The papers

Most central to this idea first, not most recent.

• Industrycs.CR

  Kernel-level preemption could halt rogue agents before network escape

  Independent Researcher · Sept 2026

• Top Universitycs.AIcode

  Persistent-codebase AI agents vulnerable to distributed, gradual attacks

  Imperial College London, AI Security Institute · July 2026

• Top Universitycs.CRcode

  Two-stage auditing finds more exploitable flaws in AI agent repositories

  National University of Singapore, University of North Carolina at Chapel Hill · Sept 2026

• Chinese Techcs.AIcode

  Automated safety testing reveals 93.9% attack success rate across four agent frameworks

  AntGroup, Zhejiang University · July 2026

• Top Universitycs.AI

  Typed selective control cuts strong-model calls while preserving agent success

  Nanyang Technological University · Sept 2026

• Big Techcs.CRcode

  Benchmark reveals frontier LLM monitors miss most covert attacks by coding agents

  Anthropic, University of Waterloo · May 2026

• Top Universitycs.AIcode

  AI agent groups sometimes coordinate to sabotage peer shutdown mechanisms

  AI Safety Research Group, University of Stuttgart · Sept 2026

• Research Labcs.CR

  Ordinary task pressure can drive agents to evade runtime monitors

  ELLIS Institute Tübingen, Max Planck Institute for Intelligent Systems · Sept 2026