发表机构
Boston University（波士顿大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对AI辅助写作中修改来源不明的问题，提出Reactant范式，通过内联注释和事务协议记录请求与修改的对应关系，实现词级谱系追踪，并经实际使用验证其支持历史查询和技能复用。
AI 中文摘要
使用AI智能体进行写作时，一段文字变成了许多请求的结果，但完成的文档很少解释哪个请求产生了哪个修改。我们引入了Reactant，一种交互范式，作者在其原始文档中放置类型化的内联注释。一个经过验证的事务协议记录每个请求、技能身份以及标识添加、删除和转换的对应关系。内核根据记录的状态验证见证，以建立词级纵向谱系。我们通过本文的修订历史演示了Reactant，并报告了三位同事四个月的自主使用情况。他们的使用包括对历史的对话式查询以及从重复请求中派生可重用技能，说明了事务记录如何作为智能体创作的可扩展基础。
英文摘要
Writing with AI agents turns a paragraph into the outcome of many requests, yet the finished document rarely explains which request produced which change. We introduce Reactant, an interaction paradigm in which authors place typed inline annotations in their original documents. A verified transaction protocol records each request, skill identity, and the correspondences that identify additions, deletions, and transformations. The kernel validates the witness against the recorded states to establish word-level longitudinal lineage. We demonstrate Reactant through this paper's revision history, and report four months of three colleagues' self-directed use. Their uses include conversational inquiry into history and deriving reusable skills from recurring requests, illustrating how the transaction record serves as an extensible substrate for agentic authoring.
