Cover Image

Chain-of-Thought Degrades Visual Spatial Reasoning Capabilities of Multimodal LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kancheti, Sai Srinivas, Kanade, Aditya Sanjiv, Balasubramanian, Vineeth N., Ganu, Tanuja
Format:	Preprint
Published:	2026
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

Faithful GRPO: Improving Visual Spatial Reasoning in Multimodal Language Models via Constrained Policy Optimization
by: Kancheti, Sai Srinivas, et al.
Published: (2026)

Mind's Eye: A Benchmark of Visual Abstraction, Transformation and Composition for Multimodal LLMs
by: Sinha, Rohit, et al.
Published: (2026)

Do You See Me : A Multidimensional Benchmark for Evaluating Visual Perception in Multimodal LLMs
by: Kanade, Aditya, et al.
Published: (2025)

Efficient Vocabulary-Free Fine-Grained Visual Recognition in the Age of Multimodal LLMs
by: Kuchibhotla, Hari Chandana, et al.
Published: (2025)

MMCTAgent: Multi-modal Critical Thinking Agent Framework for Complex Visual Reasoning
by: Kumar, Somnath, et al.
Published: (2024)

Can Better Text Semantics in Prompt Tuning Improve VLM Generalization?
by: Kuchibhotla, Hari Chandana, et al.
Published: (2024)

EarthSpatialBench: Benchmarking Spatial Reasoning Capabilities of Multimodal LLMs on Earth Imagery
by: Xu, Zelin, et al.
Published: (2026)

Multimodal Needle in a Haystack: Benchmarking Long-Context Capability of Multimodal Large Language Models
by: Wang, Hengyi, et al.
Published: (2024)

MM-CoT:A Benchmark for Probing Visual Chain-of-Thought Reasoning in Multimodal Models
by: Zhang, Jusheng, et al.
Published: (2025)

Bridging the Dynamic Perception Gap: Training-Free Draft Chain-of-Thought for Dynamic Multimodal Spatial Reasoning
by: Ou, Siqu, et al.
Published: (2025)

GeoChain: Multimodal Chain-of-Thought for Geographic Reasoning
by: Yerramilli, Sahiti, et al.
Published: (2025)

EmbodiedVSR: Dynamic Scene Graph-Guided Chain-of-Thought Reasoning for Visual Spatial Tasks
by: Zhang, Yi, et al.
Published: (2025)

Beyond Static Visual Tokens: Structured Sequential Visual Chain-of-Thought Reasoning
by: Guo, Guangfu, et al.
Published: (2026)

Multimodal Chain-of-Thought Reasoning in Language Models
by: Zhang, Zhuosheng, et al.
Published: (2023)

An Empirical Analysis on Spatial Reasoning Capabilities of Large Multimodal Models
by: Shiri, Fatemeh, et al.
Published: (2024)

Thought-For-Food: Reasoning Chain Induced Food Visual Question Answering
by: Jain, Riddhi, et al.
Published: (2025)

Fine-R1: Make Multi-modal LLMs Excel in Fine-Grained Visual Recognition by Chain-of-Thought Reasoning
by: He, Hulingxiao, et al.
Published: (2026)

RSVP: Reasoning Segmentation via Visual Prompting and Multi-modal Chain-of-Thought
by: Lu, Yi, et al.
Published: (2025)

VG-CoT: Towards Trustworthy Visual Reasoning via Grounded Chain-of-Thought
by: Lim, Byeonggeuk, et al.
Published: (2026)

CoRGI: Verified Chain-of-Thought Reasoning with Post-hoc Visual Grounding
by: Yi, Shixin, et al.
Published: (2025)

Let's Think with Images Efficiently! An Interleaved-Modal Chain-of-Thought Reasoning Framework with Dynamic and Precise Visual Thoughts
by: Liu, Xu, et al.
Published: (2026)

VLM-R$^3$: Region Recognition, Reasoning, and Refinement for Enhanced Multimodal Chain-of-Thought
by: Jiang, Chaoya, et al.
Published: (2025)

RBF++: Quantifying and Optimizing Reasoning Boundaries across Measurable and Unmeasurable Capabilities for Chain-of-Thought Reasoning
by: Chen, Qiguang, et al.
Published: (2025)

Advancing Ante-Hoc Explainable Models through Generative Adversarial Networks
by: Garg, Tanmay, et al.
Published: (2024)

SpatialCoT: Advancing Spatial Reasoning through Coordinate Alignment and Chain-of-Thought for Embodied Task Planning
by: Liu, Yuecheng, et al.
Published: (2025)

TorchSpatial: A Location Encoding Framework and Benchmark for Spatial Representation Learning
by: Wu, Nemin, et al.
Published: (2024)

Watch Wider and Think Deeper: Collaborative Cross-modal Chain-of-Thought for Complex Visual Reasoning
by: Lu, Wenting, et al.
Published: (2026)

Emma-X: An Embodied Multimodal Action Model with Grounded Chain of Thought and Look-ahead Spatial Reasoning
by: Sun, Qi, et al.
Published: (2024)

GEMeX-RMCoT: An Enhanced Med-VQA Dataset for Region-Aware Multimodal Chain-of-Thought Reasoning
by: Liu, Bo, et al.
Published: (2025)

Long Grounded Thoughts: Synthesizing Visual Problems and Reasoning Chains at Scale
by: Acuna, David, et al.
Published: (2025)

Masking Matters: Unlocking the Spatial Reasoning Capabilities of LLMs for 3D Scene-Language Understanding
by: Jeon, Yerim, et al.
Published: (2025)

Can Segmentation Models Understand the World? Towards Proactive Affordance Reasoning via Visual Chain-of-Thought
by: Guo, Yuchen, et al.
Published: (2026)

ImgCoT: Compressing Long Chain of Thought into Compact Visual Tokens for Efficient Reasoning of Large Language Model
by: Chen, Xiaoshu, et al.
Published: (2026)

S$^2$-MLLM: Boosting Spatial Reasoning Capability of MLLMs for 3D Visual Grounding with Structural Guidance
by: Xu, Beining, et al.
Published: (2025)

Theorem-Validated Reverse Chain-of-Thought Problem Generation for Geometric Reasoning
by: Deng, Linger, et al.
Published: (2024)

Revisiting the Necessity of Lengthy Chain-of-Thought in Vision-centric Reasoning Generalization
by: Du, Yifan, et al.
Published: (2025)

Mixture-of-Visual-Thoughts: Exploring Context-Adaptive Reasoning Mode Selection for General Visual Reasoning
by: Li, Zejun, et al.
Published: (2025)

Octopus: Agentic Multimodal Reasoning with Six-Capability Orchestration
by: Guo, Yifu, et al.
Published: (2025)

TOMATO: Assessing Visual Temporal Reasoning Capabilities in Multimodal Foundation Models
by: Shangguan, Ziyao, et al.
Published: (2024)

Swift Sampling: Selecting Temporal Surprises via Taylor Series
by: Kim, Dahye, et al.
Published: (2026)