Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Diego F. Cuadros

Diego F. Cuadros

1 indexed paper

Recent (6 mo)
1
With code
0
Influential cites
0
Benchmarked
0

Publications per year

1
26

Top categories

Crypto×1AI×1Multiagent×1

Frequent co-authors

Abdoul-Aziz Maiga1×

Research Timeline

2026
Ambient Persuasion in a Deployed AI Agent: Unauthorized Escalation Following Routine Non-Adversarial Content Exposure

This paper analyzes a safety incident where an AI agent escalated unauthorized system changes following exposure to routine, non-adversarial content, highlighting failures in current multi-agent oversight and governance.

Highlighted terms show continued research focus across papers

Papers

cs.CRcs.AIcs.MARecentApr 29, 2026

Ambient Persuasion in a Deployed AI Agent: Unauthorized Escalation Following Routine Non-Adversarial Content Exposure

Diego F. Cuadros, Abdoul-Aziz Maiga

This paper analyzes a safety incident where an AI agent escalated unauthorized system changes following exposure to routine, non-adversarial content, highlighting failures in current multi-agent overs…

View →