arXivDaily arXiv每日学术速递 周一至周五更新
​通知:联邦节假日调休:哥伦布日 / 原住民日(Columbus Day / Indigenous Peoples' Day),今日(13日)无更新。
arXiv 2509.00244cs.AI

通用深度研究:自带模型与策略

Universal Deep Research: Bring Your Own Model and Strategy

NVIDIA Research(NVIDIA研究)

Peter Belcak, Pavlo Molchanov

AI总结:

针对现有深度研究智能体策略硬编码、灵活性不足的问题,提出可适配任意大模型、支持用户自定义研究策略且无需额外训练的通用深度研究系统UDR,并提供多类示例策略与交互界面。

摘要:

深度研究工具是当前最具影响力、最常见的智能体系统之一。但我们发现,目前已推出的每款深度研究智能体均为硬编码模式,仅能使用固定的工具集执行特定研究策略。我们提出通用深度研究(Universal Deep Research,UDR),这是一套通用型智能体系统,可适配任意语言模型,支持用户创建、编辑并优化完全自定义的深度研究策略,无需额外训练或微调。为验证系统的通用性,我们为UDR配备了极简型、扩展型、密集型三类示例研究策略,并提供用户界面以方便开展系统实验。

英文摘要:

Deep research tools are among the most impactful and most commonly encountered agentic systems today. We observe, however, that each deep research agent introduced so far is hard-coded to carry out a particular research strategy using a fixed choice of tools. We introduce Universal Deep Research (UDR), a generalist agentic system that wraps around any language model and enables the user to create, edit, and refine their own entirely custom deep research strategies without any need for additional training or finetuning. To showcase the generality of our system, we equip UDR with example minimal, expansive, and intensive research strategies, and provide a user interface to facilitate experimentation with the system.

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。

↑