KwaiAgents：基于大型语言模型的通用信息搜寻智能体系统
KwaiAgents: Generalized Information-seeking Agent System with Large Language Models
AI总结：
本文提出基于LLMs的通用信息搜寻智能体系统KwaiAgents，以LLMs为认知核心实现查询理解、记忆检索与工具调用，并引入MAT框架使开源7B/13B模型具备卓越智能体能力。
摘要：
受好奇心驱使，人类不断寻求探索和理解周围世界，从而发明了各种工具来满足这种求知欲。尽管人类大脑不具备处理和记忆海量信息的能力，但人类擅长批判性思维、规划、反思以及利用可用工具与世界互动并进行解释，从而能够高效地找到答案。大型语言模型（LLMs）的最新进展表明，机器也可能具备上述类人能力，使其即使在参数数量受限的情况下也能展现出强大的能力。在本文中，我们介绍了KwaiAgents，一个基于LLMs的通用信息搜寻智能体系统。在KwaiAgents中，我们提出了一个以LLMs为认知核心的智能体系统，该系统能够理解用户的查询、行为准则，并参考外部文档。该智能体还能更新和检索其内部记忆中的信息，使用时间感知的搜索浏览工具包规划和执行操作，最终提供全面的回答。我们进一步研究了由不如GPT-4先进的LLMs驱动时系统的性能，并引入了Meta-Agent Tuning（MAT，元智能体微调）框架，旨在确保即使是开源的7B或13B模型也能在众多智能体系统中表现良好。我们利用基准测试和人工评估来系统地验证这些能力。大量实验表明，与其他自主智能体相比，我们的智能体系统具有优越性，并突显了我们微调后的LLMs增强的通用智能体能力。
英文摘要：
Driven by curiosity, humans have continually sought to explore and understand the world around them, leading to the invention of various tools to satiate this inquisitiveness. Despite not having the capacity to process and memorize vast amounts of information in their brains, humans excel in critical thinking, planning, reflection, and harnessing available tools to interact with and interpret the world, enabling them to find answers efficiently. The recent advancements in large language models (LLMs) suggest that machines might also possess the aforementioned human-like capabilities, allowing them to exhibit powerful abilities even with a constrained parameter count. In this paper, we introduce KwaiAgents, a generalized information-seeking agent system based on LLMs. Within KwaiAgents, we propose an agent system that employs LLMs as its cognitive core, which is capable of understanding a user's query, behavior guidelines, and referencing external documents. The agent can also update and retrieve information from its internal memory, plan and execute actions using a time-aware search-browse toolkit, and ultimately provide a comprehensive response. We further investigate the system's performance when powered by LLMs less advanced than GPT-4, and introduce the Meta-Agent Tuning (MAT) framework, designed to ensure even an open-sourced 7B or 13B model performs well among many agent systems. We exploit both benchmark and human evaluations to systematically validate these capabilities. Extensive experiments show the superiority of our agent system compared to other autonomous agents and highlight the enhanced generalized agent-abilities of our fine-tuned LLMs.
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。
