The Chameleon's Limit: Investigating Persona Collapse and Homogenization in Large Language Models
For researchers building multi-agent simulations, this reveals a critical failure mode where LLM-based agents lack population diversity, undermining simulation validity.
The paper identifies 'Persona Collapse' in LLMs, where agents assigned distinct profiles converge into homogeneous behavior. Evaluating ten LLMs on personality, moral reasoning, and self-introduction, they find that models with highest per-persona fidelity produce the most stereotyped populations.
Applications based on large language models (LLMs), such as multi-agent simulations, require population diversity among agents. We identify a pervasive failure mode we term \emph{Persona Collapse}: agents each assigned a distinct profile nonetheless converge into a narrow behavioral mode, producing a homogeneous simulated population. To quantify persona collapse, we propose a framework that measures how much of the persona space a population occupies (Coverage), how evenly agents spread across it (Uniformity), and how rich the resulting behavioral patterns are (Complexity). Evaluating ten LLMs on personality simulation (BFI-44), moral reasoning, and self-introduction, we observe persona collapse along two axes: (1) Dimensions: a model can appear diverse on one axis yet structurally degenerate on another, and (2) Domains: the same model may collapse the most in personality yet be the most diverse in moral reasoning. Furthermore, item-level diagnostics reveal that behavioral variation tracks coarse demographic stereotypes rather than the fine-grained individual differences specified in each persona. Counter-intuitively, \textbf{the models achieving the highest per-persona fidelity consistently produce the most stereotyped populations}. We release our toolkit and data to support population-level evaluation of LLMs.