Multi-Agent Teams Hold Experts Back

TL;DR

This paper investigates the performance of self-organizing multi-agent LLM teams, revealing they often underperform compared to individual experts due to poor expertise leveraging and consensus behaviors, highlighting a gap in emergent coordination.

Contribution

It provides the first systematic analysis of self-organizing LLM teams' ability to leverage expertise, identifying key bottlenecks and behaviors affecting team performance.

Findings

LLM teams fail to match expert performance, with up to 37.6% loss.

Expert leveraging is the main bottleneck, not identification.

Consensus-seeking reduces effective expertise utilization.

Abstract

Multi-agent LLM systems are increasingly deployed as autonomous collaborators, where agents interact freely rather than execute fixed, pre-specified workflows. In such settings, effective coordination cannot be fully designed in advance and must instead emerge through interaction. However, most prior work enforces coordination through fixed roles, workflows, or aggregation rules, leaving open the question of how well self-organizing teams perform when coordination is unconstrained. Drawing on organizational psychology, we study whether self-organizing LLM teams achieve strong synergy, where team performance matches or exceeds the best individual member. Across human-inspired and frontier ML benchmarks, we find that -- unlike human teams -- LLM teams consistently fail to match their expert agent's performance, even when explicitly told who the expert is, incurring performance losses of up to 37.6%. Decomposing this failure, we show that expert leveraging, rather than identification, is the primary bottleneck. Conversational analysis reveals a tendency toward integrative compromise -- averaging expert and non-expert views rather than appropriately weighting expertise -- which increases with team size and correlates negatively with performance. Interestingly, this consensus-seeking behavior improves robustness to adversarial agents, suggesting a trade-off between alignment and effective expertise utilization. Our findings reveal a significant gap in the ability of self-organizing multi-agent teams to harness the collective expertise of their members.