研究人员推出了一种名为HYSET的新方法，用于大型语言模型（LLM）代理的集级工具检索。与评估单个或顺序工具的现有方法不同，HYSET将整个工具集视为一个单元，在工具共调用超图上进行超边预测。这种方法捕捉了工具集内工具的联合效用和兼容性，甚至考虑了与大小相关的交互。HYSET作为一个预选模块，可以在不改变下游代理的情况下进行集成。在ToolBench基准测试上的实验表明，它在检索准确性和整体任务成功率方面均优于当前最先进的方法，并展现出强大的泛化能力。 AI
影响 通过提高工具选择效率和任务成功率，增强LLM代理的能力。
排序理由 该集群包含一篇详细介绍LLM代理新方法的学术论文。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
arXiv:2607.25718v1 Announce Type: cross Abstract: Large language model (LLM) agents increasingly rely on invoking external tools to complete real-world tasks. Tool retrieval, which selects a small task-relevant subset from a library of thousands of tools before the agent acts, ha…
Large language model (LLM) agents increasingly rely on invoking external tools to complete real-world tasks. Tool retrieval, which selects a small task-relevant subset from a library of thousands of tools before the agent acts, has therefore become a critical component of LLM age…
Large language model (LLM) agents increasingly rely on invoking external tools to complete real-world tasks. Tool retrieval, which selects a small task-relevant subset from a library of thousands of tools before the agent acts, has therefore become a critical component of LLM age…