WebWISE: Web Interface Control and Sequential Exploration with Large Language Models

TL;DR

This paper introduces WebWISE, a method that uses large language models to automate web tasks through sequential program generation based on filtered DOM observations, achieving high performance with minimal examples.

Contribution

WebWISE presents a novel approach combining in-context learning with DOM filtering for efficient web task automation, outperforming prior methods requiring extensive demonstrations.

Findings

Achieves comparable or better performance with only one in-context example.

Uses step-by-step program generation based on filtered DOM observations.

Effective on the MiniWob++ benchmark.

Abstract

The paper investigates using a Large Language Model (LLM) to automatically perform web software tasks using click, scroll, and text input operations. Previous approaches, such as reinforcement learning (RL) or imitation learning, are inefficient to train and task-specific. Our method uses filtered Document Object Model (DOM) elements as observations and performs tasks step-by-step, sequentially generating small programs based on the current observations. We use in-context learning, either benefiting from a single manually provided example, or an automatically generated example based on a successful zero-shot trial. We evaluate the proposed method on the MiniWob++ benchmark. With only one in-context example, our WebWISE method achieves similar or better performance than other methods that require many demonstrations or trials.