Skip to content

Reasoning with Image Generation

Sep 2026 · arXiv.org · Vol abs/2609.16409 · 0 citations · 91 references
Computer Science

TL;DR

Across six diverse visual reasoning tasks including multi-view spatial reasoning and collision prediction, ReImaGin consistently outperforms both text-only reasoning and specialist vision-tool baselines, with gains of up to 25\%, demonstrating the advantage of flexible, generative visual reasoning.

Abstract

Chain-of-thought reasoning has revolutionized natural language processing by enabling large language models (LLMs) to decompose problems into intermediate steps before answering. Yet confining reasoning to the textual domain presents limitations for tasks requiring direct manipulation of visual representations. Recent efforts augment multimodal LLMs with external visual expert tools such as depth estimation or object detection modules, but these remain fundamentally limited by their reliance on narrow, rigid operations that cannot flexibly generate or transform visual content. We propose ReImaGin, which leverages image generation models as a flexible visual reasoning mechanism for multimodal LLMs: unlike fixed-function tools, they accept natural language commands and can perform open-ended visual operations, like removing an occlusion or generating a floorplan from multiple disjoint views of a room. Across six diverse visual reasoning tasks including multi-view spatial reasoning and collision prediction, ReImaGin consistently outperforms both text-only reasoning and specialist vision-tool baselines, with gains of up to 25\%, demonstrating the advantage of flexible, generative visual reasoning.

View source

Similar papers

Sep 2026

Distilling Visual Reasoning into Text Space

V2T first trains a teacher LVLM using interleaved visual and textual chains of thought, and then uses knowledge distillation to train a student LVLM using the teacher's logits and cross-entropy supervision from ground-truth textual reasoning.

Wen-Han Yang, Nilay Naharas, Ali Payani et al. · 0 citations
Preprint Sep 2026

GenPuzzle: Benchmarking Visual Reasoning in Image Generation Models

GenPuzzle provides a testbed for measuring progress from image rendering toward visual problem solving, and uses task-specific evaluation protocols that select the automatic judge by measuring agreement with human reference scores.

Chang-Peng Zhao, Yi-Ren Song, Jin-Peng Wang · 3 citations
Preprint Sep 2026

Thinking in Pictures: A Systematic Benchmark for Reasoning-driven Image Generation

This work introduces RIG-BENCH, a novel comprehensive benchmark that systematically evaluates Reasoning-driven Image Generation (RIG) across four cognitively demanding domains: Concept-based, Transformation-based, Pattern&Structure, and Scenario-based.

Yu-Tong Liu, Nan Huang, Xu Cao et al. · 1 citation

Skip the Talk, Re-Focus on Vision: Latent Reasoning for Reasoning Segmentation in Multimodal Large Language Models

LIRSeg is proposed, which fully replaces explicit CoT with a compact set of learnable latent tokens for reasoning segmentation, and introduces three complementary mechanisms from an information perspective: extreme-advantage sampling for selecting informative training signals, decoupled exploration-stability updates fo...

Tian-Hang Guo, Yu-Lin He, Wei Chen et al. · 0 citations
Preprint Aug 2026

GLaQ: Grounding Latent Queries in Visual Evidence for Multimodal Reasoning

GLaQ, a grounded latent-query framework that replaces sequential latent rollout with a fixed set of context-conditioned queries grounded in the original visual tokens, is introduced, suggesting that direct query-to-image grounding can recover localized evidence from the full image without external visual operations or...

Ze-Sheng Yang, Lingling Zhang, Xinyu Zhang et al. · 1 citation
Preprint Aug 2026

Multi-View Relational Distillation for Spatial Reasoning with Vision-Language Models

It is shown that MVRD makes visual representations more geometric while retaining language alignment, and generalizes to 3D scene understanding tasks such as object grounding, dense captioning, and question answering, while approaching feature fusion methods with considerably fewer added parameters and lower latency.

K. T. Nguyen, Hanbo Shim, Jinwoo Kim et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.