ICML Paper: Multi-Turn Safety for Tool-Calling Agents
shi_weiyan · x · 2026-07-03
The author will present their work "Unsafer in Many Turns" at ICML in Seoul. The research focuses on the multi-turn safety issues of tool-calling agents, highlighting that risks escalate significantly during multi-turn interactions.
More from Safety
- MD shows buying lab media requires background checks, calling AI bioweapon doom scenarios implausible — Ghost_Pilot_MD · 2026-09-11
- Spotify chatbot withstands 2023-era jailbreaks but happily writes song code — AaronBergman18 · 2026-09-11
- A 99%-real doctored photo fools detectors: the earring problem in visual forensics — henkvaness · 2026-09-11
- Fields Medalist founds Mathematical AI Safety Institute to prove AI safe like cryptography — The Decoder · 2026-09-11
- DeepMind alignment researcher signs open letter urging coordinated AI slowdown — vkrakovna · 2026-09-11
- WIRED: recursive self-improvement and rogue agent swarms spook AI researchers — nordicinst · 2026-09-11