通过树状结构控制研究深度与广度，让大模型科研助手更省资源、可调可控。
A Hierarchical Tree-based approach for creating Configurable and Static Deep Research Agent (Static-DRA)
- 用可配置的树形结构分层管理研究任务，支持深度和广度自由调节。
- 在RACE评测中达34.72分，提升深度与广度可显著提高研究质量。
- 适合需要高效、透明、可控科研自动化的人群，如研究人员和工程师。
大型语言模型的发展推动了复杂智能体系统（如深度研究代理）的出现，以克服静态检索增强生成（RAG）在处理多轮复杂研究任务时的局限性。本文提出静态深度研究代理（Static-DRA），基于可配置的分层树状静态工作流构建。核心贡献在于引入两个用户可调参数——深度（Depth）与广度（Breadth），实现对研究强度的精细控制，使用户能在报告质量与计算成本之间做出权衡。该代理架构包含监督者、独立者与工作者三类智能体，支持高效的多跳信息检索与并行子主题探究。我们在DeepResearch Bench基准上，采用基于参考的自适应准则评估框架（RACE）进行评估。配置深度为2、广度为5，并使用gemini-2.5-pro模型，获得总分为34.72。实验表明，提升深度与广度配置能带来更深入的研究过程和更高的评分。Static-DRA提供了一种务实且资源感知的解决方案，赋予用户对深度研究过程的透明控制。全部源代码、输出结果及评测数据已开源至https://github.com/SauravP97/Static-Deep-Research/
原文摘要 · Abstract (English)
The advancement in Large Language Models has driven the creation of complex agentic systems, such as Deep Research Agents (DRAs), to overcome the limitations of static Retrieval Augmented Generation (RAG) pipelines in handling complex, multi-turn research tasks. This paper introduces the Static Deep Research Agent (Static-DRA), a novel solution built upon a configurable and hierarchical Tree-based static workflow. The core contribution is the integration of two user-tunable parameters, Depth and Breadth, which provide granular control over the research intensity. This design allows end-users to consciously balance the desired quality and comprehensiveness of the research report against the associated computational cost of Large Language Model (LLM) interactions. The agent's architecture, comprising Supervisor, Independent, and Worker agents, facilitates effective multi-hop information retrieval and parallel sub-topic investigation. We evaluate the Static-DRA against the established DeepResearch Bench using the RACE (Reference-based Adaptive Criteria-driven Evaluation) framework. Configured with a depth of 2 and a breadth of 5, and powered by the gemini-2.5-pro model, the agent achieved an overall score of 34.72. Our experiments validate that increasing the configured Depth and Breadth parameters results in a more in-depth research process and a correspondingly higher evaluation score. The Static-DRA offers a pragmatic and resource-aware solution, empowering users with transparent control over the deep research process. The entire source code, outputs and benchmark results are open-sourced at https://github.com/SauravP97/Static-Deep-Research/
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。