Beyond Frameworks: Unpacking Collaboration Strategies in Multi-Agent Systems
It addresses the need for scalable multi-agent systems in complex distributed tasks, shifting focus from structural frameworks to strategic mechanics, but is incremental as it builds on prior research on architectural frameworks.
This study tackled the problem of underexplored granular collaboration strategies in multi-agent systems for LLM-driven applications, finding that centralized governance, instructor-led participation, ordered interactions, and curated context summarization optimize the trade-off between decision quality and resource utilization using the proposed Token-Accuracy Ratio.
Multi-agent collaboration has emerged as a pivotal paradigm for addressing complex, distributed tasks in large language model (LLM)-driven applications. While prior research has focused on high-level architectural frameworks, the granular mechanisms governing agents, critical to performance and scalability, remain underexplored. This study systematically investigates four dimensions of collaboration strategies: (1) agent governance, (2) participation control, (3) interaction dynamics, and (4) dialogue history management. Through rigorous experimentation under two context-dependent scenarios: Distributed Evidence Integration (DEI) and Structured Evidence Synthesis (SES), we quantify the impact of these strategies on both task accuracy and computational efficiency. Our findings reveal that centralized governance, instructor-led participation, ordered interaction patterns, and instructor-curated context summarization collectively optimize the trade-off between decision quality and resource utilization with the support of the proposed Token-Accuracy Ratio (TAR). This work establishes a foundation for designing adaptive, scalable multi-agent systems, shifting the focus from structural novelty to strategic interaction mechanics.