The EpisTwin: A Knowledge Graph-Grounded Neuro-Symbolic Architecture for Personal AI
This work aims to improve trustworthy Personal AI by enabling holistic sensemaking of fragmented user data.
This paper addresses the problem of fragmented user data hindering Personal AI by introducing EpisTwin, a neuro-symbolic framework. EpisTwin grounds generative reasoning in a user-centric Personal Knowledge Graph, lifting heterogeneous data into semantic triples using Multimodal Language Models, and performing complex reasoning via an agentic coordinator. The framework demonstrates robust results on the PersonalQA-71-100 benchmark.
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.