biases through more balanced exploratory behavior. However, on the challenging MMSI-Bench, none of the verifiers, including ours, achieve consistent scaling, suggesting that the current world models form an information bottleneck where imagined views fail to enrich fine-grained reasoning. Together, these findings chart the bad, good, and ugly aspects of test-time verification for world-model-based reasoning. Our code is available at https://github.com/chandar-lab/visa-for-mindjourney.
SpatialAct: Probing Spatial Reasoning-to-Action Capabilities of VLM Agents in 3D Scenes
The Hong Kong University of Science and Technology (Guangzhou)(香港科学与技术大学(广州));Zhongguancun Academy(中关村学院);Tsinghua University(清华大学);Helsinki University(赫尔辛基大学)
Seeing Symbols, Missing Cultures: Probing Vision-Language Models' Reasoning on Fire Imagery and Cultural Meaning
Duncan of Jordanstone College of Art & Design (DJCAD), University of Dundee(邓迪大学邓迪艺术与设计学院(DJCAD));Guangzhou Institute of Science and Technology (GZIST)(广州科学技术研究院);Faculty of Arts, Xiamen University(厦门大学艺术学院);University of Birmingham(伯明翰大学)
Shanghai Jiao Tong University(上海交通大学);Renmin University of China(中国人民大学);State Key Laboratory of General Artificial Intelligence, BIGAI(通用人工智能国家重点实验室,BIGAI)
Probing Mechanical Reasoning in Large Vision Language Models
Johns Hopkins University(约翰霍普金斯大学);University of North Carolina Chapel Hill(北卡罗来纳大学教堂山分校);University of Michigan(密歇根大学);University of California San Diego(加州大学圣地亚哥分校);Carnegie Mellon University(卡内基梅隆大学)
Absurd World: A Simple Yet Powerful Method to Absurdify the Real-world for Probing LLM Reasoning Capabilities
The Nueva School(新维学校);University of Southern California(南加州大学);Notre Dame College(诺特大学);Arizona State University(亚利桑那州立大学);National University of Singapore(新加坡国立大学)
From Human Cognition to Neural Activations: Probing the Computational Primitives of Spatial Reasoning in LLMs
School of Information Science, Beijing Language and Culture University(北京语言大学信息科学学院);School of Artificial Intelligence, Beijing Normal University(北京师范大学人工智能学院)
Answer Probing-Guided Search for Diverse Solution Exploration of LLMs
University of Science and Technology of China(中国科学技术大学);Zhongguancun Academy(中关村学院);Alibaba Group(阿里巴巴集团);Shanghai Jiao Tong University(上海交通大学);Tsinghua University(清华大学)
Efficient Test-Time Scaling via Temporal Reasoning Aggregation
School of Computer Science and Engineering, Beihang University(北航计算机科学与工程学院);Qingdao Research Institute, Beihang University(北航青岛研究院);Hangzhou Innovation Institute, Beihang University(北航杭州创新研究院)
Coherence Under Commitment: Probing Generalization and Vacuous Memorization in LLM Logical Reasoning
Department of Computer Science, Informatics Institute, Istanbul Technical University(伊斯坦布尔技术大学信息学研究所计算机科学系);School of Information Technology, Deakin University(迪肯大学信息技术学院)