Flow-of-Thought: A Framework for Visual Reasoning
On the map: LLM reasoning → Spatial and embodied reasoning
Abstract (arXiv)
Mental imagery, ``seeing with the mind's eye'' is an essential aspect of human cognition. Despite rapid progress Large Language Models (LLMs) and Vision Transformers (ViTs) still underperform on tasks requiring spatial understanding. To address this, we introduce Flow-of-Thought (FoT), a framework that integrates the generation of visual sketches as intermediate reasoning steps, mimicking mental imagery in humans. We train coordinate-aware trajectory flow fields on SO(2) group orbits and cumulative shortest paths, then freeze the learned dynamics; same vs. different decisions compare competing generative hypotheses using foreground-weighted reconstruction energy. On locked tests FoT reaches 100.0% accuracy on Tetris and 99.0% on colored shapes. Under frozen transfer, the orbit-trained 2D flow improves over its endpoint-only control on BLINK Multi-view (72.2% vs. 63.9% on 133 public validation pairs), supporting continuous visual traces as an effective and interpretable representation for spatial reasoning in some out-of-distribution settings.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning. Builds on 9 of its 20 references that are in the map. First posted on arXiv 7 Oct 2026.
Builds on
9 of 20 references.
Closest ancestors · 1
Same direction, newest first
- 2024VSP: Assessing the dual challenges of perception and reasoning in spatial planning tasks for VLMs2 Jul
Other references · 8
- 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,146
- 2022Flow Matching for Generative Modelingcited by 5,426
- 2023Let's Verify Step by Stepcited by 3,598
- 2019On the Measure of Intelligencecited by 129
- 2025Latent Sketchpad: Sketching Visual Thoughts to Elicit Multimodal Reasoning in MLLMscited by 41
- 2024Self-Supervised Visual Preference Alignmentcited by 31
- 2024Chain-of-Sketch: Enabling Global Visual Reasoningcited by 3
- 2026TopoBench: Benchmarking LLMs on Hard Topological Reasoningcited by 3
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025Imagine while Reasoning in Space: Multimodal Visualization-of-Thought
- 2024Mind's Eye of LLMs: Visualization-of-Thought Elicits Spatial Reasoning in Large Language Models
- 2026TACIT: Transformation-Aware Capturing of Implicit Thought
- 2026Spectral-Progressive Thought Flow for Lightweight Multimodal Reasoning
- 2025Reasoning Path and Latent State Analysis for Multi-view Visual Spatial Reasoning: A Cognitive Science Perspective
- 2025Revisiting the Necessity of Lengthy Chain-of-Thought in Vision-centric Reasoning Generalization
- 2025From Illusion to Intention: Visual Rationale Learning for Vision-Language Reasoning
- 2025Imagine in Space: Exploring the Frontier of Spatial Intelligence and Reasoning Efficiency in Vision Language Models