面向对话式网页智能体的多轮指令遵循研究
On the Multi-turn Instruction Following for Conversational Web Agents
AI总结：
本文提出对话式网页导航任务及MT-Mind2Web数据集，并设计自反思记忆增强规划框架Self-MAP，以解决多轮指令遵循中的上下文长度限制和依赖问题。
摘要：
由大型语言模型（LLMs）驱动的网页智能体在复杂的基于网页的环境中规划和执行多步交互方面展现了卓越的能力，能够完成广泛的网页导航任务。尽管取得了这些进展，LLM驱动的智能体在真实世界场景中有效处理连续用户指令的潜力尚未被充分探索。在这项工作中，我们引入了一个新任务——对话式网页导航（Conversational Web Navigation），该任务需要与用户和环境进行跨越多个轮次的复杂交互，并配有一个专门开发的数据集，名为Multi-Turn Mind2Web（MT-Mind2Web）。为了解决LLMs有限的上下文长度以及对话式任务的上下文依赖问题，我们进一步提出了一个新的框架，名为自反思记忆增强规划（Self-MAP），该框架采用了记忆利用和自我反思技术。我们进行了大量实验来对MT-Mind2Web数据集进行基准测试，并验证了所提方法的有效性。
英文摘要：
Web agents powered by Large Language Models (LLMs) have demonstrated remarkable abilities in planning and executing multi-step interactions within complex web-based environments, fulfilling a wide range of web navigation tasks. Despite these advancements, the potential for LLM-powered agents to effectively engage with sequential user instructions in real-world scenarios has not been fully explored. In this work, we introduce a new task of Conversational Web Navigation, which necessitates sophisticated interactions that span multiple turns with both the users and the environment, supported by a specially developed dataset named Multi-Turn Mind2Web (MT-Mind2Web). To tackle the limited context length of LLMs and the context-dependency issue of the conversational tasks, we further propose a novel framework, named self-reflective memory-augmented planning (Self-MAP), which employs memory utilization and self-reflection techniques. Extensive experiments are conducted to benchmark the MT-Mind2Web dataset, and validate the effectiveness of the proposed method.
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。
