# Q-DeepSight: Incentivizing Thinking with Images for Image Quality Assessment and Refinement

arXiv: https://arxiv.org/abs/2604.16858 · HTML: https://mlsanity.com/paper/2604.16858/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 24 of its 63 references that are in the map.
- First posted on arXiv 18 Apr 2026.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)

## Builds on (most cited first, 24 of 24)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [Emerging Properties in Unified Multimodal Pretraining](https://mlsanity.com/paper/2505.14683/) (2025)
- [Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels](https://mlsanity.com/paper/2312.17090/) (2023)
- [DeepEyes: Incentivizing "Thinking with Images" via Reinforcement Learning](https://mlsanity.com/paper/2505.14362/) (2025)
- [Pixel Reasoner: Incentivizing Pixel-Space Reasoning with Curiosity-Driven Reinforcement Learning](https://mlsanity.com/paper/2505.15966/) (2025)
- [Seedream 4.0: Toward Next-generation Multimodal Image Generation](https://mlsanity.com/paper/2509.20427/) (2025)
- [Thinking with Images for Multimodal Reasoning: Foundations, Methods, and Future Frontiers](https://mlsanity.com/paper/2506.23918/) (2025)
- [OpenThinkIMG: Learning to Think with Images via Visual Tool Reinforcement Learning](https://mlsanity.com/paper/2505.08617/) (2025)
- [DeepEyesV2: Toward Agentic Multimodal Model](https://mlsanity.com/paper/2511.05271/) (2025)
- [Mini-o3: Scaling Up Reasoning Patterns and Interaction Turns for Visual Search](https://mlsanity.com/paper/2509.07969/) (2025)
- [Perception-Aware Policy Optimization for Multimodal Reasoning](https://mlsanity.com/paper/2507.06448/) (2025)
- [Q-Insight: Understanding Image Quality via Visual Reinforcement Learning](https://mlsanity.com/paper/2503.22679/) (2025)
- [Unified Multimodal Chain-of-Thought Reward Model through Reinforcement Fine-Tuning](https://mlsanity.com/paper/2505.03318/) (2025)
- [VisualQuality-R1: Reasoning-Induced Image Quality Assessment via Reinforcement Learning to Rank](https://mlsanity.com/paper/2505.14460/) (2025)
- [Degradation-Guided One-Step Image Super-Resolution with Diffusion Priors](https://mlsanity.com/paper/2409.17058/) (2024)
- [An Intelligent Agentic System for Complex Image Restoration Problems](https://mlsanity.com/paper/2410.17809/) (2024)
- [Enhancing Descriptive Image Quality Assessment with A Large-scale Multi-modal Dataset](https://mlsanity.com/paper/2405.18842/) (2024)
- [4KAgent: Agentic Any Image to 4K Super-Resolution](https://mlsanity.com/paper/2507.07105/) (2025)
- [Perceive, Understand and Restore: Real-World Image Super-Resolution with Autoregressive Multimodal Generative Models](https://mlsanity.com/paper/2503.11073/) (2025)
- [VQAThinker: Exploring Generalizable and Explainable Video Quality Assessment via Reinforcement Learning](https://mlsanity.com/paper/2508.06051/) (2025)
- [Zoom-IQA: Image Quality Assessment with Reliable Region-Aware Reasoning](https://mlsanity.com/paper/2601.02918/) (2026)
- [UARE: A Unified Vision-Language Model for Image Quality Assessment, Restoration, and Enhancement](https://mlsanity.com/paper/2512.06750/) (2025)

## Abstract (arXiv)

Image Quality Assessment (IQA) models are increasingly deployed as perceptual critics to guide generative models and image restoration. This role demands not only accurate scores but also actionable, localized feedback. However, current MLLM-based methods adopt a single-look, language-only paradigm, which departs from human evidence-seeking judgment and yields weakly grounded rationales, limiting their reliability for in-the-loop refinement. We propose Q-DeepSight, a think-with-image framework that emulates this human-like process. It performs interleaved Multimodal Chain-of-Thought (iMCoT) with tool-augmented evidence acquisition (e.g., crop-and-zoom) to explicitly determine where quality degrades and why. To train these long iMCoT trajectories via reinforcement learning, we introduce two techniques: Perceptual Curriculum Reward (PCR) to mitigate reward sparsity and Evidence Gradient Filtering (EGF) to improve credit assignment for visually-grounded reasoning. Q-DeepSight achieves state-of-the-art performance across diverse benchmarks, including natural, restored, and AI-generated content. Furthermore, we demonstrate its practical value with Perceptual-in-Generation (PiG), a training-free framework where Q-DeepSight's diagnoses guide iterative image enhancement, effectively closing the loop between assessment and refinement.