# ElecTwit: A Framework for Studying Persuasion in Multi-Agent Social Systems

arXiv: https://arxiv.org/abs/2601.00994 · HTML: https://mlsanity.com/paper/2601.00994/

## Key facts

- Cited by 1 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 10 of its 13 references that are in the map.
- First posted on arXiv 2 Jan 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, 10 of 10)

- [A Survey on Large Language Model based Autonomous Agents](https://mlsanity.com/paper/2308.11432/) (2023)
- [Large Language Models: A Survey](https://mlsanity.com/paper/2402.06196/) (2024)
- [AgentSociety: Large-Scale Simulation of LLM-Driven Generative Agents Advances Understanding of Human Behaviors and Society](https://mlsanity.com/paper/2502.08691/) (2025)
- [Evaluating Frontier Models for Dangerous Capabilities](https://mlsanity.com/paper/2403.13793/) (2024)
- [Safeguarding Large Language Models: A Survey](https://mlsanity.com/paper/2406.02622/) (2024)
- [Decoding Echo Chambers: LLM-Powered Simulations Revealing Polarization in Social Networks](https://mlsanity.com/paper/2409.19338/) (2024)
- [Among Us: A Sandbox for Measuring and Detecting Agentic Deception](https://mlsanity.com/paper/2504.04072/) (2025)
- [Must Read: A Comprehensive Survey of Computational Persuasion](https://mlsanity.com/paper/2505.07775/) (2025)
- [Casevo: A Cognitive Agents and Social Evolution Simulator](https://mlsanity.com/paper/2412.19498/) (2024)
- [Among Them: A game-based framework for assessing persuasion capabilities of LLMs](https://mlsanity.com/paper/2502.20426/) (2025)

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

- [Predicting Decisions of AI Agents from Limited Interaction through Text-Tabular Modeling](https://mlsanity.com/paper/2605.12411/) (2026)

## Abstract (arXiv)

This paper introduces ElecTwit, a simulation framework designed to study persuasion within multi-agent systems, specifically emulating the interactions on social media platforms during a political election. By grounding our experiments in a realistic environment, we aimed to overcome the limitations of game-based simulations often used in prior research. We observed the comprehensive use of 25 specific persuasion techniques across most tested LLMs, encompassing a wider range than previously reported. The variations in technique usage and overall persuasion output between models highlight how different model architectures and training can impact the dynamics in realistic social simulations. Additionally, we observed unique phenomena such as "kernel of truth" messages and spontaneous developments with an "ink" obsession, where agents collectively demanded written proof. Our study provides a foundation for evaluating persuasive LLM agents in real-world contexts, ensuring alignment and preventing dangerous outcomes.