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

• URL: http://arxiv.org/abs/2609.02864v1
• Date: Wed, 02 Sep 2026 17:48:02 GMT
• Title: Thinking in Pictures: A Systematic Benchmark for Reasoning-driven Image Generation
• Abstract summary: Unified generative models (UGMs) and world simulators have achieved unprecedented results in visual perception and synthesis.<n>These models rely on surface-level event alignment, leaving the capacity for high-level visual reasoning underexplored.<n>We introduce RIG-BENCH, a novel comprehensive benchmark that systematically evaluates Reasoning-driven Image Generation (RIG) across four cognitively demanding domains.
• Score: 40.047506660824915
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent advancements in unified generative models (UGMs) and world simulators have achieved unprecedented results in visual perception and synthesis. However, these models primarily rely on surface-level event alignment, leaving the capacity for high-level visual reasoning underexplored. True visual generative intelligence demands "Reasoning-to-Generation", an ability to infer latent rules from visual inputs and manifest solutions through precise, logically constrained visual outcomes. We introduce 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. Featuring 2000 curated samples, RIG-BENCH serves as a rigorous stress test for RIG. Our extensive evaluations of state-of-the-art UGMs and image/video generation models reveal a significant reasoning-generation gap, wherein models frequently produce locally plausible but globally illogical outputs. RIG-BENCH provides a vital diagnostic framework to guide the development of next-generation, logically grounded UGMs and world simulators.

Related papers

• Do Transformations Reveal the Truth? Generative Residual Learning for Generalized AI-Generated Image Detection [2.2672499384619993]
  GenRes is a novel framework for generative residual learning via a neural tensor network.<n>GenRes++ employs a learnable attention mechanism to aggregate relational features across multiple transformed samples.<n>Experiments on multiple benchmark datasets demonstrate that the proposed GenRes++ approach outperforms existing methods.
  arXiv  Detail & Related papers  (2026-07-09T16:36:54Z)
• RS-Gen: A Multi-Stage Agentic Framework for Reasoning and Search-Augmented Image Generation [12.610942044025473]
  We propose RS-Gen: a plug-and-play, training-free, multi-stage image agentic framework.<n> RS-Gen innovatively introduces a "Questioning-and-Solving" closed-loop mechanism to accurately identify logical issues and knowledge gaps.<n>On the WISE Verified and RISEBench benchmarks, RS-Gen yields substantial absolute performance gains of 0.313 for Qwen-Image and 19.70 for Qwen-Image-Edit-2511, respectively.
  arXiv  Detail & Related papers  (2026-06-22T12:09:29Z)
• UniG2U-Bench: Do Unified Models Advance Multimodal Understanding? [50.92401586025528]
  Unified multimodal models have recently demonstrated strong generative capabilities, yet whether and when generation improves understanding remains unclear.<n>We introduce UniG2U-Bench, a comprehensive benchmark categorizing generation-to-understanding (G2U) evaluation into 7 regimes and 30 subtasks.
  arXiv  Detail & Related papers  (2026-03-03T18:36:16Z)
• RL-RIG: A Generative Spatial Reasoner via Intrinsic Reflection [18.52946282633359]
  RL-RIG is a Reinforcement Learning framework for Reflection-based Image Generation.<n>We develop Reflection-GRPO to train the VLM Actor for edit prompts and the Image Editor for better image quality under a given prompt.<n> Experimental results show that RL-RIG outperforms existing state-of-the-art open-source models by up to 11% in terms of controllable and precise spatial reasoning in image generation.
  arXiv  Detail & Related papers  (2026-02-23T15:39:53Z)
• Can World Simulators Reason? Gen-ViRe: A Generative Visual Reasoning Benchmark [48.02995109011304]
  Video generation models have emerged as potential world simulators through Chain-of-Frames (CoF) reasoning.<n>Existing benchmarks, focusing on fidelity or alignment, do not assess CoF reasoning.<n>We introduce Gen-ViRe, a framework grounded in cognitive science and real-world AI applications.
  arXiv  Detail & Related papers  (2025-11-17T19:11:39Z)
• RAG-IGBench: Innovative Evaluation for RAG-based Interleaved Generation in Open-domain Question Answering [50.42577862494645]
  We present RAG-IGBench, a benchmark designed to evaluate the task of Interleaved Generation based on Retrieval-Augmented Generation (RAG-IG) in open-domain question answering.<n>RAG-IG integrates multimodal large language models (MLLMs) with retrieval mechanisms, enabling the models to access external image-text information for generating coherent multimodal content.
  arXiv  Detail & Related papers  (2025-10-11T03:06:39Z)
• ReasonGen-R1: CoT for Autoregressive Image generation models through SFT and RL [54.100889131719626]
  Chain-of-thought reasoning and reinforcement learning have driven breakthroughs in NLP.<n>We introduce ReasonGen-R1, a framework that imbues an autoregressive image generator with explicit text-based "thinking" skills.<n>We show that ReasonGen-R1 consistently outperforms strong baselines and prior state-of-the-art models.
  arXiv  Detail & Related papers  (2025-05-30T17:59:48Z)
• Envisioning Beyond the Pixels: Benchmarking Reasoning-Informed Visual Editing [84.16442052968615]
  We introduce RISEBench, the first benchmark for evaluating Reasoning-Informed viSual Editing (RISE)<n>RISEBench focuses on four key reasoning categories: Temporal, Causal, Spatial, and Logical Reasoning.<n>We conduct experiments evaluating nine prominent visual editing models, comprising both open-source and proprietary models.
  arXiv  Detail & Related papers  (2025-04-03T17:59:56Z)
• RealRAG: Retrieval-augmented Realistic Image Generation via Self-reflective Contrastive Learning [54.07026389388881]
  We present the first real-object-based retrieval-augmented generation framework (RealRAG)<n>RealRAG augments fine-grained and unseen novel object generation by learning and retrieving real-world images to overcome the knowledge gaps of generative models.<n>Our framework integrates fine-grained visual knowledge for the generative models, tackling the distortion problem and improving the realism for fine-grained object generation.
  arXiv  Detail & Related papers  (2025-02-02T16:41:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.