Agent Discovery in Internet of Agents: Challenges and Solutions
By: Shaolong Guo , Yuntao Wang , Zhou Su and more
Potential Business Impact:
Lets AI agents find and work together.
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.
Similar Papers
Internet of Agents: Fundamentals, Applications, and Challenges
Multiagent Systems
Connects smart robots to work together.
Security of Internet of Agents: Attacks and Countermeasures
Cryptography and Security
Keeps smart AI helpers safe and private online.
A Layered Protocol Architecture for the Internet of Agents
Networking and Internet Architecture
Lets AI agents work together on big problems.