AllTogether：探究拼接提示在大语言模型网页导航中的有效性
AllTogether: Investigating the Efficacy of Spliced Prompt for Web Navigation using Large Language Models
AI总结：
本文提出 AllTogether 标准化提示模板以增强任务上下文表示，并通过提示学习与指令微调验证其能提升大语言模型在 HTML 网页导航中的性能。
摘要：
大语言模型（LLMs）已成为用于网页导航任务的有前景的智能体，能够理解目标并与网页进行交互。然而，拼接提示在此类任务中的效率仍未得到充分探索。我们提出了 AllTogether，这是一种标准化的提示模板，可增强任务上下文表示，从而提升 LLMs 在基于 HTML 的网页导航中的性能。我们基于开源的 Llama-2 和可通过 API 访问的 GPT 模型，通过提示学习和指令微调来评估该方法的效果。结果表明，GPT-4 等模型在网页导航任务中优于较小的模型。此外，我们发现 HTML 片段和历史轨迹的长度会显著影响性能，并且与实时环境反馈相比，预先提供的逐步指令效果较差。总体而言，我们相信这项工作为未来由 LLM 驱动的网页智能体研究提供了有价值的见解。
英文摘要：
Large Language Models (LLMs) have emerged as promising agents for web navigation tasks, interpreting objectives and interacting with web pages. However, the efficiency of spliced prompts for such tasks remains underexplored. We introduces AllTogether, a standardized prompt template that enhances task context representation, thereby improving LLMs' performance in HTML-based web navigation. We evaluate the efficacy of this approach through prompt learning and instruction finetuning based on open-source Llama-2 and API-accessible GPT models. Our results reveal that models like GPT-4 outperform smaller models in web navigation tasks. Additionally, we find that the length of HTML snippet and history trajectory significantly influence performance, and prior step-by-step instructions prove less effective than real-time environmental feedback. Overall, we believe our work provides valuable insights for future research in LLM-driven web agents.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
