AutoWebGLM: A Large Language Model-based Web Navigating Agent
Hanyu Lai, Xiao Liu, Iat Long Iong, Shuntian Yao, Yuxuan Chen, Pengbo Shen, Hao Yu, Hanchen Zhang, Xiaohan Zhang, Yuxiao Dong, Jie Tang
- 🏛 Institutions
- Tsinghua, Zhipu, Beijing University of Posts and Telecommunications, University of Chinese Academy of Sciences
- 📅 Date
- April 4, 2024
- 📑 Publisher
- KDD 2024
- 💻 Env
- Web
- 🔑 Keywords
TLDR
AutoWebGLM is a web-navigation agent built on ChatGLM3-6B that combines HTML simplification, hybrid human-AI trajectory construction, and reinforcement learning with rejection sampling. The paper also introduces the bilingual AutoWebBench benchmark for real-world web navigation and uses it together with other benchmarks to evaluate the system.
Related papers
- AgentCPM‑GUI: Building Mobile‑Use Agents with Reinforcement Fine‑TuningJune 2, 2025 · EMNLP 2025 System Demonstrations
- WebArena-Infinity: Generating Browser Environments with Verifiable Tasks at ScaleMarch 2026 · Blog Post
- WebGym: Scaling Training Environments for Visual Web Agents with Realistic TasksJanuary 5, 2026 · arXiv
- Web-Shepherd: Advancing PRMs for Reinforcing Web AgentsMay 21, 2025 · NeurIPS 2025 (Spotlight)
- ClawGUI: A Unified Framework for Training, Evaluating, and Deploying GUI AgentsApril 13, 2026 · arXiv
- Don't Act Blindly: Robust GUI Automation via Action-Effect Verification and Self-CorrectionApril 7, 2026 · ACL 2026