# Synthetic Social Media Influence Experimentation via an Agentic Reinforcement Learning Large Language Model Bot

arXiv: https://arxiv.org/abs/2411.19635 · HTML: https://mlsanity.com/paper/2411.19635/

## Key facts

- Cited by 2 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 14 of its 59 references that are in the map.
- First posted on arXiv 29 Nov 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, 14 of 14)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [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)
- [Social Simulacra: Creating Populated Prototypes for Social Computing Systems](https://mlsanity.com/paper/2208.04024/) (2022)
- [Strategic Behavior of Large Language Models: Game Structure vs. Contextual Framing](https://mlsanity.com/paper/2309.05898/) (2023)
- [Emergent Social Learning via Multi-agent Reinforcement Learning](https://mlsanity.com/paper/2010.00581/) (2020)
- [Blind Judgement: Agent-Based Supreme Court Modelling With GPT](https://mlsanity.com/paper/2301.05327/) (2023)
- [Evaluating Mixed-initiative Conversational Search Systems via User Simulation](https://mlsanity.com/paper/2204.08046/) (2022)
- [Segregation Dynamics with Reinforcement Learning and Agent Based Modeling](https://mlsanity.com/paper/1909.08711/) (2019)
- [Selective Exploration and Information Gathering in Search and Rescue Using Hierarchical Learning Guided by Natural Language Input](https://mlsanity.com/paper/2409.13445/) (2024)
- [Natural-Language Multi-Agent Simulations of Argumentative Opinion Dynamics](https://mlsanity.com/paper/2104.06737/) (2021)
- [Data Driven Modeling Social Media Influence using Differential Equations](https://mlsanity.com/paper/2207.13814/) (2022)
- [How to Find Opinion Leader on the Online Social Network?](https://mlsanity.com/paper/2306.04452/) (2023)
- [Towards Opinion Shaping: A Deep Reinforcement Learning Approach in Bot-User Interactions](https://mlsanity.com/paper/2409.11426/) (2024)

## Built on by (most cited first, 2 of 2)

- [Reproducibility Study of "Cooperate or Collapse: Emergence of Sustainable Cooperation in a Society of LLM Agents"](https://mlsanity.com/paper/2505.09289/) (2025)
- [A Natural Language Agentic Approach to Study Affective Polarization](https://mlsanity.com/paper/2603.02711/) (2026)

## Abstract (arXiv)

Understanding the dynamics of public opinion evolution on online social platforms is crucial for understanding influence mechanisms and the provenance of information. Traditional influence analysis is typically divided into qualitative assessments of personal attributes (e.g., psychology of influence) and quantitative evaluations of influence power mechanisms (e.g., social network analysis). One challenge faced by researchers is the ethics of real-world experimentation and the lack of social influence data. In this study, we provide a novel simulated environment that combines agentic intelligence with Large Language Models (LLMs) to test topic-specific influence mechanisms ethically. Our framework contains agents that generate posts, form opinions on specific topics, and socially follow/unfollow each other based on the outcome of discussions. This simulation allows researchers to observe the evolution of how opinions form and how influence leaders emerge. Using our own framework, we design an opinion leader that utilizes Reinforcement Learning (RL) to adapt its linguistic interaction with the community to maximize its influence and followers over time. Our current findings reveal that constraining the action space and incorporating self-observation are key factors for achieving stable and consistent opinion leader generation for topic-specific influence. This demonstrates the simulation framework's capacity to create agents that can adapt to complex and unpredictable social dynamics. The work is important in an age of increasing online influence on social attitudes and emerging technologies.