用户离开后自主深度研究期间会发生什么？
What Happens During Autonomous Deep Research After the User Steps Away?
浏览论文内容
中文总结 AI 辅助
本研究通过DRaligned反事实框架分析自主深度研究，发现初始用户信息主要影响请求分配而非研究问题，最终建议比显式请求更清晰地区分用户条件，且该方向性差异跨模型和框架稳定存在。
中文摘要 AI 辅助
在自主深度研究中，用户提供任务和相关背景信息，然后离开，让智能体在无需进一步人工干预的情况下进行扩展调查。我们研究了这一初始用户信息如何在中间动作中得到体现，以及这些动作与最终建议之间的关系。我们引入了DRaligned，这是一个基于PDR-Bench构建的反事实行为评估框架。通过改变一个与任务相关的用户因素，同时保持其余上下文固定，我们比较了获取请求、工作草稿和最终报告。基于来源的提取、盲法本地判断和确定性聚合产生了粗略的方向性测量，同时将模糊案例留待解决。我们的实验表明，强大的用户特定交付可以从一个大体共享的研究过程中产生：智能体调查相似的广泛问题，但分配请求的方式不同，最终建议比显式请求更清晰地区分用户条件。报告还可以整合在获取过程中未同时可见的用户因素。在可读的草稿到报告比较中，建议通常保留其粗略的用户特定方向，尽管进行了大量重写。最终的方向性差异在测试的智能体模型、执行框架和评估模型中反复出现，即使执行路径各不相同。这些发现描述了初始用户信息如何塑造自主研究，并阐明了智能体所遵循的过程与其提供的建议之间的关系。
英文摘要
In autonomous deep research, a user provides a task and relevant background, then leaves the agent to conduct an extended investigation without further human intervention. We study how this initial user information is reflected in intermediate actions and how these actions relate to final recommendations. We introduce DRaligned, a counterfactual behavioral evaluation framework built on PDR-Bench. By varying one task-relevant user factor while keeping the remaining context fixed, we compare acquisition requests, working drafts, and final reports. Source-grounded extraction, blinded local judgments, and deterministic aggregation yield coarse directional measurements while leaving ambiguous cases unresolved. Our experiments show that strong user-specific delivery can emerge from a largely shared research process: agents investigate similar broad questions but allocate requests differently, and final recommendations distinguish user conditions more clearly than explicit requests do. Reports can also integrate user factors that were not jointly visible during acquisition. In readable draft-to-report comparisons, recommendations often retain their coarse user-specific direction despite substantial rewriting. Final directional differences recur across tested agent models, execution harnesses, and evaluator models, even as execution paths vary. These findings describe how initial user information shapes autonomous research and clarify the relationship between the process an agent follows and the recommendations it delivers.
发表机构
- University of Southern California（南加利福尼亚大学）
- University of Michigan, Ann Arbor（密歇根大学安娜堡分校）
- Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）
- Zhejiang University（浙江大学）
- Beijing University of Posts and Telecommunications（北京邮电大学）
- Shanghai University of Finance and Economics（上海财经大学）
机构由 AI 辅助整理，请以论文原文为准。
