ScaffoldAgent: 面向开放式深度研究的效用引导动态大纲优化
ScaffoldAgent: Utility-Guided Dynamic Outline Optimization for Open-Ended Deep Research
AI总结:
提出ScaffoldAgent框架,通过效用引导的动态大纲优化(扩展、收缩、修订操作)解决开放式深度研究中大纲漂移问题,在DeepResearch Bench和Gym上提升长报告生成与事实准确性。
摘要:
开放式深度研究(OEDR)要求系统通过多轮检索获取知识并生成连贯的长篇报告。大纲作为协调检索、证据组织和生成的结构性支架起着核心作用。然而,现有方法要么在写作前固定大纲,要么使用局部启发式方法进行优化,导致在持续信息积累下出现大纲漂移,且评估大纲修改的反馈延迟。我们提出ScaffoldAgent,一种面向OEDR的效用引导动态大纲优化框架。ScaffoldAgent将大纲演化建模为结构化决策过程,包含三种操作:扩展、收缩和修订,从而实现对报告支架的受控更新。它进一步引入效用引导的反馈机制,通过检索增益、结构连贯性和试生成质量来估计每个大纲操作的下游价值。得到的效用信号指导推理过程中的节点选择、操作调度和终止。在DeepResearch Bench和DeepResearch Gym上的实验表明,ScaffoldAgent在长报告生成和事实基础上持续优于现有的深度研究智能体。
英文摘要:
Open-ended deep research (OEDR) requires systems to acquire knowledge through multi-round retrieval and generate coherent long-form reports. The outline plays a central role as a structural scaffold that coordinates retrieval, evidence organization, and generation. However, existing methods either fix the outline before writing or refine it with local heuristics, leading to scaffold drift under continuous information accumulation and delayed feedback for evaluating outline modifications. We propose ScaffoldAgent, a utility-guided dynamic outline optimization framework for OEDR. ScaffoldAgent models outline evolution as a structured decision process with three operations: Expansion, Contraction, and Revision, enabling controlled updates to the report scaffold. It further introduces a utility-guided feedback mechanism that estimates the downstream value of each outline operation from retrieval gain, structural coherence, and trial-generation quality. The resulting utility signal guides node selection, operation scheduling, and termination during inference. Experiments on DeepResearch Bench and DeepResearch Gym show that ScaffoldAgent consistently improves long-form report generation and factual grounding over existing deep research agents.
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。