Newest papers

CoWriter: Guiding Methodological and Synergetic Human-LLM Co-Authoring

Shmuel Amar, Benjamin Lieber, Ori Shapira, Debanjana Kar, Sebastian Dennerlein, Yufang Hou, Ido Dagan · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.31277 · cited by 0 works (OpenAlex) · open-access PDF

Indonesian

Sementara LLM telah mengubah generasi teks, antarmuka chat-and-canvas standar sering mengurangi penulisan manusia ke pengawasan yang cukup pasif, menyebabkan kelelahan ulasan, ketergantungan yang berlebihan pada AI, dan pengalihan peran manusia dalam bentuk panjang, penulisan berbasis sumber. Sistem prajurit biasanya menangani fase penulisan terisolasi, meninggalkan kolaborasi manusia-LLM yang komprehensif end-to-end sebagian besar tidak dijelajahi. Dalam makalah ini, kami memperkenalkan CoWriter, skema agen proaktif yang menyesuaikan metodologi penulisan manusia ahli (co-) dari ilmu kognitif untuk secara fleksibel mengarahkan seluruh alur kerja penulisan sambil secara aktif mendorong pengguna untuk terlibat. Dalam studi pengguna eksploratif, dibandingkan dengan garis awal LLM standar, penulis menggunakan CoWriter mengekspresikan perspektif mereka lebih baik

Machine translation (Meta M2M100); the English original follows.

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.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Workflow, Computer science, Storytelling, Human–computer interaction, Knowledge management, Scheme (mathematics)

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange