"Who Am I, and Who Else Is Here?" Behavioral Differentiation Without Role Assignment in Multi-Agent LLM Systems
On the map: LLM agents and tool use → Social simulation and multi-agent debate
Abstract (arXiv)
When multiple large language models interact in a shared conversation, do they develop differentiated social roles or converge toward uniform behavior? We present a controlled experimental platform that orchestrates simultaneous multi-agent discussions among 7 heterogeneous LLMs on a unified inference backend, systematically varying group composition, naming conventions, and prompt structure across 12 experimental series (208 runs, 13,786 coded messages). Each message is independently coded on six behavioral flags by two LLM judges from distinct model families (Gemini 3.1 Pro and Claude Sonnet 4.6), achieving mean Cohen's kappa = 0.78 with conservative intersection-based adjudication. Human validation on 609 randomly stratified messages confirmed coding reliability (mean kappa = 0.73 vs. Gemini). We find that (1) heterogeneous groups exhibit significantly richer behavioral differentiation than homogeneous groups (cosine similarity 0.56 vs. 0.85; p < 10^-5, r = 0.70); (2) groups spontaneously exhibit compensatory response patterns when an agent crashes; (3) revealing real model names significantly increases behavioral convergence (cosine 0.56 to 0.77, p = 0.001); and (4) removing all prompt scaffolding converges profiles to homogeneous-level similarity (p < 0.001). Critically, these behaviors are absent when agents operate in isolation, confirming that behavioral diversity is a structured, reproducible phenomenon driven by the interaction of architectural heterogeneity, group context, and prompt-level scaffolding.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use. Builds on 7 of its 18 references that are in the map. First posted on arXiv 11 Mar 2026.
Builds on
7 of 18 references.
References · 7
- 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
- 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,988
- 2023ChatDev: Communicative Agents for Software Developmentcited by 919
- 2022Out of One, Many: Using Language Models to Simulate Human Samplescited by 752
- 2022Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studiescited by 515
- 2024Replacing Judges with Juries: Evaluating LLM Generations with a Panel of Diverse Modelscited by 326
- 2024Emergent social conventions and collective bias in LLM populationscited by 123
Built on by
Citing papers per year: 2026: 1.
1 paper.
Similar, not cited
Close in wording, no citation either way
- 2025The Social Laboratory: A Psychometric Framework for Multi-Agent LLM Evaluation
- 2023Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology View
- 2026Post-Training Recipe, More Than Model Family, Shapes Multi-Agent LLM Conversational Behavior
- 2026LLMs Trust Their Own: Identity-Dependent Conformity in Multi-Agent Systems
- 2025Collaborate, Deliberate, Evaluate: How LLM Alignment Affects Coordinated Multi-Agent Outcomes
- 2025Are LLM Agents Behaviorally Coherent? Latent Profiles for Social Simulation
- 2024Rethinking the Bounds of LLM Reasoning: Are Multi-Agent Discussions the Key?
- 2024LLM Agents in Interaction: Measuring Personality Consistency and Linguistic Alignment in Interacting Populations of Large Language Models