# German researchers introduce ReImaGin for image-based chain-of-thought reasoning

Digest AI · Research · published 2026-09-28T07:23:00Z

Canonical: https://digestai.news/story/german-researchers-introduce-reimagin-for-image-based-chain-of-thought

## Summary

A team of researchers from Germany has developed **ReImaGin**, a vision-language model (VLM) that uses image generation as part of its internal reasoning process. Unlike previous systems that relied on bolted-on image components, ReImaGin integrates image generation as a core mechanism for tasks like depth perception, occlusion counting, and spatial mapping. The model dynamically decides when to generate images—such as filling in missing puzzle pieces or creating depth maps—to aid problem-solving, without requiring human input or predefined strategies.

The system was tested across three VLMs (**Gemini-3.1-Pro**, **GPT-5**, and **Qwen-3.5-27B**) and six visual reasoning tasks, outperforming both unaided reasoning and fixed-tool baselines like **Visual Sketchpad**. For example, **GPT-5**’s puzzle accuracy improved from **29.5%** (no tools) to **44.9%** with ReImaGin. The approach relies on an iterative loop where the model experiments with prompts to discover effective visual strategies, optimizing instructions rather than retraining models. Open-weight image generators like **FLUX.2 [dev]** and **Qwen-Image-Edit-2511** were also tested, though they showed mixed results on complex tasks.

The authors argue that image generation can serve as a general ‘visual imagination’ mechanism, reducing reliance on task-specific tools. The paper suggests this method could evolve as VLMs gain broader self-tooling capabilities.

## Key points

- ReImaGin uses image generation as part of its internal chain-of-thought reasoning, dynamically deciding when to create visual aids
- Tested on **Gemini-3.1-Pro**, **GPT-5**, and **Qwen-3.5-27B**, outperforming fixed-tool baselines in tasks like puzzle completion and occlusion counting
- Open-weight image generators like **FLUX.2 [dev]** and **Qwen-Image-Edit-2511** showed mixed performance, with **75%** of ReImaGin’s generated images deemed accurate

## Why it matters

If validated, ReImaGin could shift how VLMs approach visual reasoning by automating strategy discovery, potentially reducing reliance on human-engineered tools. This could accelerate development of general-purpose AI agents that adapt visual problem-solving on the fly.

## Sources

1. [AI That Uses Imagery in Chain-of-Thought (CoT) Reasoning](https://unite.ai/ai-that-uses-imagery-in-chain-of-thought-cot-reasoning) (Unite.AI, 2026-09-28)

## Cite

Digest AI, "German researchers introduce ReImaGin for image-based chain-of-thought reasoning", 28 September 2026, https://digestai.news/story/german-researchers-introduce-reimagin-for-image-based-chain-of-thought

---

Written by Digest AI's editorial model from the linked sources; the sources are the record. Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse
JSON: https://digestai.news/story/german-researchers-introduce-reimagin-for-image-based-chain-of-thought.json