Multi-Agent Collaboration Mechanisms: A Survey of LLMs

By Khanh-Tung Tran, Dung Dao, Minh-Duong Nguyen, Quoc-Viet Pham, Barry O'Sullivan, Hoang D. Nguyen. arXiv.org, 2025

515 citations recorded by the source corpus.

With recent advances in Large Language Models (LLMs), Agentic AI has become phenomenal in real-world applications, moving toward multiple LLM-based agents to perceive, learn, reason, and act collaboratively. These LLM-based Multi-Agent Systems (MASs) enable groups of intelligent agents to coordinate and solve complex tasks collectively at scale, transitioning from isolated models to collaboration-centric approaches. This work provides an extensive survey of the collaborative aspect of MASs and introduces an extensible framework to guide future research. Our framework characterizes collaboration mechanisms based on key dimensions: actors (agents involved), types (e.g., cooperation, competition, or coopetition), structures (e.g., peer-to-peer, centralized, or distributed), strategies (e.g., role-based or model-based), and coordination protocols. Through a review of existing methodologies, our findings serve as a foundation for demystifying and advancing LLM-based MASs toward more intelligent and collaborative solutions for complex, real-world use cases. In addition, various applications of MASs across diverse domains, including 5G/6G networks, Industry 5.0, question answering, and social and cultural settings, are also investigated, demonstrating their wider adoption and broader impacts. Finally, we identify key lessons learned, open challenges, and potential research directions of MASs towards artificial collective intelligence.

View Paper: https://www.semanticscholar.org/paper/1d3de3a8eaac916f4eca09930ed8b593a10f5a46

Citations in the corpus

• AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges (2025, unknown): “A practical illustration (Figure 10c) of AI Agents in personalized content recommendation and basic data reporting can be found in e-commerce and enterprise analytics systems.”
• A Survey on the Memory Mechanism of Large Language Model-based Agents (2024, unknown): “Chen et al. [14], Guo et al. [40], Li et al. [83], and Tran et al. [155] provide comprehensive reviews on multi-agents.”
• SWE-Adept: An LLM-Based Agentic Framework for Deep Codebase Analysis and Structured Issue Resolution (2026, unknown): “The two agents operate in separate context windows with distinct tool access, preventing the full search-and-edit trace from accumulating within a single agent (Tran et al., 2025).”