发表机构
Johns Hopkins University; Microsoft（约翰斯·霍普金斯大学; 微软）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
FrankenReport通过按章节预测计算价值实现早期退出，在低预算下性能提升达4倍，并能高效适应简单用户反馈。
AI 中文摘要
尽管深度研究系统在满足交互式信息检索需求方面表现出色，但其实际部署面临延迟和资源消耗的挑战。我们提出FrankenReport，一种用于长文本知识型报告生成的界面，支持按章节进行自适应早期退出：它在生成过程中评估中间输出，并预测进一步的目标计算是否会产生显著的质量提升。在模拟研究中，FrankenReport在低预算下大幅优于随机分配基线（最高达4倍），并随着预算增加平滑恢复全流水线质量，表明未来质量提升可从中间草稿中预测。通过实验和用户研究，我们进一步表明，尽管用户和主题的偏好各异，FrankenReport适应简单、自然的用户反馈的效率与需要更昂贵监督（如生成草稿和明确理由）的方法相当。
英文摘要
While deep research systems address interactive information-seeking needs impressively, their real-world deployments face latency and resource-consumption challenges. We present FrankenReport, an interface for long-form knowledge-seeking report generation that supports adaptive early exiting per section: it evaluates intermediate outputs during generation and predicts whether further targeted computation will yield significant quality gains. In a simulation study, FrankenReport outperforms random allocation baselines by a large margin (up to 4x) under low budgets and smoothly recovers full-pipeline quality as the budget grows, showing that future quality gains are predictable from intermediate drafts. Through experiments and user studies, we further show that despite varying preferences across users and topics, FrankenReport adapts to simple, natural user feedback as efficiently as methods requiring much costlier supervision such as generated drafts and explicit rationales.
Comments23 pages, 16 figures
