Agent Discovery in Internet of Agents: Challenges and Solutions

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Guo, Shaolong, Wang, Yuntao, Su, Zhou, Pan, Yanghe, Hu, Qinnan, Luan, Tom H.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918383995322368
author Guo, Shaolong
Wang, Yuntao
Su, Zhou
Pan, Yanghe
Hu, Qinnan
Luan, Tom H.
author_facet Guo, Shaolong
Wang, Yuntao
Su, Zhou
Pan, Yanghe
Hu, Qinnan
Luan, Tom H.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2511_19113
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Agent Discovery in Internet of Agents: Challenges and Solutions
Guo, Shaolong
Wang, Yuntao
Su, Zhou
Pan, Yanghe
Hu, Qinnan
Luan, Tom H.
Networking and Internet Architecture
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.
title Agent Discovery in Internet of Agents: Challenges and Solutions
topic Networking and Internet Architecture
url https://arxiv.org/abs/2511.19113