[HUGGINGFACE]score: 0.48

PsyBer-Agent: Psychology-Driven Simulator for Recommender Systems

September 25, 2026

PsyBer-Agent is a user simulator for recommender systems that models fatigue, affect, and shifting preferences through evolving latent states. It uses Unbalanced Gromov-Wasserstein optimal transport to calibrate simulated behavior against real interaction logs.

HOW THIS AFFECTS YOU

●

builderYou can use this simulator to test recommender systems against realistic, long-term user dynamics rather than static profiles.

●

researcherThis introduces a way to model complex, non-linear user psychological states in closed-loop interaction simulations.

read original ↗huggingface.co

DAILY DIGEST

you don't check 9 sources — we do. one email every morning, read in 2 min. free. unsubscribe anytime. privacy

← back to feed