GUI Agents Papers
Star · 751

Large Language Models Empowered Personalized Web Agents

Hongru Cai, Yongqi Li, Wenjie Wang, Fengbin Zhu, Xiaoyu Shen, Wenjie Li, Tat-Seng Chua

🏛 Institutions
NUS, PolyU, USTC, Eastern Institute of Technology, Ningbo
📅 Date
October 22, 2024
📑 Publisher
WWW 2025
💻 Env
Web
🔑 Keywords
TLDR

This paper formulates personalized web agents that condition on user profiles and historical web behaviors, introduces the PersonalWAB benchmark for evaluating that setting, and proposes the PUMA alignment method. PUMA uses a memory bank with task-specific retrieval plus fine-tuning and preference optimization to improve user-dependent action execution.

Open paper Edit on GitHub Report issue
Related papers