SkillIR：面向智能体图像恢复的场景感知技能演化
SkillIR: Evolving Scene-Aware Skills for Agentic Image Restoration
- Zhongnan University of Economics and Law（中南财经政法大学）
- Wuhan University（武汉大学）
- Dongguan University of Technology（东莞理工学院）
- National Institute of Natural Hazards, Ministry of Emergency Management of China（中国应急管理部国家自然灾害防治研究院）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
SkillIR提出以退化为中心的动作证据技能框架，通过场景感知技能在验证循环中逐步引导工具使用，提升智能体图像恢复的质量与可靠性。
AI中文摘要：
本文研究智能体图像恢复问题，其中多模态智能体协调专门的恢复工具，以修复受复杂退化影响的图像。现有的恢复智能体通常从原始退化图像中推导完整的工具使用计划，或检索先前成功的轨迹，这为根据不断演变的中间恢复状态调整单个动作提供的支持有限。我们发现，被接受的工具执行会改变残余退化状态，进而影响后续工具的适用性。为解决这一问题，我们提出SkillIR，一个技能引导框架，将恢复经验表示为以退化为中心的动作证据，而非完整的工具使用轨迹。SkillIR将依赖于上下文的动作结果整合为场景感知的恢复技能，这些技能刻画了适用条件、预期效果和可归因的失败案例。该框架不预设完整的恢复计划，而是通过检索到的技能在验证的残余状态循环中一次引导一个有界动作：每个工具输出被视为候选，仅在转换验证通过后才被提交，随后重新评估活跃的残余退化。每次执行后，产生的证据用于创建、细化或修补动态技能，使累积的恢复经验能够改善后续输入的决策。在合成和真实世界的多退化数据集上的实验表明，SkillIR提高了恢复质量，并实现了更可靠和有效的工具使用。
英文摘要：
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.
