Beyond Frameworks: Unpacking Collaboration Strategies in Multi-Agent Systems

ACL ARR 2025 February Submission2882 Authors

Abstract:

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.

Paper Type: Long

Research Area: NLP Applications

Research Area Keywords: Multi-agent Collaboration,Collaboration Strategy, Computational Cost

Contribution Types: NLP engineering experiment, Approaches low compute settings-efficiency

Languages Studied: English

Submission Number: 2882