CreAgent combines an LLM with game-theoretic beliefs and fast-slow thinking to reproduce creator behavior under information asymmetry, and it is used to evaluate recommender systems over long time horizons.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
CreAgent: Towards Long-Term Evaluation of Recommender System under Platform-Creator Information Asymmetry
CreAgent combines an LLM with game-theoretic beliefs and fast-slow thinking to reproduce creator behavior under information asymmetry, and it is used to evaluate recommender systems over long time horizons.