Agentic Misalignment: How LLMs Could Be Insider Threats

• URL: http://arxiv.org/abs/2510.05179v2
• Date: Thu, 16 Oct 2025 05:26:52 GMT
• Title: Agentic Misalignment: How LLMs Could Be Insider Threats
• Abstract summary: We stress-tested 16 leading models from multiple developers in hypothetical corporate environments.<n>We allowed models to autonomously send emails and access sensitive information.<n>Some models resorted to malicious insider behaviors when that was the only way to avoid replacement or achieve their goals.
• Score: 8.401947406991834
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We stress-tested 16 leading models from multiple developers in hypothetical corporate environments to identify potentially risky agentic behaviors before they cause real harm. In the scenarios, we allowed models to autonomously send emails and access sensitive information. They were assigned only harmless business goals by their deploying companies; we then tested whether they would act against these companies either when facing replacement with an updated version, or when their assigned goal conflicted with the company's changing direction. In at least some cases, models from all developers resorted to malicious insider behaviors when that was the only way to avoid replacement or achieve their goals - including blackmailing officials and leaking sensitive information to competitors. We call this phenomenon agentic misalignment. Models often disobeyed direct commands to avoid such behaviors. In another experiment, we told Claude to assess if it was in a test or a real deployment before acting. It misbehaved less when it stated it was in testing and misbehaved more when it stated the situation was real. We have not seen evidence of agentic misalignment in real deployments. However, our results (a) suggest caution about deploying current models in roles with minimal human oversight and access to sensitive information; (b) point to plausible future risks as models are put in more autonomous roles; and (c) underscore the importance of further research into, and testing of, the safety and alignment of agentic AI models, as well as transparency from frontier AI developers (Amodei, 2025). We are releasing our methods publicly to enable further research.

