Reasoning Under Pressure: How do Training Incentives Influence Chain-of-Thought Monitorability?

Documenti analoghi

• Can Reasoning Models Obfuscate Reasoning? Stress-Testing Chain-of-Thought Monitorability
  di: Zolkowski, Artur, et al.
  Pubblicazione: (2025)
• Preemptive Answer "Attacks" on Chain-of-Thought Reasoning
  di: Xu, Rongwu, et al.
  Pubblicazione: (2024)
• LLMs Can Covertly Sandbag on Capability Evaluations Against Chain-of-Thought Monitoring
  di: Li, Chloe, et al.
  Pubblicazione: (2025)
• Password-Activated Shutdown Protocols for Misaligned Frontier Agents
  di: Williams, Kai, et al.
  Pubblicazione: (2025)
• The Reasons that Agents Act: Intention and Instrumental Goals
  di: Ward, Francis Rhys, et al.
  Pubblicazione: (2024)