Large Language Models Empowered Personalized Web Agents

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Cai, Hongru, Li, Yongqi, Wang, Wenjie, Zhu, Fengbin, Shen, Xiaoyu, Li, Wenjie, Chua, Tat-Seng
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915211760369664
author Cai, Hongru
Li, Yongqi
Wang, Wenjie
Zhu, Fengbin
Shen, Xiaoyu
Li, Wenjie
Chua, Tat-Seng
author_facet Cai, Hongru
Li, Yongqi
Wang, Wenjie
Zhu, Fengbin
Shen, Xiaoyu
Li, Wenjie
Chua, Tat-Seng
contents Web agents have emerged as a promising direction to automate Web task completion based on user instructions, significantly enhancing user experience. Recently, Web agents have evolved from traditional agents to Large Language Models (LLMs)-based Web agents. Despite their success, existing LLM-based Web agents overlook the importance of personalized data (e.g., user profiles and historical Web behaviors) in assisting the understanding of users' personalized instructions and executing customized actions. To overcome the limitation, we first formulate the task of LLM-empowered personalized Web agents, which integrate personalized data and user instructions to personalize instruction comprehension and action execution. To address the absence of a comprehensive evaluation benchmark, we construct a Personalized Web Agent Benchmark (PersonalWAB), featuring user instructions, personalized user data, Web functions, and two evaluation paradigms across three personalized Web tasks. Moreover, we propose a Personalized User Memory-enhanced Alignment (PUMA) framework to adapt LLMs to the personalized Web agent task. PUMA utilizes a memory bank with a task-specific retrieval strategy to filter relevant historical Web behaviors. Based on the behaviors, PUMA then aligns LLMs for personalized action execution through fine-tuning and direct preference optimization. Extensive experiments validate the superiority of PUMA over existing Web agents on PersonalWAB.
format Preprint
id arxiv_https___arxiv_org_abs_2410_17236
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Large Language Models Empowered Personalized Web Agents
Cai, Hongru
Li, Yongqi
Wang, Wenjie
Zhu, Fengbin
Shen, Xiaoyu
Li, Wenjie
Chua, Tat-Seng
Computation and Language
Artificial Intelligence
Information Retrieval
Web agents have emerged as a promising direction to automate Web task completion based on user instructions, significantly enhancing user experience. Recently, Web agents have evolved from traditional agents to Large Language Models (LLMs)-based Web agents. Despite their success, existing LLM-based Web agents overlook the importance of personalized data (e.g., user profiles and historical Web behaviors) in assisting the understanding of users' personalized instructions and executing customized actions. To overcome the limitation, we first formulate the task of LLM-empowered personalized Web agents, which integrate personalized data and user instructions to personalize instruction comprehension and action execution. To address the absence of a comprehensive evaluation benchmark, we construct a Personalized Web Agent Benchmark (PersonalWAB), featuring user instructions, personalized user data, Web functions, and two evaluation paradigms across three personalized Web tasks. Moreover, we propose a Personalized User Memory-enhanced Alignment (PUMA) framework to adapt LLMs to the personalized Web agent task. PUMA utilizes a memory bank with a task-specific retrieval strategy to filter relevant historical Web behaviors. Based on the behaviors, PUMA then aligns LLMs for personalized action execution through fine-tuning and direct preference optimization. Extensive experiments validate the superiority of PUMA over existing Web agents on PersonalWAB.
title Large Language Models Empowered Personalized Web Agents
topic Computation and Language
Artificial Intelligence
Information Retrieval
url https://arxiv.org/abs/2410.17236