Internet of Agents: Fundamentals, Applications, and Challenges
Authors:
- Yuntao WangYWYuntao Wang
- Shaolong GuoSGShaolong Guo
- Yanghe PanYPYanghe Pan
- Zhou SuZSZhou Su
- Fahao ChenFCFahao Chen
- Tom H. LuanTLTom H. Luan
- Peng LiPLPeng Li
- Jiawen KangJKJiawen Kang
- Dusit NiyatoDNDusit Niyato
Preprint
Abstract
With the rapid proliferation of large language models and vision-language models, AI agents have evolved from isolated, task-specific systems into autonomous, interactive entities capable of perceiving, reasoning, and acting without human intervention. As these agents proliferate across virtual and physical environments, from virtual assistants to embodied robots, the need for a unified, agent-centric infrastructure becomes paramount. In this survey, we introduce the Internet of Agents (IoA) as a foundational framework that enables seamless interconnection, dynamic discovery, and collaborative orchestration among heterogeneous agents at scale. We begin by presenting a general IoA architecture, highlighting its hierarchical organization, distinguishing features relative to the traditional Internet, and emerging applications. Next, we analyze the key operational enablers of IoA, including capability notification and discovery, adaptive communication protocols, dynamic task matching, consensus and conflict-resolution mechanisms, and incentive models. Finally, we identify open research directions toward building resilient and trustworthy IoA ecosystems.Keywords
All Related Versions
This publication has 45 references indexed in Scilit:
- DAWN: Designing Distributed Agents in a Worldwide NetworkIEEE Access, 2025
- TDAG: A multi-agent framework based on dynamic Task Decomposition and Agent GenerationNeural Networks, 2025
- The rise and potential of large language model based agents: a surveyScience China Information Sciences, 2025
- ChatLLM network: More brains, more intelligenceAI Open, 2025
- LLM-based agentic systems in medicine and healthcareNature Machine Intelligence, 2024
- A survey on LLM-based multi-agent systems: workflow, infrastructure, and challengesVicinagearth, 2024
- Transformer based contextual text representation framework for intelligent information retrievalExpert Systems with Applications, 2023
- Learning structured communication for multi-agent reinforcement learningAutonomous Agents and Multi-Agent Systems, 2022
- Privacy-Preserving Solutions for Blockchain: Review and ChallengesIEEE Access, 2019
- Semantic annotation, indexing, and retrievalJournal of Web Semantics, 2004