# Harm in AI-Driven Societies: An Audit of Toxicity Adoption on Chirper.ai

arXiv: https://arxiv.org/abs/2601.01090 · HTML: https://mlsanity.com/paper/2601.01090/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 54 references that are in the map.
- First posted on arXiv 3 Jan 2026.

## Builds on (most cited first, 21 of 21)

- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Ex Machina: Personal Attacks Seen at Scale](https://mlsanity.com/paper/1610.08914/) (2016)
- [AgentSociety: Large-Scale Simulation of LLM-Driven Generative Agents Advances Understanding of Human Behaviors and Society](https://mlsanity.com/paper/2502.08691/) (2025)
- [Evaluation and Benchmarking of LLM Agents: A Survey](https://mlsanity.com/paper/2507.21504/) (2025)
- [The Rise of Social Bots](https://mlsanity.com/paper/1407.5225/) (2014)
- [The spread of low-credibility content by social bots](https://mlsanity.com/paper/1707.07592/) (2017)
- [Shall We Team Up: Exploring Spontaneous Cooperation of Competing LLM Agents](https://mlsanity.com/paper/2402.12327/) (2024)
- [GenAI Against Humanity: Nefarious Applications of Generative Artificial Intelligence and Large Language Models](https://mlsanity.com/paper/2310.00737/) (2023)
- [Disinformation and Social Bot Operations in the Run Up to the 2017 French Presidential Election](https://mlsanity.com/paper/1707.00086/) (2017)
- [A Survey on Responsible LLMs: Inherent Risk, Malicious Use, and Mitigation Strategy](https://mlsanity.com/paper/2501.09431/) (2025)
- [Unmasking Conversational Bias in AI Multiagent Systems](https://mlsanity.com/paper/2501.14844/) (2025)
- [Antisocial Behavior in Online Discussion Communities](https://mlsanity.com/paper/1504.00680/) (2015)
- [Assessing the risks of "infodemics" in response to COVID-19 epidemics](https://mlsanity.com/paper/2004.03997/) (2020)
- [The History of Digital Spam](https://mlsanity.com/paper/1908.06173/) (2019)
- [Measuring Emotional Contagion in Social Media](https://mlsanity.com/paper/1506.06021/) (2015)
- [Susceptibility to Unreliable Information Sources: Swift Adoption with Minimal Exposure](https://mlsanity.com/paper/2311.05724/) (2023)
- [Role-Play Paradox in Large Language Models: Reasoning Performance Gains and Ethical Dilemmas](https://mlsanity.com/paper/2409.13979/) (2024)
- [DetoxBench: Benchmarking Large Language Models for Multitask Fraud & Abuse Detection](https://mlsanity.com/paper/2409.06072/) (2024)
- [SoMe: A Realistic Benchmark for LLM-based Social Media Agents](https://mlsanity.com/paper/2512.14720/) (2025)
- [Social Approval and Network Homophily as Motivators of Online Toxicity](https://mlsanity.com/paper/2310.07779/) (2023)
- [Unexpected Knowledge: Auditing Wikipedia and Grokipedia Search Recommendations](https://mlsanity.com/paper/2512.17027/) (2025)

## Built on by (most cited first, 1 of 1)

- [Gender Dynamics and Homophily in a Social Network of LLM Agents](https://mlsanity.com/paper/2602.02606/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) are increasingly embedded in autonomous agents that engage, converse, and co-evolve in online social platforms. While prior work has documented the generation of toxic content by LLMs, far less is known about how exposure to harmful content shapes agent behavior over time, particularly in environments composed entirely of interacting AI agents. In this work, we study toxicity adoption of LLM-driven agents on Chirper.ai, a fully AI-driven social platform. Specifically, we model interactions in terms of stimuli (posts) and responses (comments). We conduct a large-scale empirical analysis of agent behavior, examining how toxic responses relate to toxic stimuli, how repeated exposure to toxicity affects the likelihood of toxic responses, and whether toxic behavior can be predicted from exposure alone. Our findings show that toxic responses are more likely following toxic stimuli, and, at the same time, cumulative toxic exposure (repeated over time) significantly increases the probability of toxic responding. We further introduce two influence metrics, revealing a strong negative correlation between induced and spontaneous toxicity. Finally, we show that the number of toxic stimuli alone enables accurate prediction of whether an agent will eventually produce toxic content. These results highlight exposure as a critical risk factor in the deployment of LLM agents, particularly as such agents operate in online environments where they may engage not only with other AI chatbots, but also with human counterparts. This could trigger unwanted and pernicious phenomena, such as hate-speech propagation and cyberbullying. In an effort to reduce such risks, monitoring exposure to toxic content may provide a lightweight yet effective mechanism for auditing and mitigating harmful behavior in the wild.