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 2410.03439cs.CL
收藏

ToolGen:通过生成实现统一的工具检索与调用

ToolGen: Unified Tool Retrieval and Calling via Generation

LibrAI;Mohamed bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学);Microsoft(微软公司);University of California, Los Angeles(加州大学洛杉矶分校);The University of Melbourne(墨尔本大学)

Renxi Wang, Xudong Han, Lei Ji, Shu Wang, Timothy Baldwin, Haonan Li

AI总结:

ToolGen将工具表示为独特令牌并融入LLM参数,通过生成实现统一检索与调用,无需额外检索步骤,在47,000多个工具上验证了优越性能,为自主AI智能体奠定基础。

摘要:

随着大型语言模型(LLM)的进步,它们无法通过直接与外部工具交互来自主执行任务,这仍然是一个关键的局限性。传统方法依赖于将工具描述作为上下文输入,这受到上下文长度的限制,并且需要单独的、往往效率低下的检索机制。我们引入了ToolGen,这是一种范式转变,通过将每个工具表示为独特的令牌,将工具知识直接整合到LLM的参数中。这使得LLM能够将工具调用和参数生成作为其下一个令牌预测能力的一部分,无缝地将工具调用与语言生成融合在一起。我们的框架允许LLM无需额外的检索步骤即可访问和利用大量工具,显著提升了性能和可扩展性。在超过47,000个工具上的实验结果表明,ToolGen不仅在工具检索和自主任务完成方面取得了优异的结果,而且为能够适应不同领域工具的新一代AI智能体奠定了基础。通过将工具检索从根本上转变为生成过程,ToolGen为更通用、高效和自主的AI系统铺平了道路。ToolGen实现了端到端的工具学习,并为与其他先进技术(如思维链和强化学习)的集成提供了机会,从而扩展了LLM的实际能力。

英文摘要:

As large language models (LLMs) advance, their inability to autonomously execute tasks by directly interacting with external tools remains a critical limitation. Traditional methods rely on inputting tool descriptions as context, which is constrained by context length and requires separate, often inefficient, retrieval mechanisms. We introduce ToolGen, a paradigm shift that integrates tool knowledge directly into the LLM's parameters by representing each tool as a unique token. This enables the LLM to generate tool calls and arguments as part of its next token prediction capabilities, seamlessly blending tool invocation with language generation. Our framework allows the LLM to access and utilize a vast amount of tools with no additional retrieval step, significantly enhancing both performance and scalability. Experimental results with over 47,000 tools show that ToolGen not only achieves superior results in both tool retrieval and autonomous task completion but also sets the stage for a new era of AI agents that can adapt to tools across diverse domains. By fundamentally transforming tool retrieval into a generative process, ToolGen paves the way for more versatile, efficient, and autonomous AI systems. ToolGen enables end-to-end tool learning and opens opportunities for integration with other advanced techniques such as chain-of-thought and reinforcement learning, thereby expanding the practical capabilities of 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。

↑