mlsanityData to 14 Oct 2026

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

arXiv 2604.16060 ↗First posted 17 Apr 2026cs.CV cs.AIcited by 6

On the map: LLM reasoning → Spatial and embodied reasoning

also in 1 more
Abstract (arXiv)

Multimodal Reasoning Models (MRMs) leveraging Chain-of-Thought (CoT) based thinking have revolutionized mathematical and logical problem-solving. However, we show that this paradigm struggles with generalized spatial intelligence. We perform a comprehensive evaluation of seventeen models across thirteen spatial benchmarks and identify a critical gap: CoT prompting consistently degrades performance in visual spatial reasoning. Furthermore, through a novel No-Image++ ablation, we demonstrate that MRMs and CoT prompted MLMs suffer from severe shortcut learning, and hallucinate visual details from textual priors even when the image is absent. These findings challenge the efficacy of text-only CoT for spatial tasks and underscore the need for vision-centric reasoning paradigms.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning. Builds on 24 of its 35 references that are in the map. First posted on arXiv 17 Apr 2026.

Builds on

24 of 35 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025OmniSpatial: Towards Comprehensive Spatial Reasoning Benchmark for Vision Language Models3 Jun
  2. 2025MMSI-Bench: A Benchmark for Multi-Image Spatial Intelligence29 May
  3. 20243DSRBench: A Comprehensive 3D Spatial Reasoning Benchmark10 Dec

Other references · 21

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  3. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  4. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  5. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  6. 2025Qwen2.5-VL Technical Reportcited by 5,587
  7. 2024GPT-4o System Cardcited by 4,588
  8. 2025Qwen3-VL Technical Reportcited by 2,793
  9. 2024LLaVA-OneVision: Easy Visual Task Transfercited by 2,719
  10. 2025InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiencycited by 1,510
  11. 2024Tulu 3: Pushing Frontiers in Open Language Model Post-Trainingcited by 1,053
  12. 2025OpenAI GPT-5 System Cardcited by 989
9 more
  1. 2025Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Modelscited by 665
  2. 2025R1-Onevision: Advancing Generalized Multimodal Reasoning through Cross-Modal Formalizationcited by 370
  3. 2025VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learningcited by 323
  4. 2025SoTA with Less: MCTS-Guided Sample Selection for Data-Efficient Visual Reasoning Self-Improvementcited by 145
  5. 2025MindCube: Spatial Mental Modeling from Limited Viewscited by 95
  6. 2025Grounded Reinforcement Learning for Visual Reasoningcited by 83
  7. 2025Traceable Evidence Enhanced Visual Grounded Reasoning: Evaluation and Methodologycited by 69
  8. 2025GThinker: Towards General Multimodal Reasoning via Cue-Guided Rethinkingcited by 15
  9. 2025Vision-G1: Towards General Vision Language Reasoning with Multi-Domain Data Curationcited by 13

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 6.

6 papers.

  1. 2026LatentOmni: Rethinking Omni-Modal Understanding via Unified Audio-Visual Latent Reasoningcited by 7
  2. 2026Beyond Visual CoT: Internalized Visual Thinking for Proactive Video Reasoningcited by 1
  3. 2026Knowing Isn't Always Saying: When Do Spatial Encodings Reach Answers in Vision-Language Models?cited by 1
  4. 2026Evaluating Multi-Turn Multimodal Diagnostic Reasoning on Challenging Real-World Clinical Casescited by 0
  5. 2026Separating perception from reasoning in vision-language models: a model-free render ceiling for crystal structurescited by 0
  6. 2026Uruqi: Learning Spatial Cognition from Visual Experiencecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Imagine while Reasoning in Space: Multimodal Visualization-of-Thought
  2. 2026Look Light, Think Heavy: What Multimodal Chain-of-Thought Reasoning Can and Cannot Do
  3. 2026When More Is Less: A Systematic Analysis of Spatial and Commonsense Information for Visual Spatial Reasoning
  4. 2025Bridging the Dynamic Perception Gap: Training-Free Draft Chain-of-Thought for Dynamic Multimodal Spatial Reasoning
  5. 2025MM-CoT:A Benchmark for Probing Visual Chain-of-Thought Reasoning in Multimodal Models
  6. 2025Spatial Reasoning in Multimodal Large Language Models: A Survey of Tasks, Benchmarks and Methods
  7. 2026Faithful GRPO: Improving Visual Spatial Reasoning in Multimodal Language Models via Constrained Policy Optimization
  8. 2025Thinking with Images for Multimodal Reasoning: Foundations, Methods, and Future Frontiers