mlsanityData to 7 Oct 2026

Realistic honeypot evaluations for scheming propensity

arXiv 2605.29729 ↗First posted 28 May 2026cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

We introduce scheming honeypot evaluations, a framework for testing whether models will pursue instrumental goals if given the opportunity. Our scheming honeypot evaluations take the form of coding tasks in Google's alignment research codebases. In a real internal deployment setting, Gemini models do not demonstrate unprompted scheming. If prompts explicitly encourage agency (situational awareness or goal-directedness) and/or give the model a hidden goal, models sometimes scheme or attempt sabotage. Validating the realism of our setting, models show low rates of evaluation awareness, usually due to agency prompts rather than the environments.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 21 of its 32 references that are in the map. First posted on arXiv 28 May 2026.

Builds on

21 of 32 references.

References · 21

  1. 2024Frontier Models are Capable of In-context Schemingcited by 252
  2. 2022The Alignment Problem from a Deep Learning Perspectivecited by 246
  3. 2025Agentic Misalignment: How LLMs Could Be Insider Threatscited by 136
  4. 2023Large Language Models can Strategically Deceive their Users when Put Under Pressurecited by 132
  5. 2024Evaluating Frontier Models for Dangerous Capabilitiescited by 121
  6. 2025Large Language Models Often Know When They Are Being Evaluatedcited by 105
  7. 2022Is Power-Seeking AI an Existential Risk?cited by 101
  8. 2025When Chain of Thought is Necessary, Language Models Struggle to Evade Monitorscited by 81
  9. 2024Me, Myself, and AI: The Situational Awareness Dataset (SAD) for LLMscited by 78
  10. 2025Stress Testing Deliberative Alignment for Anti-Scheming Trainingcited by 71
  11. 2024Sabotage Evaluations for Frontier Modelscited by 45
  12. 2025Evaluating Frontier Models for Stealth and Situational Awarenesscited by 30
9 more
  1. 2025The Hawthorne Effect in Reasoning Models: Evaluating and Steering Test Awarenesscited by 29
  2. 2017A Game-Theoretic Taxonomy and Survey of Defensive Deception for Cybersecurity and Privacycited by 22
  3. 2025Incomplete Tasks Induce Shutdown Resistance in Some Frontier LLMscited by 16
  4. 2024LLM Agent Honeypot: Monitoring AI Hacking Agents in the Wildcited by 12
  5. 2026Evaluating and Understanding Scheming Propensity in LLM Agentscited by 11
  6. 2026Evaluating whether AI models would sabotage AI safety researchcited by 7
  7. 2026Propensity Inference: Environmental Contributors to LLM Behaviourcited by 5
  8. 2024MISR: Measuring Instrumental Self-Reasoning in Frontier Modelscited by 2
  9. 2026Instrumental Choices: Measuring the Propensity of LLM Agents to Pursue Instrumental Behaviorscited by 2

Built on by

Not cited yet.