RUVA: Personalized Transparent On-Device Graph Reasoning

Gabriele Conte; Alessio Mattiace; Gianni Carmosino; Potito Aghilar; Giovanni Servedio; Francesco Musicco; Vito Walter Anelli; Tommaso Di Noia

cs.AIFeb 17, 2026

RUVA: Personalized Transparent On-Device Graph Reasoning

Authors: Gabriele Conte, Alessio Mattiace, Gianni Carmosino, Potito Aghilar, Giovanni Servedio, Francesco Musicco, Vito Walter Anelli, Tommaso Di Noia,

Organizations: Politecnico di Bari · Universit`a degli Studi della Tuscia

Abstract

The Personal AI landscape is currently dominated by "Black Box" Retrieval-Augmented Generation. While standard vector databases offer statistical matching, they suffer from a fundamental lack of accountability: when an AI hallucinates or retrieves sensitive data, the user cannot inspect the cause nor correct the error. Worse, "deleting" a concept from a vector space is mathematically imprecise, leaving behind probabilistic "ghosts" that violate true privacy. We propose Ruva, the first "Glass Box" architecture designed for Human-in-the-Loop Memory Curation. Ruva grounds Personal AI in a Personal Knowledge Graph, enabling users to inspect what the AI knows and to perform precise redaction of specific facts. By shifting the paradigm from Vector Matching to Graph Reasoning, Ruva ensures the "Right to be Forgotten." Users are the editors of their own lives; Ruva hands them the pen. The project and the demo video are available at http://sisinf00.poliba.it/ruva/.

Figures & tables

Figure 1: The Ruva architecture. The Ingestion Workflow transforms multimodal data into semantic triples to populate the Personal Knowledge Graph. The Retrieval Workflow performs graph traversal to generate grounded, hallucination-free answers, entirely on-device.

Panel of Figure 2 — Figure 2: Ruva App Screenshots. Figure 2(a) shows the inferred PKG, while in Figure 2(b) Ruva answers leveraging multimodal data.

Panel of Figure 3 — Figure 3: Judicial scores for Scenario 1 and 2 , and $\Delta$ scores for 3 .

Human-in-the-Loop AI

Human-in-the-loop AI combines human feedback, oversight, and decision-making with machine learning and autonomous systems.

See all 288 papers

Opal: Private Memory for Personal AI
Apr 2, 2026Darya Kaviani, Alp Eren Ozdarendeli, Jinhao Zhu +2Agent Memory
UC Berkeley · Google DeepMind
Beyond Private Training: The New Landscape of AI Privacy
Sep 16, 2026Sean Culatana, Kang LiPrivacy Auditing Graph-Based Retrieval
Atlassian Mountain View, CA · Atlassian Bellevue, WA
PersonalAI 2.0: Enhancing knowledge graph traversal/retrieval with planning mechanism for Personalized LLM Agents
May 13, 2026Mikhail Menschikov, Matvey Iskornev, Alexander Kharitonov +8Multi-Hop QA Graph Retrieval-Augmented Generation
Skoltech, Moscow, Russia · SberAI, Moscow, Russia · Huawei, Moscow, Russia +4

Apr 2, 2026J/K move · Enter open · S save

Opal: Private Memory for Personal AI

Darya Kaviani, Alp Eren Ozdarendeli, Jinhao Zhu, Yu Ding+1

UC Berkeley · Google DeepMind

Agent Memory

Open paper AskPDF arXiv

Personal AI systems increasingly retain long-term memory of user activity, including documents, emails, messages, meetings, and ambient recordings. Trusted hardware can keep this data private, but struggles to scale with a growing datastore. This pushes the data to external storage, which exposes retrieval access patterns that leak private information to the application provider. Oblivious RAM (ORAM) is a cryptographic primitive that can hide these patterns, but it requires a fixed access budget, precluding the query-dependent traversals that agentic memory systems rely on for accuracy. We present Opal, a private memory system for personal AI. Our key insight is to decouple all data-dependent reasoning from the bulk of personal data, confining it to the trusted enclave. Untrusted disk then sees only fixed, oblivious memory accesses. This enclave-resident component uses a lightweight knowledge graph to capture personal context that semantic search alone misses and handles continuous ingestion by piggybacking reindexing and capacity management on every ORAM access. Evaluated on a comprehensive synthetic personal-data pipeline driven by stochastic communication models, Opal improves retrieval accuracy by 13 percentage points over semantic search and achieves 29x higher throughput with 15x lower infrastructure cost than a secure baseline. Opal is under consideration for deployment to millions of users at a major AI provider.

Abstract

Human-in-the-Loop AI

Explore similar work

Opal: Private Memory for Personal AI

Beyond Private Training: The New Landscape of AI Privacy

PersonalAI 2.0: Enhancing knowledge graph traversal/retrieval with planning mechanism for Personalized LLM Agents