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

arXiv:2307.12856v4 Announce Type: replace
Abstract: 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 …

abstract arxiv automation autonomous bias context cs.ai cs.cl cs.lg efficiency html inductive language language models large language large language models llms performance planning sample synthesis type understanding web websites world