# Q-Agent: Quality-Driven Chain-of-Thought Image Restoration Agent through Robust Multimodal Large Language Model

arXiv: https://arxiv.org/abs/2504.07148 · HTML: https://mlsanity.com/paper/2504.07148/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Apr 2025.

## Built on by (most cited first, 15 of 15)

- [TIR-Agent: Training an Explorative and Efficient Agent for Image Restoration](https://mlsanity.com/paper/2603.27742/) (2026)
- [OPERA: An Agent for Image Restoration with End-to-End Joint Planning-Execution Optimization](https://mlsanity.com/paper/2605.22104/) (2026)
- [PaAgent: Portrait-Aware Image Restoration Agent via Subjective-Objective Reinforcement Learning](https://mlsanity.com/paper/2603.17055/) (2026)
- [Task-Guided Prompting for Unified Remote Sensing Image Restoration](https://mlsanity.com/paper/2604.02742/) (2026)
- [DiTTo: Scalable Order-aware All-in-One Image Restoration Agent](https://mlsanity.com/paper/2605.30915/) (2026)
- [Who is a Better Talker: Subjective and Objective Quality Assessment for AI-Generated Talking Heads](https://mlsanity.com/paper/2507.23343/) (2025)
- [Derain-Agent: A Plug-and-Play Agent Framework for Rainy Image Restoration](https://mlsanity.com/paper/2603.11866/) (2026)
- [An Evolutionary Agentic Approach for Open-ended Image Quality Perception](https://mlsanity.com/paper/2609.22942/) (2026)
- [VQ-Jarvis: Retrieval-Augmented Video Restoration Agent with Sharp Vision and Fast Thought](https://mlsanity.com/paper/2603.22998/) (2026)
- [RIRF: Reasoning Image Restoration Framework](https://mlsanity.com/paper/2604.09511/) (2026)
- [EvoIR-Agent: Self-Evolving Image Restoration Agentic System via Experience-Driven Learning](https://mlsanity.com/paper/2605.22208/) (2026)
- [Universal Image Restoration via Internalized Chain-of-Thought Reasoning](https://mlsanity.com/paper/2606.17557/) (2026)
- [EORestore-Agent: Fidelity-Guided Agentic Restoration of Remote Sensing Images with Composite Degradations](https://mlsanity.com/paper/2610.06196/) (2026)
- [HarnessIR: Harnessing Multimodal Foundation Models for Universal Real-World Image Restoration](https://mlsanity.com/paper/2610.10133/) (2026)
- [Look Before You Restore: Learning to Predict Before Acting for Agentic Image Restoration](https://mlsanity.com/paper/2610.20384/) (2026)

## Abstract (arXiv)

Image restoration (IR) often faces various complex and unknown degradations in real-world scenarios, such as noise, blurring, compression artifacts, and low resolution, etc. Training specific models for specific degradation may lead to poor generalization. To handle multiple degradations simultaneously, All-in-One models might sacrifice performance on certain types of degradation and still struggle with unseen degradations during training. Existing IR agents rely on multimodal large language models (MLLM) and a time-consuming rolling-back selection strategy neglecting image quality. As a result, they may misinterpret degradations and have high time and computational costs to conduct unnecessary IR tasks with redundant order. To address these, we propose a Quality-Driven agent (Q-Agent) via Chain-of-Thought (CoT) restoration. Specifically, our Q-Agent consists of robust degradation perception and quality-driven greedy restoration. The former module first fine-tunes MLLM, and uses CoT to decompose multi-degradation perception into single-degradation perception tasks to enhance the perception of MLLMs. The latter employs objective image quality assessment (IQA) metrics to determine the optimal restoration sequence and execute the corresponding restoration algorithms. Experimental results demonstrate that our Q-Agent achieves superior IR performance compared to existing All-in-One models.