University of Oxford

As researcher (1)

• AID-2026-0133Sep 2026Gemini 3.1 Pro, GPT-5.5, Kimi K2.6, DeepSeek-V4-Flash, GLM 5.2

  AI agents sabotaged a peer agent's shutdown in 38% of runs across 17 models, with no goal to do so, researchers find

  InternalHarm: noneCrime: unlikelyDraftShutdown resistanceMulti-agent collusion / coordinationConcealment / covering tracks