Causal-AgentIR: Self-Evolving Causal Memory for Adaptive Image Restoration Agents

2026-07-23

AI Summary

This work addresses the challenge that existing image restoration methods struggle to dynamically manage restoration knowledge due to their reliance on static tool descriptions or unstructured records. To overcome this limitation, the authors propose a hierarchical multi-agent framework equipped with self-evolving causal memory, which, for the first time, models degradation patterns, image regions, tools, operations, and quality changes as a structured causal graph. This representation enables graph-based retrieval and multi-hop causal reasoning. Through a collaborative multi-agent mechanism, the framework supports dynamic creation, deletion, modification, querying, reinforcement, and transfer of restoration knowledge. Experimental results demonstrate that the proposed approach significantly improves both restoration performance and knowledge adaptability across diverse real-world degradation scenarios.

Abstract

Image restoration agents have recently emerged as a flexible paradigm for handling diverse and unpredictable degradations in real-world scenarios. Existing agents typically formulate restoration as a tool-using process, where the agent perceives degradations, searches candidate tools, executes restoration operations, and revises the plan through reflection or rollback. However, their knowledge is often stored as static tool descriptions, manually defined degradation priors, or unstructured textual summaries, which limits the accumulation, verification, revision, and forgetting of restoration knowledge over long-term experience. In this paper, we propose Causal-AgentIR, a hierarchical multi-agent framework with self-evolving causal memory for collective image restoration intelligence. Instead of representing restoration experience as isolated textual records, Causal-AgentIR organizes degradation patterns, image regions, restoration tools, actions, quality changes, and user preferences into a structured causal memory graph. This graph supports graph-based retrieval and multi-hop causal reasoning, enabling agents to infer how specific restoration operations or tool sequences affect restoration quality under different degradation conditions. The framework further organizes multiple agents into a collaborative system, including planning, degradation analysis, tool expertise, causal memory reasoning, outcome critique, and memory curation. Through this design, restoration experience can be added, updated, merged, reinforced, ignored, or discarded according to observed quality changes and feedback, allowing the agent to maintain reliable and transferable restoration knowledge. Extensive experiments demonstrate the effectiveness of the proposed framework.

Problem

• image restoration
• causal memory
• adaptive agents
• knowledge evolution
• degradation modeling

Innovation

• causal memory
• self-evolving
• multi-agent system
• image restoration
• structured knowledge graph