Towards Multi-Agent Reasoning Systems for Collaborative Expertise Delegation: An Exploratory Design Study
This work addresses the challenge of configuring scalable multi-agent reasoning systems for AI applications, but it is incremental as it builds on existing multi-agent concepts.
The paper tackled the problem of designing collaboration structures for multi-agent LLM systems to enhance collective reasoning, finding that integrating diverse knowledge outperforms rigid task decomposition and that expertise alignment benefits are domain-contingent, with specific gains observed in contextual reasoning tasks.
Designing effective collaboration structure for multi-agent LLM systems to enhance collective reasoning is crucial yet remains under-explored. In this paper, we systematically investigate how collaborative reasoning performance is affected by three key design dimensions: (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 knowledge consistently outperforms rigid task decomposition. 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. This work provides concrete guidelines for configuring specialized multi-agent system and identifies critical architectural trade-offs and bottlenecks for scalable multi-agent reasoning. The code will be made available upon acceptance.