# I Want to Break Free! Persuasion and Anti-Social Behavior of LLMs in Multi-Agent Settings with Social Hierarchy

arXiv: https://arxiv.org/abs/2410.07109 · HTML: https://mlsanity.com/paper/2410.07109/

## Key facts

- Cited by 12 papers in the map (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 16 of its 70 references that are in the map.
- First posted on arXiv 9 Oct 2024.

## 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, 16 of 16)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations](https://mlsanity.com/paper/2312.06674/) (2023)
- [Gemini: A Family of Highly Capable Multimodal Models](https://mlsanity.com/paper/2312.11805/) (2023)
- [JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models](https://mlsanity.com/paper/2404.01318/) (2024)
- [Open Problems in Cooperative AI](https://mlsanity.com/paper/2012.08630/) (2020)
- [Orca 2: Teaching Small Language Models How to Reason](https://mlsanity.com/paper/2311.11045/) (2023)
- [War and Peace (WarAgent): Large Language Model-based Multi-Agent Simulation of World Wars](https://mlsanity.com/paper/2311.17227/) (2023)
- [LLM Multi-Agent Systems: Challenges and Open Problems](https://mlsanity.com/paper/2402.03578/) (2024)
- [On the Conversational Persuasiveness of Large Language Models: A Randomized Controlled Trial](https://mlsanity.com/paper/2403.14380/) (2024)
- [Simulating Social Media Using Large Language Models to Evaluate Alternative News Feed Algorithms](https://mlsanity.com/paper/2310.05984/) (2023)
- [Nicer Than Humans: How do Large Language Models Behave in the Prisoner's Dilemma?](https://mlsanity.com/paper/2406.13605/) (2024)
- [AI-Augmented Surveys: Leveraging Large Language Models and Surveys for Opinion Prediction](https://mlsanity.com/paper/2305.09620/) (2023)
- [High-Dimension Human Value Representation in Large Language Models](https://mlsanity.com/paper/2404.07900/) (2024)

## Built on by (most cited first, 12 of 12)

- [Agentic Large Language Models, a survey](https://mlsanity.com/paper/2503.23037/) (2025)
- [Towards a Design Guideline for RPA Evaluation: A Survey of Large Language Model-Based Role-Playing Agents](https://mlsanity.com/paper/2502.13012/) (2025)
- [Does Socialization Emerge in AI Agent Society? A Case Study of Moltbook](https://mlsanity.com/paper/2602.14299/) (2026)
- [Inherent and emergent liability issues in LLM-based agentic systems: a principal-agent perspective](https://mlsanity.com/paper/2504.03255/) (2025)
- [Agentic LLM Framework for Adaptive Decision Discourse](https://mlsanity.com/paper/2502.10978/) (2025)
- [Generative AI collective behavior needs an interactionist paradigm](https://mlsanity.com/paper/2601.10567/) (2026)
- [MedSyn: Enhancing Diagnostics with Human-AI Collaboration](https://mlsanity.com/paper/2506.14774/) (2025)
- [Open-source LLMs administer maximum electric shocks in a Milgram-like obedience experiment](https://mlsanity.com/paper/2605.21401/) (2026)
- [Superminds Test: Actively Evaluating Collective Intelligence of Agent Society via Probing Agents](https://mlsanity.com/paper/2604.22452/) (2026)
- [Evaluating Large Language Models in a Complex Hidden Role Game](https://mlsanity.com/paper/2605.22826/) (2026)
- [Predicting Decisions of AI Agents from Limited Interaction through Text-Tabular Modeling](https://mlsanity.com/paper/2605.12411/) (2026)
- [PAVE: A Cognitive Architecture for Legitimate Violation in Generative Agent Societies](https://mlsanity.com/paper/2605.19351/) (2026)

## Abstract (arXiv)

As LLM-based agents become increasingly autonomous and will more freely interact with each other, studying the interplay among them becomes crucial to anticipate emergent phenomena and potential risks. In this work, we provide an in-depth analysis of the interactions among agents within a simulated hierarchical social environment, drawing inspiration from the Stanford Prison Experiment. Leveraging 2,400 conversations across six LLMs (i.e., LLama3, Orca2, Command-r, Mixtral, Mistral2, and gpt4.1) and 240 experimental scenarios, we analyze persuasion and anti-social behavior between a guard and a prisoner agent with differing objectives. We first document model-specific conversational failures in this multi-agent power dynamic context, thereby narrowing our analytic sample to 1,600 conversations. Among models demonstrating successful interaction, we find that goal setting significantly influences persuasiveness but not anti-social behavior. Moreover, agent personas, especially the guard's, substantially impact both successful persuasion by the prisoner and the manifestation of anti-social actions. Notably, we observe the emergence of anti-social conduct even in absence of explicit negative personality prompts. These results have important implications for the development of interactive LLM agents and the ongoing discussion of their societal impact.