The EpisTwin: A Knowledge Graph-Grounded Neuro-Symbolic Architecture for Personal AI
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915839510315008 |
|---|---|
| author | Servedio, Giovanni Aghilar, Potito Mattiace, Alessio Carmosino, Gianni Musicco, Francesco Conte, Gabriele Anelli, Vito Walter Di Noia, Tommaso Donini, Francesco Maria |
| author_facet | Servedio, Giovanni Aghilar, Potito Mattiace, Alessio Carmosino, Gianni Musicco, Francesco Conte, Gabriele Anelli, Vito Walter Di Noia, Tommaso Donini, Francesco Maria |
| contents | Personal Artificial Intelligence is currently hindered by the fragmentation of user data across isolated silos. While Retrieval-Augmented Generation offers a partial remedy, its reliance on unstructured vector similarity fails to capture the latent semantic topology and temporal dependencies essential for holistic sensemaking. We introduce EpisTwin, a neuro-symbolic framework that grounds generative reasoning in a verifiable, user-centric Personal Knowledge Graph. EpisTwin leverages Multimodal Language Models to lift heterogeneous, cross-application data into semantic triples. At inference, EpisTwin enables complex reasoning over the personal semantic graph via an agentic coordinator that combines Graph Retrieval-Augmented Generation with Online Deep Visual Refinement, dynamically re-grounding symbolic entities in their raw visual context. We also introduce PersonalQA-71-100, a synthetic benchmark designed to simulate a realistic user's digital footprint and evaluate EpisTwin performance. Our framework demonstrates robust results across a suite of state-of-the-art judge models, offering a promising direction for trustworthy Personal AI. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_06290 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | The EpisTwin: A Knowledge Graph-Grounded Neuro-Symbolic Architecture for Personal AI Servedio, Giovanni Aghilar, Potito Mattiace, Alessio Carmosino, Gianni Musicco, Francesco Conte, Gabriele Anelli, Vito Walter Di Noia, Tommaso Donini, Francesco Maria Artificial Intelligence Computation and Language Personal Artificial Intelligence is currently hindered by the fragmentation of user data across isolated silos. While Retrieval-Augmented Generation offers a partial remedy, its reliance on unstructured vector similarity fails to capture the latent semantic topology and temporal dependencies essential for holistic sensemaking. We introduce EpisTwin, a neuro-symbolic framework that grounds generative reasoning in a verifiable, user-centric Personal Knowledge Graph. EpisTwin leverages Multimodal Language Models to lift heterogeneous, cross-application data into semantic triples. At inference, EpisTwin enables complex reasoning over the personal semantic graph via an agentic coordinator that combines Graph Retrieval-Augmented Generation with Online Deep Visual Refinement, dynamically re-grounding symbolic entities in their raw visual context. We also introduce PersonalQA-71-100, a synthetic benchmark designed to simulate a realistic user's digital footprint and evaluate EpisTwin performance. Our framework demonstrates robust results across a suite of state-of-the-art judge models, offering a promising direction for trustworthy Personal AI. |
| title | The EpisTwin: A Knowledge Graph-Grounded Neuro-Symbolic Architecture for Personal AI |
| topic | Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2603.06290 |