Large Model Based Agents: State-of-the-Art, Cooperation Paradigms, Security and Privacy, and Future Trends

TL;DR

This paper reviews the current state, cooperation paradigms, security challenges, and future trends of large model-based agents, emphasizing their potential for autonomous collaboration and the need for secure, privacy-preserving systems.

Contribution

It provides a comprehensive overview of LM agent architectures, collaboration methods, security vulnerabilities, and proposes future research directions for robust multi-agent ecosystems.

Findings

LM agents are capable of autonomous communication and collaboration.

Security vulnerabilities in multi-agent LM systems are significant and require targeted countermeasures.

Future research should focus on robustness and privacy in LM agent ecosystems.

Abstract

With the rapid advancement of large models (LMs), the development of general-purpose intelligent agents powered by LMs has become a reality. It is foreseeable that in the near future, LM-driven general AI agents will serve as essential tools in production tasks, capable of autonomous communication and collaboration without human intervention. This paper investigates scenarios involving the autonomous collaboration of future LM agents. We review the current state of LM agents, the key technologies enabling LM agent collaboration, and the security and privacy challenges they face during cooperative operations. To this end, we first explore the foundational principles of LM agents, including their general architecture, key components, enabling technologies, and modern applications. We then discuss practical collaboration paradigms from data, computation, and knowledge perspectives to achieve connected intelligence among LM agents. After that, we analyze the security vulnerabilities and privacy risks associated with LM agents, particularly in multi-agent settings, examining underlying mechanisms and reviewing current and potential countermeasures. Lastly, we propose future research directions for building robust and secure LM agent ecosystems.