Skip to content

Prompted Identity Degrades Cooperation in Multi-Agent LLM Systems

Sep 2026 · 0 citations · 61 references
Computer Science

TL;DR

It is argued that when agents are aware of each other's model family, the group splits into clusters, where agents prefer interacting with others carrying their same label, although nothing in the task rewards or asks for such a split.

Abstract

Multi-agent LLM systems increasingly mix models from several providers, yet exposing each agent's underlying model identity to its peers significantly impairs cooperation. We show that when agents are aware of each other's model family, the group splits into clusters, where agents prefer interacting with others carrying their same label, although nothing in the task rewards or asks for such a split. We argue that the label itself causes this split, which we define as $\textit{factionalism}$. We show and measure this phenomenon in two cooperative games and on a reasoning benchmark, with nine to twenty-five agents drawn from up to five open-weight model families. We further show that when the announced families are shuffled, or replaced by arbitrary labels, the factions still follow this information; when the label is removed, this behavior disappears. In strictly cooperative tasks, labeled groups spend on average $30\%$ more rounds and $55\%$ more tokens to reach a decision, and their success rate drops from $96\%$ to $81\%$. The effect replicates across tasks, group sizes and model families. Withholding identity labels from the agents is simple and effective mitigation.

View source

Similar papers

#artificial intelligence Preprint Sep 2026

Testing Interchangeability in LLM Agent Teams

Production multi-agent systems replace agents constantly, on the assumption that an agent filling a role is interchangeable with any other agent that can do the job, and agents are more fungible in task outcome than in coordination efficiency, with larger swap effects after longer formation histories.

Jian-Xi Gao, Tian-Yi Yu, Lin-Na Deng et al. · 1 citation
Preprint Aug 2026

The Interaction Tax: When Communication Erases Diversity in Multi-Agent Teams

The results suggest that multi-agent performance depends less on the number of agents than on the information they exchange, and interaction helps only when agents share the right information at the right time.

Summer Eunhyung Ann, Haokun Liu, Chen-Hao Tan · 5 citations

Theory of Scene: Breaking the Symmetry Trap in Multi-Agent LLM Coordination

Tory of Scene (ToS), a training-free reasoning schema in which each agent reads its public role, the only difference between the agents, and the task context they all observe, is proposed, which outperforms all six baselines on every benchmark, and each baseline falls far behind it in at least one setting.

Liang-Qi Yuan, Wen-Zhi Fang, Shi-Qiang Wang et al. · 1 citation

Related blog posts

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.