# Personalizing Agent Privacy Decisions via Logical Entailment

arXiv: https://arxiv.org/abs/2512.05065 · HTML: https://mlsanity.com/paper/2512.05065/

## Key facts

- Cited by 4 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 32 of its 103 references that are in the map.
- First posted on arXiv 4 Dec 2025.

## 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, 30 of 32)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [A Survey on Large Language Model based Autonomous Agents](https://mlsanity.com/paper/2308.11432/) (2023)
- [Gemma 3 Technical Report](https://mlsanity.com/paper/2503.19786/) (2025)
- [Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection](https://mlsanity.com/paper/2302.12173/) (2023)
- [A-MEM: Agentic Memory for LLM Agents](https://mlsanity.com/paper/2502.12110/) (2025)
- [Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory](https://mlsanity.com/paper/2504.19413/) (2025)
- [Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoning](https://mlsanity.com/paper/2305.12295/) (2023)
- [Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory](https://mlsanity.com/paper/2310.17884/) (2023)
- [ZebraLogic: On the Scaling Limits of LLMs for Logical Reasoning](https://mlsanity.com/paper/2502.01100/) (2025)
- [Don't Hallucinate, Abstain: Identifying LLM Knowledge Gaps via Multi-LLM Collaboration](https://mlsanity.com/paper/2402.00367/) (2024)
- [PrivacyLens: Evaluating Privacy Norm Awareness of Language Models in Action](https://mlsanity.com/paper/2409.00138/) (2024)
- [The Unreliability of Explanations in Few-shot Prompting for Textual Reasoning](https://mlsanity.com/paper/2205.03401/) (2022)
- [LINC: A Neurosymbolic Approach for Logical Reasoning by Combining Language Models with First-Order Logic Provers](https://mlsanity.com/paper/2310.15164/) (2023)
- [AbstentionBench: Reasoning LLMs Fail on Unanswerable Questions](https://mlsanity.com/paper/2506.09038/) (2025)
- [SatLM: Satisfiability-Aided Language Models Using Declarative Prompting](https://mlsanity.com/paper/2305.09656/) (2023)
- [Contextual Agent Security: A Policy for Every Purpose](https://mlsanity.com/paper/2501.17070/) (2025)
- [Fully Autonomous AI Agents Should Not be Developed](https://mlsanity.com/paper/2502.02649/) (2025)
- [GoldCoin: Grounding Large Language Models in Privacy Laws via Contextual Integrity Theory](https://mlsanity.com/paper/2406.11149/) (2024)
- [Operationalizing Contextual Integrity in Privacy-Conscious Assistants](https://mlsanity.com/paper/2408.02373/) (2024)
- [CI-Bench: Benchmarking Contextual Integrity of AI Assistants on Synthetic Data](https://mlsanity.com/paper/2409.13903/) (2024)
- [PrivaCI-Bench: Evaluating Privacy with Contextual Integrity and Legal Compliance](https://mlsanity.com/paper/2502.17041/) (2025)
- [Protecting Users From Themselves: Safeguarding Contextual Privacy in Interactions with Conversational Agents](https://mlsanity.com/paper/2502.18509/) (2025)
- [CIMemories: A Compositional Benchmark for Contextual Integrity of Persistent Memory in LLMs](https://mlsanity.com/paper/2511.14937/) (2025)
- [Towards Automating Data Access Permissions in AI Agents](https://mlsanity.com/paper/2511.17959/) (2025)
- [Discovering Smart Home Internet of Things Privacy Norms Using Contextual Integrity](https://mlsanity.com/paper/1805.06031/) (2018)
- [The Feasibility of Dynamically Granted Permissions: Aligning Mobile Privacy with User Preferences](https://mlsanity.com/paper/1703.02090/) (2017)
- [Understanding Privacy Norms Around LLM-Based Chatbots: A Contextual Integrity Perspective](https://mlsanity.com/paper/2508.06760/) (2025)
- [Evaluating the Contextual Integrity of Privacy Regulation: Parents' IoT Toy Privacy Norms Versus COPPA](https://mlsanity.com/paper/1903.05152/) (2019)
- [Benchmarking LLM Privacy Recognition for Social Robot Decision Making](https://mlsanity.com/paper/2507.16124/) (2025)
- [Towards Aligning Personalized Conversational Recommendation Agents with Users' Privacy Preferences](https://mlsanity.com/paper/2508.07672/) (2025)

## Built on by (most cited first, 4 of 4)

- [An AI Agent Execution Environment to Safeguard User Data](https://mlsanity.com/paper/2604.19657/) (2026)
- [PrivacySIM: Evaluating LLM Simulation of User Privacy Behavior](https://mlsanity.com/paper/2605.12147/) (2026)
- [MemArena: An Ego-Centric Benchmark for On-Device Agentic Personal Memory Assistants at Scale](https://mlsanity.com/paper/2608.02613/) (2026)
- [CIDER: A Dataset of Contextual Disclosure Boundaries for Privacy Preference Alignment](https://mlsanity.com/paper/2608.09164/) (2026)

## Abstract (arXiv)

Personal large language model (LLM) agents increasingly perform tasks that require access to user data, raising concerns about appropriate data disclosure. We show that relying solely on LLMs to make data-sharing decisions is insufficient. Prompting LLMs with general privacy norms fails to capture individual users' privacy preferences, while providing prior user data-sharing decisions through in-context learning (ICL) leads to unreliable and opaque reasoning. To address these limitations, we propose ARIEL (Agentic Reasoning with Individualized Entailment Logic), a framework that combines LLMs with rule-based logic to enable structured, personalized privacy reasoning. The core mechanism of ARIEL determines whether a user's prior decision on a data-sharing request textitlogically entails the same decision for a new request. Experimental evaluations using advanced models and public datasets show that ARIEL reduces the F1 error rate for appropriate judgments by 40.6% compared to standard ICL-based reasoning, indicating that ARIEL is effective at correctly judging requests where the user would approve data sharing. These results demonstrate that integrating LLMs with logical entailment provides an effective and interpretable approach for automating personalized privacy decisions.