LITMUS: Benchmarking Behavioral Jailbreaks of LLM Agents in Real OS Environments

Chiyu Zhang, Huiqin Yang, Bendong Jiang, Xiaolei Zhang, Yiran Zhao, Ruyi Chen

By Callan Zhang · May 11, 2026 · Editorial standards →

Summarised from the primary source with AI assistance under human editorial oversight. Turing Wire is not a primary source — read the original for the authoritative account.

Source: arXiv cs.CL