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

arXiv: https://arxiv.org/abs/2604.02500 · HTML: https://mlsanity.com/paper/2604.02500/

## Key facts

- Cited by 1 papers in the map (data through 14 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.

## Placed in

- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)

## Builds on (most cited first, 24 of 24)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Jailbroken: How Does LLM Safety Training Fail?](https://mlsanity.com/paper/2307.02483/) (2023)
- [OpenAI GPT-5 System Card](https://mlsanity.com/paper/2601.03267/) (2025)
- [RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback](https://mlsanity.com/paper/2309.00267/) (2023)
- [Great, Now Write an Article About That: The Crescendo Multi-Turn LLM Jailbreak Attack](https://mlsanity.com/paper/2404.01833/) (2024)
- [Alignment faking in large language models](https://mlsanity.com/paper/2412.14093/) (2024)
- [Frontier Models are Capable of In-context Scheming](https://mlsanity.com/paper/2412.04984/) (2024)
- [ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs](https://mlsanity.com/paper/2402.11753/) (2024)
- [AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges](https://mlsanity.com/paper/2505.10468/) (2025)
- [Agentic Misalignment: How LLMs Could Be Insider Threats](https://mlsanity.com/paper/2510.05179/) (2025)
- [Evaluating Frontier Models for Dangerous Capabilities](https://mlsanity.com/paper/2403.13793/) (2024)
- [Large Language Models Often Know When They Are Being Evaluated](https://mlsanity.com/paper/2505.23836/) (2025)
- [Evaluating Language-Model Agents on Realistic Autonomous Tasks](https://mlsanity.com/paper/2312.11671/) (2023)
- [Stress Testing Deliberative Alignment for Anti-Scheming Training](https://mlsanity.com/paper/2509.15541/) (2025)
- [Superintelligent Agents Pose Catastrophic Risks: Can Scientist AI Offer a Safer Path?](https://mlsanity.com/paper/2502.15657/) (2025)
- [International AI Safety Report](https://mlsanity.com/paper/2501.17805/) (2025)
- [Measuring Agents in Production](https://mlsanity.com/paper/2512.04123/) (2025)
- [Frontier AI systems have surpassed the self-replicating red line](https://mlsanity.com/paper/2412.12140/) (2024)
- [International AI Safety Report 2025: First Key Update: Capabilities and Risk Implications](https://mlsanity.com/paper/2510.13653/) (2025)
- [International AI Safety Report 2025: Second Key Update: Technical Safeguards and Risk Management](https://mlsanity.com/paper/2511.19863/) (2025)

## Built on by (most cited first, 1 of 1)

- [Towards an Agent Operating System - Lessons from Classical and Cloud OS](https://mlsanity.com/paper/2607.25076/) (2026)

## 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.