Customer-R1: Personalized Simulation of Human Behaviors via RL-based LLM Agent in Online Shopping

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Wang, Ziyi, Lu, Yuxuan, Zhang, Yimeng, Huang, Jing, Wang, Dakuo
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909853894574080
author Wang, Ziyi
Lu, Yuxuan
Zhang, Yimeng
Huang, Jing
Wang, Dakuo
author_facet Wang, Ziyi
Lu, Yuxuan
Zhang, Yimeng
Huang, Jing
Wang, Dakuo
contents Simulating step-wise human behavior with Large Language Models (LLMs) has become an emerging research direction, enabling applications in various practical domains. While prior methods, including prompting, supervised fine-tuning (SFT), and reinforcement learning (RL), have shown promise in modeling step-wise behavior, they primarily learn a population-level policy without conditioning on a user's persona, yielding generic rather than personalized simulations. In this work, we pose a critical question: how can LLM agents better simulate personalized user behavior? We introduce Customer-R1, an RL-based method for personalized, step-wise user behavior simulation in online shopping environments. Our policy is conditioned on an explicit persona, and we optimize next-step rationale and action generation via action correctness reward signals. Experiments on the OPeRA dataset emonstrate that Customer-R1 not only significantly outperforms prompting and SFT-based baselines in next-action prediction tasks, but also better matches users' action distribution, indicating higher fidelity in personalized behavior simulation.
format Preprint
id arxiv_https___arxiv_org_abs_2510_07230
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Customer-R1: Personalized Simulation of Human Behaviors via RL-based LLM Agent in Online Shopping
Wang, Ziyi
Lu, Yuxuan
Zhang, Yimeng
Huang, Jing
Wang, Dakuo
Computation and Language
Simulating step-wise human behavior with Large Language Models (LLMs) has become an emerging research direction, enabling applications in various practical domains. While prior methods, including prompting, supervised fine-tuning (SFT), and reinforcement learning (RL), have shown promise in modeling step-wise behavior, they primarily learn a population-level policy without conditioning on a user's persona, yielding generic rather than personalized simulations. In this work, we pose a critical question: how can LLM agents better simulate personalized user behavior? We introduce Customer-R1, an RL-based method for personalized, step-wise user behavior simulation in online shopping environments. Our policy is conditioned on an explicit persona, and we optimize next-step rationale and action generation via action correctness reward signals. Experiments on the OPeRA dataset emonstrate that Customer-R1 not only significantly outperforms prompting and SFT-based baselines in next-action prediction tasks, but also better matches users' action distribution, indicating higher fidelity in personalized behavior simulation.
title Customer-R1: Personalized Simulation of Human Behaviors via RL-based LLM Agent in Online Shopping
topic Computation and Language
url https://arxiv.org/abs/2510.07230