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

ACL ARR 2025 July Submission384 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, 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 analyze the resulting performance-computational cost trade-off, highlighting the need for more efficient communication protocol design.
Our work provides concrete guidelines for configuring multi-agent reasoning system with expertise role delegation.

Paper Type: Long

Research Area: Interpretability and Analysis of Models for NLP

Research Area Keywords: multi-agent system design, multi-agent system interpretability

Contribution Types: Model analysis & interpretability, NLP engineering experiment

Languages Studied: English

Submission Number: 384