# Disentangling Models from Personas in Heterogeneous LLM Simulations

arXiv: https://arxiv.org/abs/2610.07535 · HTML: https://mlsanity.com/paper/2610.07535/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 30 of its 76 references that are in the map.
- First posted on arXiv 6 Oct 2026.

## Builds on (most cited first, 30 of 30)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [gpt-oss-120b & gpt-oss-20b Model Card](https://mlsanity.com/paper/2508.10925/) (2025)
- [ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools](https://mlsanity.com/paper/2406.12793/) (2024)
- [Mixture-of-Agents Enhances Large Language Model Capabilities](https://mlsanity.com/paper/2406.04692/) (2024)
- [ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMs](https://mlsanity.com/paper/2309.13007/) (2023)
- [More Agents Is All You Need](https://mlsanity.com/paper/2402.05120/) (2024)
- [Multi-Agent Risks from Advanced AI](https://mlsanity.com/paper/2502.14143/) (2025)
- [Generative agent-based modeling with actions grounded in physical, social, or digital space using Concordia](https://mlsanity.com/paper/2312.03664/) (2023)
- [From Individual to Society: A Survey on Social Simulation Driven by Large Language Model-based Agents](https://mlsanity.com/paper/2412.03563/) (2024)
- [Open Challenges in Multi-Agent Security: Towards Secure Systems of Interacting AI Agents](https://mlsanity.com/paper/2505.02077/) (2025)
- [Magistral](https://mlsanity.com/paper/2506.10910/) (2025)
- [GEO: Generative Engine Optimization](https://mlsanity.com/paper/2311.09735/) (2023)
- [SocioVerse: A World Model for Social Simulation Powered by LLM Agents and A Pool of 10 Million Real-World Users](https://mlsanity.com/paper/2504.10157/) (2025)
- [Rethinking Mixture-of-Agents: Is Mixing Different Large Language Models Beneficial?](https://mlsanity.com/paper/2502.00674/) (2025)
- [X-MAS: Towards Building Multi-Agent Systems with Heterogeneous LLMs](https://mlsanity.com/paper/2505.16997/) (2025)
- [When One LLM Drools, Multi-LLM Collaboration Rules](https://mlsanity.com/paper/2502.04506/) (2025)
- [Strategic Collusion of LLM Agents: Market Division in Multi-Commodity Competitions](https://mlsanity.com/paper/2410.00031/) (2024)
- [Institutional AI: Governing LLM Collusion in Multi-Agent Cournot Markets via Public Governance Graphs](https://mlsanity.com/paper/2601.11369/) (2026)
- [Generative Engine Optimization: How to Dominate AI Search](https://mlsanity.com/paper/2509.08919/) (2025)
- [The PIMMUR Principles: Ensuring Validity in Collective Behavior of LLM Societies](https://mlsanity.com/paper/2509.18052/) (2025)
- [Thought Virus: Viral Misalignment via Subliminal Prompting in Multi-Agent Systems](https://mlsanity.com/paper/2603.00131/) (2026)
- [Peer-Preservation in Frontier Models](https://mlsanity.com/paper/2604.19784/) (2026)
- [Evaluating Collective Behaviour of Hundreds of LLM Agents](https://mlsanity.com/paper/2602.16662/) (2026)
- [Quantifying the Vulnerabilities of the Online Public Square to Adversarial Manipulation Tactics](https://mlsanity.com/paper/1907.06130/) (2019)
- [Scheming Ability in LLM-to-LLM Strategic Interactions](https://mlsanity.com/paper/2510.12826/) (2025)
- [Simulating Misinformation Propagation in Social Networks using Large Language Models](https://mlsanity.com/paper/2511.10384/) (2025)
- [On the Dynamics of Multi-Agent LLM Communities Driven by Value Diversity](https://mlsanity.com/paper/2512.10665/) (2025)
- [Multi-LLM Systems Exhibit Robust Semantic Collapse](https://mlsanity.com/paper/2605.17193/) (2026)
- [Optimal Selection Using Algorithmic Rankings with Side Information](https://mlsanity.com/paper/2511.04867/) (2025)

## Abstract (arXiv)

Multi-agent simulations with large language models (LLMs) often operate networks of agents with a single base model. This overlooks the inter-model effects which may dominate engagement dynamics in real-world deployments. To show this, we simulate a heterogeneous social network powered by several different base models and show that the amount of engagement an agent receives depends more on its base model than on its assigned persona. The attraction or repulsion effects of a base model strengthen dramatically when more models are added in the mix, suggesting that networks dynamics may converge to base model effects at scale. To help explain this effect, we conduct a series of content-mediating analyses, showing the predictability of base models across contexts as well as the relationship between a model's lexical patterns and an engagement-maximizing style. In light of recent developments in mass multi-agent interaction, this work underscores the relevance of heterogeneous compositions in driving the outcomes of those networks