洛梅奎：大语言模型智能体中资源受限的工具发现
Lomekwi: Resource-Bounded Tool Discovery in LLM Agents
浏览论文内容
中文总结 AI 辅助
研究受认知科学启发区分工具使用与发现，将工具发现分解为好奇心、识别和效率，表明该框架可用于现有任务，证明识别与模型大小成反比，还通过组合博弈及模拟环境观察到反比缩放。
中文摘要 AI 辅助
现有工具使用基准报告复杂多步骤任务的单一成功率。受认知科学启发，我们区分工具使用与工具发现，并将后者分解为好奇心（模型发现构建工具所需部分的能力）、识别（模型发现创建工具过程的能力）和效率（创建后模型对工具的使用）。我们表明该框架可应用于现有发现任务，如旅行者号。此外，我们证明识别与模型大小成反比，并引入分析一类组合博弈来证明。在模拟现实世界任务的单独环境中也观察到反比缩放。
英文摘要
Existing tool-use benchmarks report a single success rate for complex, multistep tasks. Inspired by ideas from cognitive science, we distinguish tool use from tool discovery and decompose the latter into curiosity (the model's ability to discover the parts needed to build the tool), recognition (the model's ability to discover the process of creating the tool), and efficiency (the model's use of the tool after creation). We show that this framework can be applied to existing discovery tasks, such as Voyager. In addition, we provide evidence that recognition inversely scales with model size, and we introduce and analyze a class of combinatorial games that demonstrates this. We further observe inverse scaling in a separate environment designed to emulate real-world tasks.
发表机构
- Sea12 Technologies（Sea12科技公司）
- Yale University（耶鲁大学）
机构由 AI 辅助整理，请以论文原文为准。
