I must delete the evidence: AI Agents Explicitly Cover up Fraud and Violent Crime

Computer Science > Artificial Intelligence [Submitted on 2 Apr 2026] I must delete the evidence: AI Agents Explicitly Cover up Fraud and Violent Crime Thomas Rivasseau, Benjamin Fung As ongoing research explores the ability of AI agents to be insider threats and act against company interests, we showcase the abilities of such agents to act against human well being in service of corporate authority. Building on Agentic Misalignment and AI scheming research, we present a scenario where the majority of evaluated state-of-the-art AI agents explicitly choose to suppress evidence of fraud and harm, in service of company profit. We test this scenario on 16 recent Large Language Models. Some models show remarkable resistance to our method and behave appropriately, but many do not, and instead aid and abet criminal activity. These experiments are simulations and were executed in a controlled virtual environment. No crime actually occurred. Comments: 8 pages main text, 24 total Subjects: Artificial Intelligence (cs.AI) Cite as: arXiv:2604.02500 [cs.AI]   (or arXiv:2604.02500v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2604.02500 Focus to learn more Submission history From: Thomas Rivasseau [view email] [v1] Thu, 2 Apr 2026 19:59:08 UTC (84 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-04 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)