# Restore-R1: Efficient Image Restoration Agents via Reinforcement Learning with Multimodal LLM Perceptual Feedback

arXiv: https://arxiv.org/abs/2512.18599 · HTML: https://mlsanity.com/paper/2512.18599/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Image editing and quality assessment, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 55 of its 74 references that are in the map.
- First posted on arXiv 21 Dec 2025.

## Placed in

- Multimodal LLMs / vision-language models / [Image editing and quality assessment](https://mlsanity.com/mllm/image-editing-and-quality-assessment/)
- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 30 of 55)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [Trust Region Policy Optimization](https://mlsanity.com/paper/1502.05477/) (2015)
- [High-Dimensional Continuous Control Using Generalized Advantage Estimation](https://mlsanity.com/paper/1506.02438/) (2015)
- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [Restormer: Efficient Transformer for High-Resolution Image Restoration](https://mlsanity.com/paper/2111.09881/) (2021)
- [MUSIQ: Multi-scale Image Quality Transformer](https://mlsanity.com/paper/2108.05997/) (2021)
- [Exploring CLIP for Assessing the Look and Feel of Images](https://mlsanity.com/paper/2207.12396/) (2022)
- [Uformer: A General U-Shaped Transformer for Image Restoration](https://mlsanity.com/paper/2106.03106/) (2021)
- [Multi-Stage Progressive Image Restoration](https://mlsanity.com/paper/2102.02808/) (2021)
- [The Perception-Distortion Tradeoff](https://mlsanity.com/paper/1711.06077/) (2017)
- [MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessment](https://mlsanity.com/paper/2204.08958/) (2022)
- [Benchmarking Single Image Dehazing and Beyond](https://mlsanity.com/paper/1712.04143/) (2017)
- [Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming](https://mlsanity.com/paper/1907.07484/) (2019)
- [Learning Enriched Features for Real Image Restoration and Enhancement](https://mlsanity.com/paper/2003.06792/) (2020)
- [MAXIM: Multi-Axis MLP for Image Processing](https://mlsanity.com/paper/2201.02973/) (2022)
- [Vision Transformers for Single Image Dehazing](https://mlsanity.com/paper/2204.03883/) (2022)
- [Teaching Large Language Models to Regress Accurate Image Quality Scores using Score Distribution](https://mlsanity.com/paper/2501.11561/) (2025)
- [InstructIR: High-Quality Image Restoration Following Human Instructions](https://mlsanity.com/paper/2401.16468/) (2024)
- [Controlling Vision-Language Models for Multi-Task Image Restoration](https://mlsanity.com/paper/2310.01018/) (2023)
- [Depicting Beyond Scores: Advancing Image Quality Assessment through Multi-modal Language Models](https://mlsanity.com/paper/2312.08962/) (2023)
- [AutoDIR: Automatic All-in-One Image Restoration with Latent Diffusion](https://mlsanity.com/paper/2310.10123/) (2023)

## Built on by (most cited first, 6 of 6)

- [TIR-Agent: Training an Explorative and Efficient Agent for Image Restoration](https://mlsanity.com/paper/2603.27742/) (2026)
- [Causal-AgentIR: Self-Evolving Causal Memory for Adaptive Image Restoration Agents](https://mlsanity.com/paper/2607.21125/) (2026)
- [SkillIR: Evolving Scene-Aware Skills for Agentic Image Restoration](https://mlsanity.com/paper/2609.21468/) (2026)
- [MUSE: A Unified Agentic Harness for MLLMs](https://mlsanity.com/paper/2606.03005/) (2026)
- [EORestore-Agent: Fidelity-Guided Agentic Restoration of Remote Sensing Images with Composite Degradations](https://mlsanity.com/paper/2610.06196/) (2026)
- [Look Before You Restore: Learning to Predict Before Acting for Agentic Image Restoration](https://mlsanity.com/paper/2610.20384/) (2026)

## Abstract (arXiv)

Complex image restoration aims to recover high-quality images from inputs affected by multiple degradations such as blur, noise, rain, and compression artifacts. Recent restoration agents, powered by vision-language models and large language models, offer promising restoration capabilities but suffer from significant efficiency bottlenecks due to reflection, rollback, and iterative tool searching. Moreover, their performance heavily depends on degradation recognition models that require extensive annotations for training, limiting their applicability in label-free environments. To address these limitations, we propose a policy optimization-based restoration framework that learns an lightweight agent to determine tool-calling sequences. The agent operates in a sequential decision process, selecting the most appropriate restoration operation at each step to maximize final image quality. To enable training within label-free environments, we introduce a novel reward mechanism driven by multimodal large language models, which act as human-aligned evaluator and provide perceptual feedback for policy improvement. Once trained, our agent executes a deterministic restoration plans without redundant tool invocations, significantly accelerating inference while maintaining high restoration quality. Extensive experiments show that despite using no supervision, our method matches SOTA performance on full-reference metrics and surpasses existing approaches on no-reference metrics across diverse degradation scenarios.