paper-with-me

홈 › Papers

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

2026-01-02 · Michael Bao 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.

📄 PDF Abstract BibTeX arXiv:2601.00994

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Persuade Me if You Can: A Framework for Evaluating Persuasion Effectiveness and Susceptibility Among Large Language Models

2025-03-03 · Nimet Beyza Bozdag, Shuhaib Mehri, Gokhan Tur, Dilek Hakkani-Tür

Large Language Models (LLMs) demonstrate persuasive capabilities that rival human-level persuasion. While these capabilities can be used for social good, they also present risks of potential misuse. Moreover, LLMs' susce…

Misinformation

Understanding Persuasion in Long-Running Agents

2026-01-31 · Hyejun Jeong, Amir Houmansadr, Shlomo Zilberstein, Eugene Bagdasarian arxiv

Modern AI agents increasingly combine conversational interaction with autonomous task execution, such as coding and web research, raising a natural question: What happens when an agent engaged in long-horizon tasks is ex…

It's a TRAP! Task-Redirecting Agent Persuasion Benchmark for Web Agents

2025-12-29 · Karolina Korgul, Yushi Yang, Arkadiusz Drohomirecki, Piotr Błaszczyk 외 arxiv

Web-based agents powered by large language models are increasingly used for tasks such as email management or professional networking. Their reliance on dynamic web content, however, makes them vulnerable to prompt injec…

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

2024-10-09 · Gian Maria Campedelli, Nicolò Penzo, Massimo Stefan, Roberto Dessì 외

As Large Language Model (LLM)-based agents become increasingly autonomous and will more freely interact with each other, studying interactions between them becomes crucial to anticipate emergent phenomena and potential r…

Large Language ModelPersuasiveness

Understanding Persuasive Interactions between Generative Social Agents and Humans: The Knowledge-based Persuasion Model (KPM)

2026-02-12 · Stephan Vonschallen, Friederike Eyssel, Theresa Schmiedel arxiv

Generative social agents (GSAs) use artificial intelligence to autonomously communicate with human users in a natural and adaptive manner. Currently, there is a lack of theorizing regarding interactions with GSAs, and li…