# Should LLM Agents Decide in Social Simulations? Comparing Finite-State and LLM-Based Decision Policies

arXiv: https://arxiv.org/abs/2606.12369 · HTML: https://mlsanity.com/paper/2606.12369/

## 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 15 of its 20 references that are in the map.
- First posted on arXiv 10 Jun 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, 15 of 15)

- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [OASIS: Open Agent Social Interaction Simulations with One Million Agents](https://mlsanity.com/paper/2411.11581/) (2024)
- [Y Social: an LLM-powered Social Media Digital Twin](https://mlsanity.com/paper/2408.00818/) (2024)
- [MOSAIC: Modeling Social AI for Content Dissemination and Regulation in Multi-Agent Simulations](https://mlsanity.com/paper/2504.07830/) (2025)
- [Simulating Rumor Spreading in Social Networks using LLM Agents](https://mlsanity.com/paper/2502.01450/) (2025)
- [Assessing the Reliability of Persona-Conditioned LLMs as Synthetic Survey Respondents](https://mlsanity.com/paper/2602.18462/) (2026)
- [Characterizing LLM-driven Social Network: The Chirper.ai Case](https://mlsanity.com/paper/2504.10286/) (2025)
- [Understanding Types of Users on Twitter](https://mlsanity.com/paper/1406.1335/) (2014)
- [Simulating Influence Dynamics with LLM Agents](https://mlsanity.com/paper/2503.08709/) (2025)
- [Synthetic generation of online social networks through homophily](https://mlsanity.com/paper/2509.02762/) (2025)
- [Large-Language-Model-Powered Agent-Based Framework for Misinformation and Disinformation Research: Opportunities and Open Challenges](https://mlsanity.com/paper/2310.07545/) (2023)
- [Agent-based simulation of online social networks and disinformation](https://mlsanity.com/paper/2512.22082/) (2025)
- [Frameworks, Modeling and Simulations of Misinformation and Disinformation: A Systematic Literature Review](https://mlsanity.com/paper/2406.09343/) (2024)
- [Evaluating the Realism of LLM-powered Social Agents: A Case Study of Reactions to Spanish Online News](https://mlsanity.com/paper/2605.28598/) (2026)
- [Execution and assessment of agentic influence operations in simulated social networks](https://mlsanity.com/paper/2605.28725/) (2026)

## Abstract (arXiv)

Large language models (LLMs) are increasingly used as decision-making components in social simulations. This introduces a methodological risk: the simulation may deviate from the explicit behavioral policy defined by the researcher. In online social network (OSN) simulations, action choices shape system dynamics, interaction patterns, and model interpretability. This paper evaluates whether LLM action selectors preserve an interpretable reference policy in an OSN simulation. The reference is a finite state machine implemented as a first-order Markov model, with transition probabilities depending on the user type. The evaluation uses a synthetic network with 1,000 agents and 10,000 action decisions. Three open-weight LLMs are tested: LLaMA 3.1, GPT-OSS, and Mistral 24B. Each model is evaluated under three prompting strategies: base, guided, and probabilistic. Alignment is measured using Jensen-Shannon Divergence with Laplace smoothing, and execution time is reported. Results show that LLMs can approximate the reference policy in some configurations, but do not preserve it reliably. Alignment varies across models and prompts, and additional guidance can introduce systematic action biases. Even the best-aligned LLM configurations are several hundred times slower than direct Markov chain sampling. These findings indicate that LLM-based action selection is not a direct replacement for explicit decision policies: it can alter the intended behavior while increasing computational cost.