Agentization of Digital Assets for the Agentic Web: Concepts, Techniques, and Benchmark

2026-04-05

AI Summary

This work addresses the current lack of methods for automatically transforming digital assets into autonomous, interactive agents—a key bottleneck hindering the development of the Agentic Web. The study formally defines the A2A-Agentization process and introduces Agentization Agent, the first dedicated framework capable of automatically encapsulating digital assets into high-fidelity agents. Furthermore, it presents A2A-Agentization Bench, the first benchmark specifically designed to evaluate agent fidelity and interoperability. Experimental results demonstrate that the proposed approach effectively activates the functional capabilities of digital assets, significantly enhances agent generation quality, and enables multi-agent collaboration under the A2A protocol, thereby advancing standardized and scalable integration within the Agentic Web ecosystem.

Abstract

Agentic Web, as a new paradigm that redefines the internet through autonomous, goal-driven interactions, plays an important role in group intelligence. As the foundational semantic primitives of the Agentic Web, digital assets encapsulate interactive web elements into agents, which expand the capacities and coverage of agents in agentic web. The lack of automated methodologies for agent generation limits the wider usage of digital assets and the advancement of the Agentic Web. In this paper, we first formalize these challenges by strictly defining the A2A-Agentization process, decomposing it into critical stages and identifying key technical hurdles on top of the A2A protocol. Based on this framework, we develop an Agentization Agent to agentize digital assets for the Agentic Web. To rigorously evaluate this capability, we propose A2A-Agentization Bench, the first benchmark explicitly designed to evaluate agentization quality in terms of fidelity and interoperability. Our experiments demonstrate that our approach effectively activates the functional capabilities of digital assets and enables interoperable A2A multi-agent collaboration. We believe this work will further facilitate scalable and standardized integration of digital assets into the Agentic Web ecosystem.

Problem

• Agentization
• Digital Assets
• Agentic Web
• Autonomous Agents
• A2A Protocol

Innovation

• Agentization
• Agentic Web
• Digital Assets
• A2A Protocol
• Benchmark