Towards Multi-Agent Reasoning Systems for Collaborative Expertise Delegation: An Exploratory Design Study

ACL ARR 2025 May Submission776 Authors

Abstract:

Designing effective collaboration structure for multi-agent systems to stimulate collective reasoning capability is crucial yet remains under-explored.
In this paper, we systematically investigate how collaborative reasoning performance is affected by three key design factors: (1) expertise-domain alignment, (2) collaboration paradigm (structured workflow vs. diversity-driven integration), and (3) system scale.
Our findings reveal that expertise alignment benefits are highly domain-contingent, proving most effective for contextual reasoning tasks.
Furthermore, collaboration focused on integrating diverse responses consistently outperforms sequential functional cooperation.
Finally, we empirically explore the impact of scaling the multi-agent system with expertise specialization and study the computational trade off, highlighting the need for more efficient communication protocol design.
Our work provides concrete guidelines for configuring specialized multi-agent system and identifies critical architectural trade-offs and bottlenecks for scalable multi-agent reasoning.

Paper Type: Long

Research Area: NLP Applications

Research Area Keywords: Multi-agent;Reasoning;Expertise Specialization of LLMs

Contribution Types: Model analysis & interpretability, NLP engineering experiment

Languages Studied: English

Keywords: multi-agent system, reasoning

Submission Number: 776