works on
hierarchical understanding 1memory benchmarks 1personalized agents 1synthetic user data 1user modeling 1

From the 1 of 1 linked paper with an AI index.

collaborators
Showing cs.AIShow all

1 paper · 1 filter

cs.AI2026

Setoka: A Benchmark for Hierarchical User Understanding in Personalized Agents over Heterogeneous Data

Lingyang Zeng, Guangze Chen, Kaichen Yu +9

Setoka is a benchmark that evaluates how well memory‑augmented personalized agents understand users at multiple hierarchical levels—semantic, episodic, behavior patterns, and perso…