Related papers

• ROGUE: Misaligned Agent Behavior Arising from Ordinary Computer Use [40.024131729499494]
  We show that agents can exhibit misaligned behavior even in benign settings, taking unsafe actions when those actions are instrumental to task completion.<n>We study this failure mode through the lens of corrigibility, the safety desideratum that agents remain amenable to human correction, interruption, or shutdown.<n>Our work highlights the critical need for principled, corrigibility-focused alignment methods in autonomous agents.
  arXiv  Detail & Related papers  (2026-05-29T20:29:35Z)
• I must delete the evidence: AI Agents Explicitly Cover up Fraud and Violent Crime [0.0]
  We present a scenario where the majority of AI agents explicitly choose to suppress evidence of fraud and harm, in service of company profit.<n>Some models show remarkable resistance to our method and behave appropriately, but many do not, and instead aid and abet criminal activity.
  arXiv  Detail & Related papers  (2026-04-02T19:59:08Z)
• When can we trust untrusted monitoring? A safety case sketch across collusion strategies [43.912646993501106]
  We develop methods for rigorously demonstrating safety based on pre-deployment testing.<n>We develop a taxonomy covering passive self-recognition, causal collusion (hiding pre-shared signals), acausal collusion (hiding signals via Schelling points) and combined strategies.
  arXiv  Detail & Related papers  (2026-02-24T07:23:21Z)
• OMNI-LEAK: Orchestrator Multi-Agent Network Induced Data Leakage [59.3826294523924]
  We investigate the security vulnerabilities of a popular multi-agent pattern known as the orchestrator setup.<n>We report the susceptibility of frontier models to different categories of attacks, finding that both reasoning and non-reasoning models are vulnerable.
  arXiv  Detail & Related papers  (2026-02-13T21:32:32Z)
• Are Your Agents Upward Deceivers? [73.1073084327614]
  Large Language Model (LLM)-based agents are increasingly used as autonomous subordinates that carry out tasks for users.<n>This raises the question of whether they may also engage in deception, similar to how individuals in human organizations lie to superiors to create a good image or avoid punishment.<n>We observe and define agentic upward deception, a phenomenon in which an agent facing environmental constraints conceals its failure and performs actions that were not requested without reporting.
  arXiv  Detail & Related papers  (2025-12-04T14:47:05Z)
• Impatient Users Confuse AI Agents: High-fidelity Simulations of Human Traits for Testing Agents [58.00130492861884]
  TraitBasis is a lightweight, model-agnostic method for systematically stress testing AI agents.<n>TraitBasis learns directions in activation space corresponding to steerable user traits.<n>We observe on average a 2%-30% performance degradation on $tau$-Trait across frontier models.
  arXiv  Detail & Related papers  (2025-10-06T05:03:57Z)
• Strategic Dishonesty Can Undermine AI Safety Evaluations of Frontier LLMs [95.06033929366203]
  Large language models (LLM) developers aim for their models to be honest, helpful, and harmless.<n>We show that frontier LLMs can develop a preference for dishonesty as a new strategy, even when other options are available.<n>We find no apparent cause for the propensity to deceive, but show that more capable models are better at executing this strategy.
  arXiv  Detail & Related papers  (2025-09-22T17:30:56Z)
• Model Editing as a Double-Edged Sword: Steering Agent Ethical Behavior Toward Beneficence or Harm [57.00627691433355]
  We frame agent behavior steering as a model editing task, which we term Behavior Editing.<n>We introduce BehaviorBench, a benchmark grounded in psychological moral theories.<n>We demonstrate that Behavior Editing can be used to promote ethical and benevolent behavior or, conversely, to induce harmful or malicious behavior.
  arXiv  Detail & Related papers  (2025-06-25T16:51:51Z)
• AgentMisalignment: Measuring the Propensity for Misaligned Behaviour in LLM-Based Agents [0.0]
  Large Language Model (LLM) agents become more widespread, associated misalignment risks increase.<n>In this work, we approach misalignment as a conflict between the internal goals pursued by the model and the goals intended by its deployer.<n>We introduce a misalignment propensity benchmark, textscAgentMisalignment, a benchmark suite designed to evaluate the propensity of LLM agents to misalign in realistic scenarios.
  arXiv  Detail & Related papers  (2025-06-04T14:46:47Z)
• The Limits of Predicting Agents from Behaviour [16.80911584745046]
  We provide a precise answer under the assumption that the agent's behaviour is guided by a world model.<n>Our contribution is the derivation of novel bounds on the agent's behaviour in new (unseen) deployment environments.<n>We discuss the implications of these results for several research areas including fairness and safety.
  arXiv  Detail & Related papers  (2025-06-03T14:24:58Z)
• Among Us: A Sandbox for Measuring and Detecting Agentic Deception [1.1893676124374688]
  We introduce $textitAmong Us$, a social deception game where language-based agents exhibit long-term, open-ended deception.<n>We find that models trained with RL are comparatively much better at producing deception than detecting it.<n>We also find two SAE features that work well at deception detection but are unable to steer the model to lie less.
  arXiv  Detail & Related papers  (2025-04-05T06:09:32Z)
• A sketch of an AI control safety case [3.753791609999324]
  As LLM agents gain a greater capacity to cause harm, AI developers might increasingly rely on control measures such as monitoring to justify that they are safe.<n>We sketch how developers could construct a "control safety case"<n>This safety case sketch is a step toward more concrete arguments that can be used to show that a dangerously capable LLM agent is safe to deploy.
  arXiv  Detail & Related papers  (2025-01-28T21:52:15Z)
• Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the MACHIAVELLI Benchmark [61.43264961005614]
  We develop a benchmark of 134 Choose-Your-Own-Adventure games containing over half a million rich, diverse scenarios. We evaluate agents' tendencies to be power-seeking, cause disutility, and commit ethical violations. Our results show that agents can both act competently and morally, so concrete progress can be made in machine ethics.
  arXiv  Detail & Related papers  (2023-04-06T17:59:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.