arXiv cs.CL· Shmuel Amar, Benjamin Lieber, Ori Shapira, Debanjana Kar, Sebastian Maximilian Dennerlein, Yufang Hou, Ido Dagan·· 13 小时前AI 评分31
CoWriter：引导方法论与协同式人机共同写作
CoWriter: Guiding Methodological and Synergetic Human-LLM Co-Authoring
AI 导读
CoWriter 是一个主动式智能体方案，将认知科学中的人类专家（合）写作方法论引入整个写作流程，主动引导用户参与而非被动监督。在探索性用户研究中，使用 CoWriter 的作者成功触发智能体交互的次数是标准 LLM 基线的 2.2 倍，更好地表达了自身观点并保持更高的文档主人翁感。外部读者评审还认为其文本在故事性和融入个人独特经历等"人味"维度上得分更高。
正文 · 原文
Abstract:While LLMs have transformed text generation, standard chat-and-canvas interfaces often reduce human authoring to quite passive supervision, causing review fatigue, over-reliance on AI, and the sidelining of the human role in long-form, source-grounded writing. Prior systems typically address isolated writing phases, leaving comprehensive end-to-end human-LLM collaboration largely unexplored. In this paper, we introduce CoWriter, a proactive agentic scheme that adapts expert human (co-)authoring methodologies from cognitive science to flexibly steer the entire writing workflow while actively encouraging the user to engage. In an exploratory user study, compared to a standard LLM baseline, authors using CoWriter better expressed their perspectives and maintained a higher sense of document ownership, supported quantitatively by $2.2\times$ more successful agent engagements. Furthermore, external reader judges rated the resulting texts higher in "human touch" qualities like storytelling and integrating unique personal experiences. Overall, our results demonstrate that proactively engaging users through established human practices is beneficial for effective LLM-supported co-authoring, providing useful methodologies, techniques and insights for future research on collaborative agents.
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC) |
| Cite as: | arXiv:2610.31277 [cs.CL] |
| (or arXiv:2610.31277v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.31277 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Shmuel Amar [view email]
[v1]
Thu, 22 Oct 2026 13:45:47 UTC (2,808 KB)
来源：arXiv cs.CL · arxiv.org