Skip to yearly menu bar Skip to main content


A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis

Izzeddin Gur · Hiroki Furuta · Austin Huang · Mustafa Safdari · Yutaka Matsuo · Douglas Eck · Aleksandra Faust

Halle A 7
[ ] [ Visit Oral 1B ]
Tue 7 May 1 a.m. — 1:15 a.m. PDT


Pre-trained large language models (LLMs) have recently achieved better generalization and sample efficiency in autonomous web automation.However, the performance on real-world websites has still suffered from (1) open domainness, (2) limited context length, and (3) lack of inductive bias on HTML.We introduce WebAgent, an LLM-driven agent that learns from self-experience to complete tasks on real websites following natural language instructions.WebAgent plans ahead by decomposing instructions into canonical sub-instructions, summarizes long HTML documents into task-relevant snippets, and acts on websites via Python programs generated from those.We design WebAgent with Flan-U-PaLM, for grounded code generation, and HTML-T5, new pre-trained LLMs for long HTML documents using local and global attention mechanisms and a mixture of long-span denoising objectives, for planning and summarization.We empirically demonstrate that our modular recipe improves the success on real websites by over 50%, and that HTML-T5 is the best model to solve various HTML understanding tasks; achieving 18.7% higher success rate than the prior method on MiniWoB web automation benchmark, and SoTA performance on Mind2Web, an offline task planning evaluation.

Chat is not available.