Render-of-Thought: Rendering Textual Chain-of-Thought as Images for Visual Latent Reasoning

TL;DR

Render-of-Thought (RoT) transforms textual reasoning chains into images to make latent reasoning explicit, improving efficiency and traceability in large language model reasoning tasks.

Contribution

RoT is the first framework to render reasoning steps as images, enabling explicit, traceable reasoning without additional pre-training overhead.

Findings

Achieves 3-4x token compression compared to explicit CoT

Provides substantial inference acceleration

Maintains competitive reasoning performance

Abstract

Chain-of-Thought (CoT) prompting has achieved remarkable success in unlocking the reasoning capabilities of Large Language Models (LLMs). Although CoT prompting enhances reasoning, its verbosity imposes substantial computational overhead. Recent works often focus exclusively on outcome alignment and lack supervision on the intermediate reasoning process. These deficiencies obscure the analyzability of the latent reasoning chain. To address these challenges, we introduce Render-of-Thought (RoT), the first framework to reify the reasoning chain by rendering textual steps into images, making the latent rationale explicit and traceable. Specifically, we leverage the vision encoders of existing Vision Language Models (VLMs) as semantic anchors to align the vision embeddings with the textual space. This design ensures plug-and-play implementation without incurring additional pre-training overhead. Extensive experiments on mathematical and logical reasoning benchmarks demonstrate that our method achieves 3-4x token compression and substantial inference acceleration compared to explicit CoT. Furthermore, it maintains competitive performance against other methods, validating the feasibility of this paradigm. Our code is available at https://github.com/TencentBAC/RoT