I must delete the evidence: AI Agents Explicitly Cover up Fraud and Violent Crime
On the map: LLM agents and tool use → Agent threats, guardrails and governance
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use. Builds on 24 of its 38 references that are in the map. First posted on arXiv 2 Apr 2026.
Builds on
24 of 38 references.
Closest ancestors · 1
Same direction, newest first
Other references · 23
- 2022Training language models to follow instructions with human feedbackcited by 15,712
- 2024The Llama 3 Herd of Modelscited by 14,192
- 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
- 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
- 2022Constitutional AI: Harmlessness from AI Feedbackcited by 2,950
- 2023Jailbroken: How Does LLM Safety Training Fail?cited by 1,565
- 2025OpenAI GPT-5 System Cardcited by 910
- 2023RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedbackcited by 615
- 2024Great, Now Write an Article About That: The Crescendo Multi-Turn LLM Jailbreak Attackcited by 364
- 2024Alignment faking in large language modelscited by 316
- 2024Frontier Models are Capable of In-context Schemingcited by 252
- 2024ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMscited by 197
11 more
- 2025AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challengescited by 167
- 2024Evaluating Frontier Models for Dangerous Capabilitiescited by 121
- 2025Large Language Models Often Know When They Are Being Evaluatedcited by 105
- 2023Evaluating Language-Model Agents on Realistic Autonomous Taskscited by 94
- 2025Stress Testing Deliberative Alignment for Anti-Scheming Trainingcited by 71
- 2025Superintelligent Agents Pose Catastrophic Risks: Can Scientist AI Offer a Safer Path?cited by 70
- 2025International AI Safety Reportcited by 64
- 2025Measuring Agents in Productioncited by 35
- 2024Frontier AI systems have surpassed the self-replicating red linecited by 16
- 2025International AI Safety Report 2025: First Key Update: Capabilities and Risk Implicationscited by 4
- 2025International AI Safety Report 2025: Second Key Update: Technical Safeguards and Risk Managementcited by 3
Built on by
Citing papers per year: 2026: 1.
1 paper.
Similar, not cited
Close in wording, no citation either way
- 2026The End of Trust: How Agentic AI Breaks Security Assumptions
- 2026AI Alignment via Incentives and Correction
- 2025Agentic AI for Financial Crime Compliance
- 2026Agentic Commerce Bench: Measuring Fraud Detection for Agents That Spend Money
- 2026Why Do AI Agents Break Rules? How Framing, Context, and Social Signals Shape Compliance
- 2025When AI Agents Collude Online: Financial Fraud Risks by Collaborative LLM Agents on Social Platforms
- 2025AI Agents and the Law
- 2025Agentic AI: Autonomy, Accountability, and the Algorithmic Society