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

Spanish

Mientras que los LLMs han transformado la generación de texto, las interfaces estándar de chat y canvas a menudo reducen la escritura humana a una supervisión bastante pasiva, causando fatiga de revisión, excesiva dependencia de la IA y el aislamiento del papel humano en la escritura de forma larga, basada en la fuente. Los sistemas previos suelen abordar las fases de escritura aisladas, dejando a los usuarios involucrados activamente. En un estudio de usuario exploratorio, en comparación con una línea de base de LLM estándar, los autores que usan CoWriter expresaron mejor sus perspectivas y un sentido proactivo de la colaboración de documentos propios, respaldados cuantitativamente por los métodos personales de $2.2$ veces más agentes exitosos. Además, las experiencias de los lectores exter

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