When Does Personality Composition Matter for Multi-Agent LLM Teams?
For designers of multi-agent LLM systems, this work shows that personality prompting's impact on task performance is task-dependent, with limited effect in structured tasks but significant degradation in open-ended ones.
This paper investigates whether personality composition affects multi-agent LLM team performance across three task domains, finding that effects depend on task structure: low agreeableness has little effect on coding tasks but substantially degrades performance in open-ended collaboration and bargaining.
Personality prompting shapes how large language models communicate, yet whether these behavioral shifts affect objective task outcomes remains under-explored. Prior work shows that agents prompted with low agreeableness produce adversarial language, while those prompted with high agreeableness become cooperative, but the relationship between communication style and task performance has not been systematically examined across multiple domains. In this work, we investigate whether personality composition matters for multi-agent team performance by manipulating personality traits across frontier LLMs on three task domains: structured coding, open-ended research collaboration, and competitive bargaining. We find that personality effects depend critically on task structure. In coding tasks, low agreeableness leads to large communication shifts that have little effect on milestone completion. In open-ended collaboration and bargaining, the same manipulation substantially degrades performance. We discuss implications for multi-agent system design and the limits of personality manipulation.