agent/papers/items/2026-2605-10779-litmus-benchmarking-behavioral-jailbreaks-of-llm-agents-in-real-os-environments.md

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

---

type: paper title: "LITMUS: Benchmarking Behavioral Jailbreaks of LLM Agents in Real OS Environments" authors: Chiyu Zhang, Huiqin Yang, Bendong Jiang, Xiaolei Zhang, Yiran Zhao, Ruyi Chen, Lu Zhou, Xiaogang Xu, et al. year: 2026 venue: arXiv url: https://arxiv.org/abs/2605.10779 code_url: source: arxiv collected_at: 2026-07-08 published_at: 2026-05-11 updated_at: 2026-05-11 status: queued relevance: high topics:

• agent-evaluation
• agent-safety
• multi-agent
• tool-use methods:

benchmarks:

models:

datasets:

• cs.CR
• cs.CL related_concepts:

related_jobs:

related_experiments:

related_projects:

collection_score: 19 collection_queries: autonomous-agent-llm

One-line Takeaway

Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.

Why Collected

• matched queries: autonomous-agent-llm
• inferred topics: agent-evaluation, agent-safety, multi-agent, tool-use
• arXiv categories: cs.CR, cs.CL
• collection score: 19

Review Checklist

• Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
• Does it include a benchmark, dataset, code, or reproducible experimental setup?
• Should it be promoted from queued to skimmed or summarized?

Links

• arXiv: https://arxiv.org/abs/2605.10779