告诉我更多！迈向语言模型驱动智能体的隐式用户意图理解
Tell Me More! Towards Implicit User Intention Understanding of Language Model Driven Agents
AI总结：
针对语言模型智能体难以理解模糊用户意图的问题，提出IN3基准并训练Mistral-Interact模型作为上游，通过主动询问和细化意图提升XAgent框架的指令理解与执行效率。
摘要：
当前语言模型驱动的智能体通常缺乏有效的用户参与机制，而鉴于用户指令中普遍存在的模糊性，这一点至关重要。尽管这些智能体擅长制定策略和执行任务，但在寻求澄清和把握精确用户意图方面却存在困难。为弥合这一差距，我们引入了Intention-in-Interaction (IN3)，这是一个旨在通过显式查询来检查用户隐式意图的新型基准。接下来，我们提出在智能体设计中将模型专家作为上游，以增强用户与智能体间的交互。利用IN3，我们通过实验训练了Mistral-Interact，这是一个强大的模型，能够在启动下游智能体任务执行前，主动评估任务模糊性，询问用户意图，并将其细化为可执行目标。将其集成到XAgent框架后，我们全面评估了增强后智能体系统在用户指令理解和执行方面的表现，结果表明我们的方法在识别模糊用户任务、恢复并总结关键缺失信息、设定精确且必要的智能体执行目标，以及减少冗余工具使用方面表现显著，从而提升了整体效率。所有数据和代码均已开源。
英文摘要：
Current language model-driven agents often lack mechanisms for effective user participation, which is crucial given the vagueness commonly found in user instructions. Although adept at devising strategies and performing tasks, these agents struggle with seeking clarification and grasping precise user intentions. To bridge this gap, we introduce Intention-in-Interaction (IN3), a novel benchmark designed to inspect users' implicit intentions through explicit queries. Next, we propose the incorporation of model experts as the upstream in agent designs to enhance user-agent interaction. Employing IN3, we empirically train Mistral-Interact, a powerful model that proactively assesses task vagueness, inquires user intentions, and refines them into actionable goals before starting downstream agent task execution. Integrating it into the XAgent framework, we comprehensively evaluate the enhanced agent system regarding user instruction understanding and execution, revealing that our approach notably excels at identifying vague user tasks, recovering and summarizing critical missing information, setting precise and necessary agent execution goals, and minimizing redundant tool usage, thus boosting overall efficiency. All the data and codes are released.
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。
