论文:Large Language Models as Tool Makers 摘要 最近的研究表明,通过使用外部工具,可以提高大型语言模型(LLM)的问题解决能力。然而,以往的研究依赖于现有工具的可用性。在这项工作中,我们通过提出一个闭环框架,即LLMs作为工具生成器(LATM),迈出了消除这种依赖性的初步步骤,其中LLMs为问题解决创建自己的可重用
创新点：LLM通过LATM框架生成自己的可重用工具，这些工具以Python实用函数的形式实现。关键阶段：工具生成阶段：LLM充当工具生成器，为给定任务设计并生成工具。工具使用阶段：LLM充当工具用户，使用由工具生成器构建的工具来解决问题。这两个角色可以由相同的或不同的LLM担任。成本效益优化：该方法通过将工具生...
近期，Google Deepmind、普林斯顿和斯坦福的研究人员发布了一项研究，名为“Large Language Models as Tool Makers”。该研究展示了一种让大型语言模型（LLM）自动生成工具的创新方法，以解决复杂问题。以下是该研究的概述和关键点：研究的创新点在于，LLM通过闭环框架“LLMs作为工具生成器（LATM）”来生成自己...
In this work, we take an initial step towards removing this dependency by proposing a closed-loop framework, referred to as LLMs As Tool Makers (LATM), where LLMs create their own reusable tools for problem-solving. Our approach consists of two key phases: 1) tool making: an LLM acts ...
几篇论文实现代码:《Large Language Models as Tool Makers》(2023) GitHub: github.com/ctlllll/LLM-ToolMaker [fig1] 《Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manif...
LanguageMPC: Large Language Models as Decision Makers for Autonomous Driving搜索 PreprintL ANGUAGE MPC: L ARGE L ANGUAGE M ODELS AS D E -CISION M AKERS FOR A UTONOMOUS D RIVINGHao Sha 1 , Yao Mu 2 , Yuxuan Jiang 1 , Guojian Zhan 1 , Li Chen 2 , Chenfeng Xu 3 , Ping Luo 2 ...
近期，Google Deepmind、普林斯顿和斯坦福的研究人员共同发布了一项创新成果：将大型语言模型（LLM）应用于工具制作领域。该研究旨在通过LLM生成“工具”来解决复杂问题，以此提高问题解决能力与效率。通过开发一个闭环框架，即LLMs作为工具生成器（LATM），研究团队迈出了解决依赖现有工具问题的初步步骤。在这个...
Large Language Models as Tool Makers; Tianle Cai et al VOYAGER: An Open-Ended Embodied Agent with Large Language Models; Guanzhi Wang et al FACTOOL: Factuality Detection in Generative AI A Tool Augmented Framework for Multi-Task and Multi-Domain Scenarios; I-Chun Chern et al WebArena: A Real...
Strong alignment requires cognitive abilities (either human-like or different from humans) such as understanding and reasoning about agents' intentions and their ability to causally produce desired effects. We argue that this is required for AI systems like large language models (LLMs) to be able ...
Chang S, Wang R, Ren P, Huang H (2024) Enhanced short text modeling: leveraging large language models for topic refinement. arXiv preprint arXiv:2403.17706 Chaudhari A, Parseja A, Patyal A (2020) CNN based hate-o-meter: a hate speech detecting tool. In: 2020 third international conferen...