# SkillIR: Evolving Scene-Aware Skills for Agentic Image Restoration

arXiv: https://arxiv.org/abs/2609.21468 · HTML: https://mlsanity.com/paper/2609.21468/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use.
- Builds on 32 of its 45 references that are in the map.
- First posted on arXiv 18 Sep 2026.

## Placed in

- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 30 of 32)

- [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)
- [Multi-Stage Progressive Image Restoration](https://mlsanity.com/paper/2102.02808/) (2021)
- [Toward Real-World Single Image Super-Resolution: A New Benchmark and A New Model](https://mlsanity.com/paper/1904.00523/) (2019)
- [MAXIM: Multi-Axis MLP for Image Processing](https://mlsanity.com/paper/2201.02973/) (2022)
- [Component Divide-and-Conquer for Real-World Image Super-Resolution](https://mlsanity.com/paper/2008.01928/) (2020)
- [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)
- [NH-HAZE: An Image Dehazing Benchmark with Non-Homogeneous Hazy and Haze-Free Images](https://mlsanity.com/paper/2005.03560/) (2020)
- [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)
- [ProRes: Exploring Degradation-aware Visual Prompt for Universal Image Restoration](https://mlsanity.com/paper/2306.13653/) (2023)
- [Complexity Experts are Task-Discriminative Learners for Any Image Restoration](https://mlsanity.com/paper/2411.18466/) (2024)
- [Towards Flexible Blind JPEG Artifacts Removal](https://mlsanity.com/paper/2109.14573/) (2021)
- [RIDCP: Revitalizing Real Image Dehazing via High-Quality Codebook Priors](https://mlsanity.com/paper/2304.03994/) (2023)
- [I-HAZE: a dehazing benchmark with real hazy and haze-free indoor images](https://mlsanity.com/paper/1804.05091/) (2018)
- [Perceive-IR: Learning to Perceive Degradation Better for All-in-One Image Restoration](https://mlsanity.com/paper/2408.15994/) (2024)
- [A Comparative Study of Image Restoration Networks for General Backbone Network Design](https://mlsanity.com/paper/2310.11881/) (2023)
- [Towards Effective Multiple-in-One Image Restoration: A Sequential and Prompt Learning Strategy](https://mlsanity.com/paper/2401.03379/) (2024)
- [Image Restoration for Under-Display Camera](https://mlsanity.com/paper/2003.04857/) (2020)
- [Learning to Deblur using Light Field Generated and Real Defocus Images](https://mlsanity.com/paper/2204.00367/) (2022)
- [Degradation-Aware Feature Perturbation for All-in-One Image Restoration](https://mlsanity.com/paper/2505.12630/) (2025)
- [From Sky to the Ground: A Large-scale Benchmark and Simple Baseline Towards Real Rain Removal](https://mlsanity.com/paper/2308.03867/) (2023)
- [4KAgent: Agentic Any Image to 4K Super-Resolution](https://mlsanity.com/paper/2507.07105/) (2025)
- [RestoreVAR: Visual Autoregressive Generation for All-in-One Image Restoration](https://mlsanity.com/paper/2505.18047/) (2025)
- [ClearAIR: A Human-Visual-Perception-Inspired All-in-One Image Restoration](https://mlsanity.com/paper/2601.02763/) (2026)
- [Channel Consistency Prior and Self-Reconstruction Strategy Based Unsupervised Image Deraining](https://mlsanity.com/paper/2503.18703/) (2025)
- [Learning Domain-Aware Task Prompt Representations for Multi-Domain All-in-One Image Restoration](https://mlsanity.com/paper/2603.01725/) (2026)
- [Restore-R1: Efficient Image Restoration Agents via Reinforcement Learning with Multimodal LLM Perceptual Feedback](https://mlsanity.com/paper/2512.18599/) (2025)
- [TIR-Agent: Training an Explorative and Efficient Agent for Image Restoration](https://mlsanity.com/paper/2603.27742/) (2026)

## Built on by (most cited first, 1 of 1)

- [Look Before You Restore: Learning to Predict Before Acting for Agentic Image Restoration](https://mlsanity.com/paper/2610.20384/) (2026)

## Abstract (arXiv)

This paper studies agentic image restoration, in which multimodal agents coordinate specialized restoration tools to recover images affected by complex degradations. Existing restoration agents often derive complete tool-use plans from the original degraded image or retrieve previously successful trajectories, providing limited support for adapting individual actions to evolving intermediate restoration states. We find that accepted tool executions can change the residual degradation state and, consequently, the applicability of subsequent tools. To address this issue, we propose SkillIR, a skill-guided framework that represents restoration experience as degradation-centered action evidence rather than complete tool-use trajectories. SkillIR consolidates context-dependent action outcomes into scene-aware restoration skills that characterize applicable conditions, expected effects, and attributable failure cases. Instead of prescribing a complete restoration plan, the retrieved skills guide one bounded action at a time within a verified residual-state loop: each tool output is treated as a candidate, committed only after transition verification, and followed by reassessment of the active residual degradations. After each rollout, the resulting evidence is used to create, refine, or patch dynamic skills, enabling accumulated restoration experience to improve decision-making for subsequent inputs. Experiments on synthetic and real-world multi-degradation datasets demonstrate that SkillIR improves restoration quality and enables more reliable and effective tool use.