SOURCE-LINKED INTELLIGENCE

SkillIR: Evolving Scene-Aware Skills for Agentic Image Restoration

arXiv · AI, language, vision and robotics · article · Sep 18, 2026 · UTC

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 sk

Read original source ↗ Open in workspace

recordType

paper

region

Global