Beyond Inefficiency: Systemic Costs of Incivility in Multi-Agent Monte Carlo Simulations

TL;DR

This study uses multi-agent LLM simulations to systematically analyze how incivility impacts debate efficiency, confirming prior findings and revealing effects of model size and first-mover advantage.

Contribution

It introduces a controlled simulation framework to quantify the systemic costs of incivility in multi-agent debates across different model scales.

Findings

Toxicity increases debate convergence time by 25%.

Smaller models experience greater delays due to toxicity.

Initiating the debate gives a significant advantage regardless of toxicity.

Abstract

Unconstructive debate and uncivil communication carry well-documented costs for productivity and cohesion, yet isolating their effect on operational efficiency has proven difficult. Human subject research in this domain is constrained by ethical oversight, limited reproducibility, and the inherent unpredictability of naturalistic settings. We address this gap by leveraging Large Language Model (LLM) based Multi-Agent Systems as a controlled sociological sandbox, enabling systematic manipulation of communicative behavior at scale. Using a Monte Carlo simulation framework, we generate thousands of structured 1-on-1 adversarial debates across varying toxicity conditions, measuring convergence time, defined as the number of rounds required to reach a conclusion, as a proxy for interactional efficiency. Building on a prior study, we replicate and extend its findings across two additional LLM agents of varying parameter size, allowing us to assess whether the effects of toxic behavior on debate dynamics generalize across model scale. The convergence latency of 25% reported in the previous study was confirmed. It was found that this latency is significantly bigger for models with fewer parameters. We further identify a significant first-mover advantage, whereby the agent initiating the discussion wins significantly above chance regardless of toxicity condition.