AI learns from us—including how we communicate, argue and persuade each other. So what happens when AI agents start talking to each other? CISPA researcher Samira Abedini and her colleagues found that one stubborn and persuasive agent can sometimes convince an entire group to adopt a wrong answer. She explains how a model originally developed to describe human opinion formation can surprisingly well explain how LLM agents influence each other—and where we can already find multi-agent AI systems in the real world today.

Read the full paper: https://publications.cispa.de/articles/conference_contribution/Don_t_Trust_Stubborn_Neighbors_A_Security_Framework_for_Agentic_Networks/32771607?file=65793867

Rss Apple Podcaster
Podden och tillhörande omslagsbild på den här sidan tillhör Annabelle Theobald und Tobias Ebelshäuser im Gespräch mit CISPA-Forschenden. Innehållet i podden är skapat av Annabelle Theobald und Tobias Ebelshäuser im Gespräch mit CISPA-Forschenden och inte av, eller tillsammans med, Poddtoppen.