解决企业深度研究中信息不全和过早停止的问题
Dont Stop Early: Scalable Enterprise Deep Research with Controlled Information Flow and Evidence-Aware Termination
- 通过反思式提纲分解任务，确保覆盖全面
- 依赖控制上下文，显式共享信息，避免混乱
- 基于证据充分性判断终止，提升报告深度与一致
企业深度研究常因信息覆盖不均、上下文爆炸和过早终止而无法产出决策可用报告。本文提出可扩展的企业深度研究（EDR）架构：(i) 通过反思式提纲生成，将请求分解为覆盖驱动的目标；(ii) 借助依赖关系引导执行与显式信息共享，实现上下文定位；(iii) 强制基于证据的完成标准，使代理迭代收集信息直至满足充分性条件。在内部销售赋能任务和公开的DeepResearch Bench基准上评估，所提系统相比现有深度研究基线表现最优。结果表明，依赖控制的上下文管理与显式证据充分性标准能有效减少过早终止，提升研究输出的一致性与深度。
原文摘要 · Abstract (English)
Enterprise deep research often fails to produce decision-ready reports due to uneven information coverage, context explosion, and premature stopping. We propose a scalable Enterprise Deep Research (EDR) architecture to address these failures. Our system (i) decomposes requests into coverage-driven objectives via outline generation with reflection, (ii) localizes context with dependency-guided execution and explicit information sharing, and (iii) enforces evidence-based completion criteria so agents iteratively collect information until sufficiency conditions are met. We evaluate on an internal sales enablement task and the public DeepResearch Bench benchmark, where our proposed system design achieves the strongest overall performance compared with competitive deep-research baselines. The results show that dependency-controlled context and explicit evidence sufficiency criteria reduce premature stopping and improve the consistency and depth of enterprise research outputs.
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。