Agent Discovery in Internet of Agents: Challenges and Solutions

TL;DR

This paper presents a two-stage framework for agent capability discovery in the Internet of Agents, addressing heterogeneity and scalability challenges through semantic modeling and continual discovery methods.

Contribution

It introduces a novel two-stage capability discovery framework with semantic modeling, scalable indexing, and continual updates for IoA agent collaboration.

Findings

Enhanced discovery performance in simulations

Improved scalability of agent matching

Effective context-aware agent assembly

Abstract

Rapid advances in large language models and agentic AI are driving the emergence of the Internet of Agents (IoA), a paradigm where billions of autonomous software and embodied agents interact, coordinate, and collaborate to accomplish complex tasks. A key prerequisite for such large-scale collaboration is agent capability discovery, where agents identify, advertise, and match one another's capabilities under dynamic tasks. Agent's capability in IoA is inherently heterogeneous and context-dependent, raising challenges in capability representation, scalable discovery, and long-term performance. To address these issues, this paper introduces a novel two-stage capability discovery framework. The first stage, autonomous capability announcement, allows agents to credibly publish machine-interpretable descriptions of their abilities. The second stage, task-driven capability discovery, enables context-aware search, ranking, and composition to locate and assemble suitable agents for specific tasks. Building on this framework, we propose a novel scheme that integrates semantic capability modeling, scalable and updatable indexing, and memory-enhanced continual discovery. Simulation results demonstrate that our approach enhances discovery performance and scalability. Finally, we outline a research roadmap and highlight open problems and promising directions for future IoA.