EpiAgent: An Agent-Centric System for Ancient Inscription Restoration

TL;DR

EpiAgent introduces an agent-centric, hierarchical planning system utilizing LLMs for flexible, expert-level restoration of degraded ancient inscriptions, surpassing traditional methods in quality and generalization.

Contribution

It presents a novel agent-based framework that coordinates multimodal analysis and restoration tools through hierarchical planning, inspired by human epigraphers' workflows.

Findings

EpiAgent achieves superior restoration quality on real-world inscriptions.

The system demonstrates strong generalization across diverse degradation types.

It outperforms existing AI-based restoration methods.

Abstract

Ancient inscriptions, as repositories of cultural memory, have suffered from centuries of environmental and human-induced degradation. Restoring their intertwined visual and textual integrity poses one of the most demanding challenges in digital heritage preservation. However, existing AI-based approaches often rely on rigid pipelines, struggling to generalize across such complex and heterogeneous real-world degradations. Inspired by the skill-coordinated workflow of human epigraphers, we propose EpiAgent, an agent-centric system that formulates inscription restoration as a hierarchical planning problem. Following an Observe-Conceive-Execute-Reevaluate paradigm, an LLM-based central planner orchestrates collaboration among multimodal analysis, historical experience, specialized restoration tools, and iterative self-refinement. This agent-centric coordination enables a flexible and adaptive restoration process beyond conventional single-pass methods. Across real-world degraded inscriptions, EpiAgent achieves superior restoration quality and stronger generalization compared to existing methods. Our work marks an important step toward expert-level agent-driven restoration of cultural heritage. The code is available at https://github.com/blackprotoss/EpiAgent.