Startseite
Podcasts
CISPA TL;DR - Der Podcast über KI- und IT-Sicherheitsforschung Podcast
#50 Multi-Agent AI Systems with Samira Abedini

#50 Multi-Agent AI Systems with Samira Abedini

CISPA TL;DR - Der Podcast über KI- und IT-Sicherheitsforschung vor 3 Tagen

0:00

36:16

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