Benchmarking and Evolving Reason-Reflect-Rectify for Reflective Visual Generation

• URL: http://arxiv.org/abs/2605.19639v1
• Date: Tue, 19 May 2026 10:24:31 GMT
• Title: Benchmarking and Evolving Reason-Reflect-Rectify for Reflective Visual Generation
• Abstract summary: We formalize the Reason-Reflect-Rectify (R3) loop as a core framework to enable multi-round Reflective Visual Generation (RVG)<n>We introduce R3-Bench, a benchmark of over 600 expert-annotated instances that quantifies iterative reasoning and rectification capabilities.<n>Experiments show that R3-Refiner achieves significant improvements on R3-Bench.
• Score: 65.7390808636333
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Text-to-Image (T2I) models and Unified Multimodal Models (UMMs) have achieved remarkable progress in visual generation. However, their reliance on a single-pass generation paradigm limits their ability to handle complex prompts requiring iterative refinement. To enable multi-round Reflective Visual Generation (RVG), we formalize the Reason-Reflect-Rectify (R^3) loop as a core framework and introduce R^3-Bench, a benchmark of over 600 expert-annotated instances that quantifies iterative reasoning and rectification capabilities. Evaluation on R^3-Bench reveals a critical gap: while state-of-the-art models can identify generation errors, they fail to generate actionable rectification instructions. To bridge this gap, we propose R^3-Refiner, a dual-stage framework leveraging Group Relative Policy Optimization (GRPO) and a Hierarchical Reward Mechanism (HRM) to better align rectification with reflective reasoning. Experiments show that R^3-Refiner achieves significant improvements on R^3-Bench (+12.0% in Reflective Verdict Score, +9.0% in Rectification Score), and can be seamlessly integrated with various MLLMs to enhance the generation quality of different T2I models on GenEval++ and T2I-CompBench. Code is available at https://github.com/xiaomoguhz/R3-Bench.

Related papers

• Improved Baselines with Representation Autoencoders [61.47127824064028]
  Representation Autoencoders (RAE) replace traditional VAE with pretrained vision encoders.<n>We find three insights which simplify and improve RAE.<n> RAEv2 leads to more than 10x faster convergence over the original RAE.
  arXiv  Detail & Related papers  (2026-05-18T12:42:34Z)
• RationalRewards: Reasoning Rewards Scale Visual Generation Both Training and Test Time [51.256131853751754]
  We show that teaching reward models to produce explicit, multi-dimensional critiques transforms them from passive evaluators into active optimization tools.<n>We introduce Preference-Anchored Rationalization (PARROT), a principled framework that recovers high-quality rationales from readily available preference data.<n>The resulting model, RationalRewards (8B), achieves state-of-the-art preference prediction among open-source reward models.
  arXiv  Detail & Related papers  (2026-04-13T15:38:09Z)
• CLEAR: Unlocking Generative Potential for Degraded Image Understanding in Unified Multimodal Models [23.357627415320025]
  multimodal models that combine understanding and generation fail to leverage their own generative capacity on degraded inputs.<n>We present CLEAR, a framework that connects the two capabilities through three progressive steps.<n> Experiments show that CLEAR substantially improves robustness on degraded inputs while preserving clean-image performance.
  arXiv  Detail & Related papers  (2026-04-06T15:54:00Z)
• RAISE: Requirement-Adaptive Evolutionary Refinement for Training-Free Text-to-Image Alignment [37.59966317174412]
  We introduce RAISE, a training-free, requirement-driven evolutionary framework for adaptive T2I generation.<n> RAISE formulates image generation as a requirement-driven adaptive scaling process.<n>On GenEval and DrawBench, RAISE attains state-of-the-art alignment.
  arXiv  Detail & Related papers  (2026-02-28T05:53:01Z)
• OCR-Agent: Agentic OCR with Capability and Memory Reflection [5.8505408398110434]
  Large Vision-Language Models (VLMs) have demonstrated significant potential on complex visual understanding tasks.<n>We propose a novel iterative self-correction framework that endows models with two key capabilities: Capability Reflection and Memory Reflection.<n> Experiments on the challenging OCRBench v2 benchmark show that OCR-Agent outperforms the current open-source SOTA model InternVL3-8B by +2.0 on English and +1.2 on Chinese subsets.
  arXiv  Detail & Related papers  (2026-02-24T16:10:27Z)
• GenAgent: Scaling Text-to-Image Generation via Agentic Multimodal Reasoning [54.42973725693]
  We introduce GenAgent, unifying visual understanding and generation through an agentic multimodal model.<n>GenAgent significantly boosts base generator(FLUX.1-dev) performance on GenEval++ and WISE.<n>Our framework demonstrates three key properties: 1) cross-tool generalization to generators with varying capabilities, 2) test-time scaling with consistent improvements across interaction rounds, and 3) task-adaptive reasoning that automatically adjusts to different tasks.
  arXiv  Detail & Related papers  (2026-01-26T14:49:04Z)
• A2R: An Asymmetric Two-Stage Reasoning Framework for Parallel Reasoning [57.727084580884075]
  Asymmetric Two-Stage Reasoning framework designed to bridge gap between a model's potential and its actual performance.<n>A2R-Efficient is a "small-to-big" variant that combines a Qwen3-4B explorer with a Qwen3-8B synthesizer.<n>Results show A2R is not only a performance-boosting framework but also an efficient and practical solution for real-world applications.
  arXiv  Detail & Related papers  (2025-09-26T08:27:03Z)
• Can We Generate Images with CoT? Let's Verify and Reinforce Image Generation Step by Step [86.69947123512836]
  Chain-of-Thought (CoT) reasoning has been extensively explored in large models to tackle complex understanding tasks.<n>We provide the first comprehensive investigation of the potential of CoT reasoning to enhance autoregressive image generation.<n>We propose the Potential Assessment Reward Model (PARM) and PARM++, specialized for autoregressive image generation.
  arXiv  Detail & Related papers  (2025-01-23T18:59:43Z)
• Vision-Language Models Can Self-Improve Reasoning via Reflection [20.196406628954303]
  Chain-of-thought (CoT) has proven to improve the reasoning capability of large language models (LLMs) We propose a self-training framework, R3V, which iteratively enhances the model's Vision-language Reasoning by Reflecting on CoT Rationales. Our approach supports self-reflection on generated solutions, further boosting performance through test-time computation.
  arXiv  Detail & Related papers  (2024-10-30T14:45:00Z)

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.