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

TL;DR
AutoWebGLM is a large language model-based web navigation agent that simplifies webpage data, uses hybrid training, and employs reinforcement learning to outperform existing models like GPT-4 in real-world web navigation tasks.
Contribution
The paper introduces AutoWebGLM, a novel web navigation agent based on ChatGLM3-6B, with an HTML simplification algorithm, hybrid training data, and reinforcement learning for improved web task performance.
Findings
AutoWebGLM outperforms GPT-4 on web navigation benchmarks.
The HTML simplification algorithm effectively preserves vital webpage information.
Reinforcement learning enhances webpage comprehension and task decomposition.
Abstract
Large language models (LLMs) have fueled many intelligent web agents, but most existing ones perform far from satisfying in real-world web navigation tasks due to three factors: (1) the complexity of HTML text data (2) versatility of actions on webpages, and (3) task difficulty due to the open-domain nature of the web. In light of these challenges, we develop the open AutoWebGLM based on ChatGLM3-6B. AutoWebGLM can serve as a powerful automated web navigation agent that outperform GPT-4. Inspired by human browsing patterns, we first design an HTML simplification algorithm to represent webpages with vital information preserved succinctly. We then employ a hybrid human-AI method to build web browsing data for curriculum training. Finally, we bootstrap the model by reinforcement learning and rejection sampling to further facilitate webpage comprehension, browser operations, and efficient…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsWeb Data Mining and Analysis
MethodsAttention Is All You Need · Dropout · Layer Normalization · Adam · Dense Connections · Residual Connection · Position-Wise Feed-Forward Layer · Linear Layer · Byte Pair Encoding · Absolute Position Encodings
