The EpisTwin: A Knowledge Graph-Grounded Neuro-Symbolic Architecture for Personal AI

2026-03-06

AI Summary

This work addresses the challenges of fragmented user data in personal artificial intelligence and the inability of existing retrieval-augmented generation (RAG) methods to effectively model semantic topology and temporal dependencies. To this end, we propose EpisTwin, a novel neuro-symbolic architecture that uniquely integrates user-centric personal knowledge graphs with dynamic visual relocalization. Leveraging multimodal large language models, EpisTwin transforms heterogeneous cross-application data into semantic triples and employs an intelligent coordinator to unify graph-based RAG with online visual refinement, enabling verifiable neuro-symbolic reasoning. We also introduce PersonalQA-71-100, a synthetic evaluation benchmark that significantly enhances the trustworthiness and holistic perception capabilities of personal AI systems, as demonstrated across multiple state-of-the-art evaluators.

Technology Category

• Humans and AI: Human-Aware Planning and Behavior Prediction
• Philosophy and Ethics of AI: AI & Epistemology
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

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.

Problem

• Personal AI
• data fragmentation
• semantic topology
• temporal dependencies
• knowledge graph

Innovation

• Neuro-Symbolic Architecture
• Personal Knowledge Graph
• Graph Retrieval-Augmented Generation
• Multimodal Language Models
• Online Deep Visual Refinement