mlsanityData to 7 Oct 2026

Can Lessons From Human Teams Be Applied to Multi-Agent Systems? The Role of Structure, Diversity, and Interaction Dynamics

arXiv 2510.07488 ↗First posted 8 Oct 2025cs.CL cs.AIcited by 2

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

Abstract (arXiv)

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.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 20 of its 60 references that are in the map. First posted on arXiv 8 Oct 2025.

Builds on

20 of 60 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025ReflAct: World-Grounded Decision Making in LLM Agents via Goal-State Reflection21 May
  2. 2025MultiAgentBench: Evaluating the Collaboration and Competition of LLM agents3 Mar
  3. 2024Devil's Advocate: Anticipatory Reflection for LLM Agents25 May
  4. 2023Towards Reasoning in Large Language Models via Multi-Agent Peer Review Collaboration14 Nov

Other references · 16

  1. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
  2. 2018CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledgecited by 1,793
  3. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,739
  4. 2024A Survey on LLM-as-a-Judgecited by 1,384
  5. 2023Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debatecited by 995
  6. 2021Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategiescited by 736
  7. 2023ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMscited by 297
  8. 2023PersonaLLM: Investigating the Ability of Large Language Models to Express Personality Traitscited by 229
  9. 2023Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology Viewcited by 221
  10. 2021Latent Hatred: A Benchmark for Understanding Implicit Hate Speechcited by 216
  11. 2024From Persona to Personalization: A Survey on Role-Playing Language Agentscited by 206
  12. 2023Simulating Opinion Dynamics with Networks of LLM-based Agentscited by 153
4 more
  1. 2024PersonaGym: Evaluating Persona Agents and LLMscited by 89
  2. 2024Beyond Demographics: Aligning Role-playing LLM-based Agents Using Human Belief Networkscited by 39
  3. 2024Diversity of Thought Elicits Stronger Reasoning Capabilities in Multi-Agent Debate Frameworkscited by 12
  4. 2025The Impact of Generative AI on Social Media: An Experimental Studycited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Loop-Back Authority in LLM Agent Teams: A Paired Experiment on Flat and Hierarchical Coordinationcited by 1
  2. 2026Leadership as Coordination Control: Behavioral Signatures and the Recovery-Advantage Boundary in Multi-Agent LLM Teamscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023MetaAgents: Large Language Model Based Agents for Decision-Making on Teaming
  2. 2023AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors
  3. 2026Diversity Collapse in Multi-Agent LLM Systems: Structural Coupling and Collective Failure in Open-Ended Idea Generation
  4. 2025Adaptive Human-Agent Teaming: A Review of Empirical Studies from the Process Dynamics Perspective
  5. 2025Towards Cognitive Synergy in LLM-Based Multi-Agent Systems: Integrating Theory of Mind and Critical Evaluation
  6. 2026Scaling Behavior of Single LLM-Driven Multi-Agent Systems
  7. 2026Multi-agent Scaling Across Disjunctive and Compensatory Tasks
  8. 2025Beyond Frameworks: Unpacking Collaboration Strategies in Multi-Agent Systems