arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2403.00839cs.AIcs.CL
收藏

ToolNet:通过工具图谱连接大语言模型与海量工具

ToolNet: Connecting Large Language Models with Massive Tools via Tool Graph

Northwestern University(西北大学);North Carolina State University(北卡罗来纳州立大学);Microsoft Research Asia(微软亚洲研究院)

Xukun Liu, Zhiyuan Peng, Xiaoyuan Yi, Xing Xie, Lirong Xiang, Yuchen Liu, Dongkuan Xu

AI总结:

本文提出即插即用框架 ToolNet,用有向加权工具图谱组织数千个工具,让 LLM 通过图导航选择工具,从而以较低 token 增量提升多跳工具学习能力与故障韧性。

摘要:

尽管大语言模型(LLM)已在广泛任务中取得显著进展,但它们在正确使用海量外部工具方面仍存在明显局限。现有的上下文学习方法只是将工具格式化为纯文本描述列表并输入给 LLM,LLM 据此生成一系列工具调用以逐步解决问题。这种范式忽视了工具之间的内在依赖关系,并将全部推理负担都转嫁给 LLM,使其受限于数量有限、专门设计的工具。因此,LLM 要在包含海量工具的工具库上运行仍然颇具挑战,在面对真实世界场景时形成很大限制。本文提出 ToolNet,这是一个即插即用框架,能够将工具数量扩展至数千个,同时仅适度增加 token 消耗。ToolNet 将工具组织成有向图:每个节点表示一个工具,加权边表示工具之间的转移。LLM 从初始工具节点出发,在图中进行导航,通过迭代地从后继节点中选择下一个工具,直到任务被解决。大量实验表明,ToolNet 在具有挑战性的多跳工具学习数据集上取得了令人瞩目的结果,并且对工具故障具有韧性。

英文摘要:

While achieving remarkable progress in a broad range of tasks, large language models (LLMs) remain significantly limited in properly using massive external tools. Existing in-context learning approaches simply format tools into a list of plain text descriptions and input them to LLMs, from which, LLMs generate a sequence of tool calls to solve problems step by step. Such a paradigm ignores the intrinsic dependency between tools and offloads all reasoning loads to LLMs, making them restricted to a limited number of specifically designed tools. It thus remains challenging for LLMs to operate on a library of massive tools, casting a great limitation when confronted with real-world scenarios. This paper proposes ToolNet, a plug-and-play framework that scales up the number of tools to thousands with a moderate increase in token consumption. ToolNet organizes tools into a directed graph. Each node represents a tool, and weighted edges denote tool transition. Starting from an initial tool node, an LLM navigates in the graph by iteratively choosing the next one from its successors until the task is resolved. Extensive experiments show that ToolNet can achieve impressive results in challenging multi-hop tool learning datasets and is resilient to tool failures.

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。

↑