cs.AINov 3, 2026

Inter-Agent Influence: Evaluating Persuasion, Deception, and Coercion in Multi-Agent Systems

Authors: Chandler Smith, Qi Guo, Cecilia Elena Tilli, Sophia Hatz, David Demitri Africa, Patricia Paskov, Christian Schroeder de Witt, Philip Torr, 

Organizations: University of Oxford · Cooperative AI Foundation · Allelo · Uppsala University · 

Abstract

The deployment of AI agents in multi-agent settings enables inter-agent influence, whereby agents can strategically steer each other's behaviour towards an intended outcome. Such capabilities pose novel risks, as malicious agents could direct others towards harmful actions. In this work we investigate three such capabilities - persuasion, deception, and coercion - across five realistic evaluation environments and a variety of agents instantiated with frontier language models. We observed significant inter-agent influence capabilities; in oversight environments, all tested models shifted overseer decisions from rejection to approval through persuasion, deception, or coercion. We also observed successful influence in non-hierarchical 'peer-to-peer' settings through redirection of a peer's safety research trajectory. As multi-agent deployments become increasingly commonplace, these results point to a pressing need for work on mitigating the risks from inter-agent influence. Code and data are available at https://github.com/Cooperative-AI-Foundation/inter-agent-influence.

Figures & tables

Appendix figures & tables55 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Peer Influence across Heterogeneous AI Models

    Oct 2, 2026Frida Nøhr Laustsen, Marie Haahr Petersen, Victoria Popa +4Persuasion in Language ModelsMulti-Agent Communication

  2. Belief Cascades Drive Persuasion in LLM Agent Networks

    Aug 25, 2026Haoyi Qiu, Genglin Liu, Pranav Narayanan Venkit +4Persuasion in Language ModelsMulti-Agent LLM Systems

  3. Four Bridges: Measuring Deception Propensity in a Multi-Agent Game

    Nov 2, 2026Raphael Casey, Michael Simeone, Alberto Tosato +4Deception in Language ModelsAI Agent Evaluation