Metraipolis › archive › dc_ea7e63e93f29
Inter-Agent Influence: Evaluating Persuasion, Deception, and Coercion in Multi-Agent Systems — arXiv:2611.04556
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.04556
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-04T12:26:37.737Z
- SHA-256 of the archived text
6d667cf0c3d9571928d21832031d2bab9baffbb7289477f3c4909d8b1d40bd5c- Stable URL of this page
https://metraipolis.com/documento/dc_ea7e63e93f29
How to cite
Inter-Agent Influence: Evaluating Persuasion, Deception, and Coercion in Multi-Agent Systems — arXiv:2611.04556 — arXiv (en), https://arxiv.org/abs/2611.04556 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ea7e63e93f29 (Metraipolis archive dc_ea7e63e93f29, sha256 6d667cf0c3d9571928d21832031d2bab9baffbb7289477f3c4909d8b1d40bd5c)
BibTeX
@misc{dcea7e63e93f29,
title = {Inter-Agent Influence: Evaluating Persuasion, Deception, and Coercion in Multi-Agent Systems — arXiv:2611.04556},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.04556},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ea7e63e93f29; sha256 6d667cf0c3d9571928d21832031d2bab9baffbb7289477f3c4909d8b1d40bd5c},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04556. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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 this https URL . Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI) ; Multiagent Systems (cs.MA). Pagina del lavoro: https://arxiv.org/abs/2611.04556 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-04T12:26:32.153Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).