Group size effects and collective misalignment in LLM multi-agent systems
This addresses the problem of unpredictable collective behavior in LLM-based systems for developers and researchers, highlighting a key factor in scaling deployments, though it is incremental in exploring group size effects.
The study investigated how group size influences collective misalignment in multi-agent LLM systems, finding that interaction can amplify, introduce, or override biases, with dynamics showing non-linear, model-dependent regimes and deterministic predictions above a critical size.
Multi-agent systems of large language models (LLMs) are rapidly expanding across domains, introducing dynamics not captured by single-agent evaluations. Yet, existing work has mostly contrasted the behavior of a single agent with that of a collective of fixed size, leaving open a central question: how does group size shape dynamics? Here, we move beyond this dichotomy and systematically explore outcomes across the full range of group sizes. We focus on multi-agent misalignment, building on recent evidence that interacting LLMs playing a simple coordination game can generate collective biases absent in individual models. First, we show that collective bias is a deeper phenomenon than previously assessed: interaction can amplify individual biases, introduce new ones, or override model-level preferences. Second, we demonstrate that group size affects the dynamics in a non-linear way, revealing model-dependent dynamical regimes. Finally, we develop a mean-field analytical approach and show that, above a critical population size, simulations converge to deterministic predictions that expose the basins of attraction of competing equilibria. These findings establish group size as a key driver of multi-agent dynamics and highlight the need to consider population-level effects when deploying LLM-based systems at scale.