🤖 AI Summary
This work addresses the challenges of digital social fatigue and the erosion of meaningful in-person connections by proposing a novel social discovery platform that integrates large language models with gamified mechanisms. Built upon the CogniPair cognitive architecture, the system constructs user digital twins to simulate multi-round compatibility dialogues, employs territory-based competition to incentivize offline exploration, and leverages cross-device persistent-memory AI companions to facilitate real-world social engagement. For the first time, it unifies three core components—digital twin matching, gamified motivation, and persistent-memory AI—to bridge simulated compatibility assessment with deployable real-world social environments. Validated on a 551-participant speed-dating dataset from Columbia University, the deployment not only establishes a cost–quality benchmark but also uncovers system-level scalability bottlenecks invisible to component-wise evaluations.
📝 Abstract
We present an LLM-powered social discovery platform that uses digital twins to autonomously evaluate interpersonal compatibility through behavioral simulation. The platform unifies three key pillars: (1) digital twins that engage in autonomous multi-turn conversations on behalf of users to estimate compatibility, (2) gamified territory conquest mechanics that incentivize real-world exploration and create organic settings for in-person encounters, and (3) AI companions that preserve persistent shared memory across devices. Built upon CogniPair's cognitive architecture (Ye et al., 2026), validated on the Columbia Speed Dating dataset (551 participants), our system extends prior simulation-only matching into a fully deployed social discovery environment. Through deployment, we derive empirical cost-quality baselines and identify fundamental scaling bottlenecks that remain hidden in component-level testing alone.