CI-Work: Benchmarking Contextual Integrity in Enterprise LLM Agents

Computer Science > Cryptography and Security [Submitted on 23 Apr 2026] CI-Work: Benchmarking Contextual Integrity in Enterprise LLM Agents Wenjie Fu, Xiaoting Qin, Jue Zhang, Qingwei Lin, Lukas Wutschitz, Robert Sim, Saravan Rajmohan, Dongmei Zhang Enterprise LLM agents can dramatically improve workplace productivity, but their core capability, retrieving and using internal context to act on a user's behalf, also creates new risks for sensitive information leakage. We introduce CI-Work, a Contextual Integrity (CI)-grounded benchmark that simulates enterprise workflows across five information-flow directions and evaluates whether agents can convey essential content while withholding sensitive context in dense retrieval settings. Our evaluation of frontier models reveals that privacy failures are prevalent (violation rates range from 15.8%-50.9%, with leakage reaching up to 26.7%) and uncovers a counterintuitive trade-off critical for industrial deployment: higher task utility often correlates with increased privacy violations. Moreover, the massive scale of enterprise data and potential user behavior further amplify this vulnerability. Simply increasing model size or reasoning depth fails to address the problem. We conclude that safeguarding enterprise workflows requires a paradigm shift, moving beyond model-centric scaling toward context-centric architectures. Subjects: Cryptography and Security (cs.CR); Computation and Language (cs.CL) Cite as: arXiv:2604.21308 [cs.CR]   (or arXiv:2604.21308v1 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2604.21308 Focus to learn more Journal reference: The 64th Annual Meeting of the Association for Computational Linguistics (ACL'2026) -- Industry Track Submission history From: Wenjie Fu [view email] [v1] Thu, 23 Apr 2026 06:00:22 UTC (10,630 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2026-04 Change to browse by: cs cs.CL References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)