发表机构
Xiaohongshu Inc.; Zhejiang University（小红书科技有限公司; 浙江大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对现有OEDR系统无法高效维护更新报告的问题，提出Incremental-OEDR设定与Structured Harness工具，经实验验证其可在保持报告质量的同时提升连续性、降低研究成本。
AI 中文摘要
现有的开放式深度研究（Open-Ended Deep Research, OEDR）系统主要从零生成报告，在新信息出现时需持续维护报告的场景下效率低下。我们提出增量开放式深度研究（Incremental Open-Ended Deep Research, Incremental-OEDR），该研究设定将报告视为不断演化的研究状态，通过保留有效知识、修订过时或不完整内容、整合新获取信息实现增量更新。为支持该设定，我们提出结构化工具（Structured Harness），将报告表示为大纲、章节和支撑证据的结构化集合，提供结构化检索、持久结构化证据池及结构化生成功能，用于选择性更新报告和复用证据。我们进一步建立了覆盖十年的时间评估框架，包含单步任务（Single-Step Task）和长链任务（Long-Chain Task），以评估从单个过渡到长期更新链的增量更新效果。在DeepResearch Bench和DeepConsult数据集上，分别采用开源配置（Open-source Configuration, OC）和专有配置（Proprietary Configuration, PC）开展的大量实验表明，Incremental-OEDR在保持报告质量竞争力的同时，大幅提升了报告连续性并降低了研究成本。如图1所示，在DeepResearch Bench上，其内容级ROUGE-L F1值最高提升0.51，大纲级EM F1值最高提升0.63，token消耗降低33%，搜索调用次数减少61%，优于OEDR。更多详情可访问我们的项目页面：this https URL。
英文摘要
Existing Open-Ended Deep Research (OEDR) systems primarily generate reports from scratch, making them inefficient for scenarios where research reports need to be continuously maintained as new information emerges. We introduce \textbf{Incremental Open-Ended Deep Research (Incremental-OEDR)}, a research setting that treats a report as an evolving research state and incrementally updates it by preserving valid knowledge, revising outdated or incomplete content, and incorporating newly available information. To support this setting, we propose \textbf{Structured Harness}, which represents reports as structured collections of outlines, sections, and supporting evidence, and provides structured retrieval, a persistent structured evidence pool, and structured generation for selective report updating and evidence reuse. We further establish a temporal evaluation framework spanning ten years, with \emph{Single-Step Task} and \emph{Long-Chain Task} to evaluate incremental updates over both individual transitions and long-term update chains. Extensive Experiments on DeepResearch Bench and DeepConsult under both the Open-source Configuration (OC) and Proprietary Configuration (PC) show that Incremental-OEDR maintains competitive report quality while substantially improving report continuity and reducing research costs. As shown in Figure~\ref{fig:profile}, it achieves up to 0.51 higher content-level ROUGE-L F1, 0.63 higher outline-level EM F1, 33\% lower token consumption, and 61\% fewer search calls than OEDR on DeepResearch Bench. For more details, please refer to our project page: https://ioedr-project.github.io/.
