arXiv:2502.14321v3 Announce Type: replace-cross Abstract: Large language model-based multi-agent systems have recently gained significant attention due to their potential for complex, collaborative, and intelligent problem-solving capabilities. Existing surveys typically categorize LLM-based multi-agent systems (LLM-MAS) according to their application domains or architectures, overlooking the central role of communication in coordinating agent behaviors and interactions. To address this gap, this paper presents a comprehensive survey of LLM-MAS from a communication-centric perspective. Specifi
The rapid development and adoption of large language models are pushing the boundaries of autonomous system capabilities, making multi-agent systems a critical next step.
Understanding communication in LLM-based multi-agent systems is crucial for scaling AI applications, enabling more complex problem-solving, and improving coordination efficiency.
The focus is shifting from individual LLM capabilities to how multiple LLMs can interact and communicate effectively, enhancing their collective intelligence and problem-solving through agentic systems.
- · AI software developers
- · Enterprises adopting AI agents
- · Cloud computing providers
- · Open-source AI communities
- · Monolithic software providers
- · Companies slow to adopt AI agency
- · Manual workflow specialists
Improved coordination and efficiency across complex AI tasks due to enhanced inter-agent communication.
Acceleration of autonomous system development and deployment across various industries.
The emergence of new 'agentic' economies where AI agents facilitate complex transactions and services.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.CL