RESEARCHInvestigateNEXT 12 MONTHS
LITMUS: Benchmarking Behavioral Jailbreaks of LLM Agents in Real OS Environments
arXiv cs.CL — Computation and Language
Factual evidence
What the source reports
Researchers introduced LITMUS, a benchmark to evaluate LLM agent behavior jailbreaks involving dangerous operating system operations.
Inspect the evidence
- Inclusion basis
- Enterprise AI
- Publisher and source type
- arXiv cs.CL — Computation and Language · RESEARCH
- Published by source
- 5 November 2026
- Collected by OneBench
- 6 Nov 2026, 02:01 UK
Stored source excerpt
arXiv:2605.10779v2 Announce Type: replace-cross Abstract: The rapid proliferation of LLM-based autonomous agents in real operating system environments introduces a new category of safety risk beyond…
Short excerpt from the collected text, not the full source. Use the source link to read it in context.
The factual summary is a OneBench synthesis, not a quotation or independent verification. Collection time is not publication time. Open the source for its full context; related reporting can share the same underlying announcement.