AugTwins

Anushhka Thakur, Mateo Larrea Ferro, Dunya Baradari, Lars Langenbach

Track: Artwork

Keywords: AugTwins, interactive artwork, AI symbionts, digital twins, digital doubles, MetaHuman, cloned voice, persistent memory, autobiographical memory, large language model, identity, empathy, narrative continuity, human–machine interaction, recognition, reciprocity

TL;DR: AugTwins is an interactive artwork where lifelike digital doubles remember past conversations, speak in cloned voices, and adapt over time, exploring identity, memory, and empathy in human–machine interaction.

Abstract: AugTwins is a pipeline for creating interactive human digital twins that engage users in natural, face-to-face conversation. By integrating photorealistic embodiment (Unreal Engine MetaHuman), voice cloning, and a hybrid multi-agent memory architecture, the system enables realistic encounters with digital representations of real people. Each twin is grounded in the person’s life story, experiences, and knowledge while maintaining conversational continuity across sessions. The architecture combines fast pattern matching for common queries with deep semantic retrieval for biographical details, coordinated through metacognitive monitoring that guides socially appropriate responses. We present two deployed twins demonstrating faithful personality representation and accurate biographical recall. Beyond technical implementation, AugTwins invites reflection on how memory and embodiment shape identity, and what it means to extend human presence through computational reconstruction.

Submission Number: 234