arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2512.04445cs.SEcs.AI
收藏

通过分步和回滚功能的操作编排自动化复杂文档工作流

Automating Complex Document Workflows via Stepwise and Rollback-Enabled Operation Orchestration

Yanbin Zhang, Hanhui Ye, Yue Bai, Qiming Zhang, Liao Xiang, Wu Mianzhi, Renjun Hu(作者)

Yanbin Zhang, Hanhui Ye, Yue Bai, Qiming Zhang, Liao Xiang, Wu Mianzhi, Renjun Hu

AI总结:

AutoDW通过分步和回滚功能的操作编排,提升复杂文档工作流的自动化效率

摘要:

工作流自动化在日常文档相关任务中能够带来显著的生产率提升。尽管先前的代理系统可以执行孤立的指令,但它们在自动化多步骤、会话级工作流方面遇到困难,因为对操作过程的控制有限。为此,我们引入了AutoDW,一种新的执行框架,能够实现分步和回滚的操作编排。AutoDW会根据用户指令、意图过滤的API候选者以及文档的演变状态逐步规划API操作。它进一步在参数和API层面采用稳健的回滚机制,能够实现动态修正和容错。这些设计共同确保AutoDW的执行轨迹在长周期工作流中始终与用户意图和文档上下文保持一致。为了评估其有效性,我们构建了一个包含250个会话和1708个人工标注指令的综合基准,反映了具有相互依赖指令的真实文档处理场景。AutoDW在指令级和会话级任务上分别实现了90%和62%的完成率,分别优于强基线模型40%和76%。此外,AutoDW在选择基础LLM时也保持稳健,并在难度不同的任务中表现良好。代码和数据将被开源。代码:https://github.com/YJett/AutoDW

英文摘要:

Workflow automation promises substantial productivity gains in everyday document-related tasks. While prior agentic systems can execute isolated instructions, they struggle with automating multi-step, session-level workflows due to limited control over the operational process. To this end, we introduce AutoDW, a novel execution framework that enables stepwise, rollback-enabled operation orchestration. AutoDW incrementally plans API actions conditioned on user instructions, intent-filtered API candidates, and the evolving states of the document. It further employs robust rollback mechanisms at both the argument and API levels, enabling dynamic correction and fault tolerance. These designs together ensure that the execution trajectory of AutoDW remains aligned with user intent and document context across long-horizon workflows. To assess its effectiveness, we construct a comprehensive benchmark of 250 sessions and 1,708 human-annotated instructions, reflecting realistic document processing scenarios with interdependent instructions. AutoDW achieves 90% and 62% completion rates on instruction- and session-level tasks, respectively, outperforming strong baselines by 40% and 76%. Moreover, AutoDW also remains robust for the decision of backbone LLMs and on tasks with varying difficulty. Code and data will be open-sourced. Code: https://github.com/YJett/AutoDW

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。

↑