# CI-Work: Benchmarking Contextual Integrity in Enterprise LLM Agents

arXiv: https://arxiv.org/abs/2604.21308 · HTML: https://mlsanity.com/paper/2604.21308/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use.
- Builds on 21 of its 38 references that are in the map.
- First posted on arXiv 23 Apr 2026.

## Placed in

- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)

## Builds on (most cited first, 21 of 21)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Towards Understanding Sycophancy in Language Models](https://mlsanity.com/paper/2310.13548/) (2023)
- [Identifying the Risks of LM Agents with an LM-Emulated Sandbox](https://mlsanity.com/paper/2309.15817/) (2023)
- [Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory](https://mlsanity.com/paper/2310.17884/) (2023)
- [PrivacyLens: Evaluating Privacy Norm Awareness of Language Models in Action](https://mlsanity.com/paper/2409.00138/) (2024)
- [AgentDAM: Privacy Leakage Evaluation for Autonomous Web Agents](https://mlsanity.com/paper/2503.09780/) (2025)
- [STAIR: Improving Safety Alignment with Introspective Reasoning](https://mlsanity.com/paper/2502.02384/) (2025)
- [CRMArena: Understanding the Capacity of LLM Agents to Perform Professional CRM Tasks in Realistic Environments](https://mlsanity.com/paper/2411.02305/) (2024)
- [WorkBench: a Benchmark Dataset for Agents in a Realistic Workplace Setting](https://mlsanity.com/paper/2405.00823/) (2024)
- [GoldCoin: Grounding Large Language Models in Privacy Laws via Contextual Integrity Theory](https://mlsanity.com/paper/2406.11149/) (2024)
- [CI-Bench: Benchmarking Contextual Integrity of AI Assistants on Synthetic Data](https://mlsanity.com/paper/2409.13903/) (2024)
- [Privacy in Action: Towards Realistic Privacy Mitigation and Evaluation for LLM-Powered Agents](https://mlsanity.com/paper/2509.17488/) (2025)
- [Contextual Integrity in LLMs via Reasoning and Reinforcement Learning](https://mlsanity.com/paper/2506.04245/) (2025)
- [CIMemories: A Compositional Benchmark for Contextual Integrity of Persistent Memory in LLMs](https://mlsanity.com/paper/2511.14937/) (2025)
- [Benchmarking Deep Search over Heterogeneous Enterprise Data](https://mlsanity.com/paper/2506.23139/) (2025)
- [Privacy Bias in Language Models: A Contextual Integrity-based Auditing Metric](https://mlsanity.com/paper/2409.03735/) (2024)
- [The Impact of Scaling Training Data on Adversarial Robustness](https://mlsanity.com/paper/2509.25927/) (2025)

## Built on by (most cited first, 14 of 14)

- [GateMem: Benchmarking Memory Governance in Multi-Principal Shared-Memory Agents](https://mlsanity.com/paper/2606.18829/) (2026)
- [The Authorization-Execution Gap Is a Major Safety and Security Problem in Open-World Agents](https://mlsanity.com/paper/2605.11003/) (2026)
- [POLAR-Bench: A Diagnostic Benchmark for Privacy-Utility Trade-offs in LLM Agents](https://mlsanity.com/paper/2605.19127/) (2026)
- [PrivacyAlign: Contextual Privacy Alignment for LLM Agents](https://mlsanity.com/paper/2606.21710/) (2026)
- [PiSAs: Benchmarking Contextual Integrity in Multi-User Agentic Systems](https://mlsanity.com/paper/2607.05318/) (2026)
- [CIDER: A Dataset of Contextual Disclosure Boundaries for Privacy Preference Alignment](https://mlsanity.com/paper/2608.09164/) (2026)
- [Inferring Hidden User Models from the Behavior of Personalized LLM Agents](https://mlsanity.com/paper/2609.03815/) (2026)
- ["Nothing to See Here'': Unintended Disclosure through Revision Traces of LLM Deliverables](https://mlsanity.com/paper/2609.35408/) (2026)
- [Can Agents Trust Their Skills? Uncovering Unsafe Chains of Trust in Skill-Based LLM Agents](https://mlsanity.com/paper/2609.39065/) (2026)
- [Deny Without Disabling: Authorization-Paired Evaluation and Control for Multi-Agent Systems](https://mlsanity.com/paper/2610.00371/) (2026)
- [AgentPrivArena: Evaluating and Auditing Real-world AI Agent Privacy](https://mlsanity.com/paper/2610.06454/) (2026)
- [RelLedger: Relational Information Governance for LLM Agent Organizations](https://mlsanity.com/paper/2610.16281/) (2026)
- [Empowering Edge Agents: A Systematic Analysis of Edge-Cloud Collaboration in LLM Agent Execution](https://mlsanity.com/paper/2610.17816/) (2026)
- [AgentCIScope: Grounded Contextual Integrity Evaluation for LLM Agents](https://mlsanity.com/paper/2610.19158/) (2026)

## Abstract (arXiv)

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.