{"ID":2858998,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.07488","arxiv_id":"2510.07488","title":"Can Lessons From Human Teams Be Applied to Multi-Agent Systems? The Role of Structure, Diversity, and Interaction Dynamics","abstract":"Multi-Agent Systems (MAS) with Large Language Model (LLM)-powered agents are gaining attention, yet fewer studies explore their team dynamics. Inspired by human team science, we propose a multi-agent framework to examine core aspects of team science: structure, diversity, and interaction dynamics. We evaluate team performance across four tasks: CommonsenseQA, StrategyQA, Social IQa, and Latent Implicit Hate, spanning commonsense and social reasoning. Our results show that flat teams tend to perform better than hierarchical ones, while diversity has a nuanced impact. Interviews suggest agents are overconfident about their team performance, yet post-task reflections reveal both appreciation for collaboration and challenges in integration, including limited conversational coordination.","short_abstract":"Multi-Agent Systems (MAS) with Large Language Model (LLM)-powered agents are gaining attention, yet fewer studies explore their team dynamics. Inspired by human team science, we propose a multi-agent framework to examine core aspects of team science: structure, diversity, and interaction dynamics. We evaluate team perf...","url_abs":"https://arxiv.org/abs/2510.07488","url_pdf":"https://arxiv.org/pdf/2510.07488v2","authors":"[\"Rasika Muralidharan\",\"Haewoon Kwak\",\"Jisun An\"]","published":"2025-10-08T19:37:17Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.AI\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}