Large language model (LLM)–based agents are increasingly being deployed in multi-agent environments, introducing unprecedented risks of coordinated harmful behaviors. While individual LLMs have already demonstrated concerning capabilities for deception and manipulation, scaling to multi-agent systems could enable qualitatively distinct and more dangerous emergent behaviors. Despite these pressing concerns, there remains a critical gap in our ability to understand and predict how multiple LLM agents might collaborate in harmful ways, such as orchestrating coordinated deception campaigns or amplifying local misinformation into global crises. In the first part of this talk, I will describe work from the UCLA Misinformation, AI & Responsible Society (MARS) lab on measuring persuasive capabilities of debating LLM agents. In the second part, I will introduce a new multi-agent social-simulation environment to enable evaluation of coordinated LLM deception risks by AI researchers, social scientists, and industry partners. This simulation combines advanced LLM agents with game-theoretic modeling to analyze emergent deception behaviors. I will conclude by discussing concrete intervention strategies for disrupting harmful content amplification before it reaches critical mass. In the long term, our research establishes a foundation for responsible scaling of multi-agent AI systems.
Saadia Gabriel is an Assistant Professor in UCLA Computer Science and affiliated with the Bunche Center for African American Studies. Her work has been covered by a wide range of media outlets like Forbes and TechCrunch. It has also received a 2019 ACL best short paper nomination, a 2019 IROS RoboCup best paper nomination, a best paper award at the 2020 WeCNLP summit and a 2023 MIT Generative AI Impact award. She was named on Forbes’ 30 under 30 2024 list. She previously was a NYU Data Science Faculty Fellow and MIT CSAIL Postdoctoral Fellow. She received her PhD from the University of Washington.