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

arXiv: https://arxiv.org/abs/2605.11789 · HTML: https://mlsanity.com/paper/2605.11789/

## Key facts

- No citing papers in the map yet (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 20 of its 25 references that are in the map.
- First posted on arXiv 12 May 2026.

## Placed in

- LLM agents and tool use / [Social simulation and multi-agent debate](https://mlsanity.com/agents/social-simulation-and-multi-agent-debate/)

## Builds on (most cited first, 20 of 20)

- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society](https://mlsanity.com/paper/2303.17760/) (2023)
- [RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models](https://mlsanity.com/paper/2009.11462/) (2020)
- [Towards Understanding Sycophancy in Language Models](https://mlsanity.com/paper/2310.13548/) (2023)
- [Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate](https://mlsanity.com/paper/2305.19118/) (2023)
- [Ethical and social risks of harm from Language Models](https://mlsanity.com/paper/2112.04359/) (2021)
- [Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studies](https://mlsanity.com/paper/2208.10264/) (2022)
- [Toxicity in ChatGPT: Analyzing Persona-assigned Language Models](https://mlsanity.com/paper/2304.05335/) (2023)
- [Playing repeated games with Large Language Models](https://mlsanity.com/paper/2305.16867/) (2023)
- [In-Context Impersonation Reveals Large Language Models' Strengths and Biases](https://mlsanity.com/paper/2305.14930/) (2023)
- [Context-faithful Prompting for Large Language Models](https://mlsanity.com/paper/2303.11315/) (2023)
- [Talk Isn't Always Cheap: Understanding Failure Modes in Multi-Agent Debate](https://mlsanity.com/paper/2509.05396/) (2025)
- [Anchoring Bias in Large Language Models: An Experimental Study](https://mlsanity.com/paper/2412.06593/) (2024)
- [Debate-to-Write: A Persona-Driven Multi-Agent Framework for Diverse Argument Generation](https://mlsanity.com/paper/2406.19643/) (2024)
- [Peacemaker or Troublemaker: How Sycophancy Shapes Multi-Agent Debate](https://mlsanity.com/paper/2509.23055/) (2025)
- [How Does Cognitive Bias Affect Large Language Models? A Case Study on the Anchoring Effect in Price Negotiation Simulations](https://mlsanity.com/paper/2508.21137/) (2025)
- [Understanding the Anchoring Effect of LLM with Synthetic Data: Existence, Mechanism, and Potential Mitigations](https://mlsanity.com/paper/2505.15392/) (2025)
- [Toxicity in Online Platforms and AI Systems: A Survey of Needs, Challenges, Mitigations, and Future Directions](https://mlsanity.com/paper/2509.25539/) (2025)
- [The High Cost of Incivility: Quantifying Interaction Inefficiency via Multi-Agent Monte Carlo Simulations](https://mlsanity.com/paper/2512.08345/) (2025)

## Abstract (arXiv)

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.