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

Hindi

जबकि एलएलएम ने पाठ उत्पादन को बदल दिया है, मानक चैट-और-कैनव इंटरफ़ेस अक्सर मानवीय लेखन को काफी निष्क्रिय पर्यवेक्षण में कम करते हैं, जो समीक्षा थकान, एआई पर अत्यधिक निर्भरता और लंबे समय तक, स्रोत आधारित लेखन में मानव भूमिका को समायोजित करते हैं। पूर्व सिस्टम आमतौर पर अलग-अलग लेखन कार्यप्रणाली को संबोधित करते हैं, जबकि सक्रिय रूप से उपयोगकर्ता को संलग्न करने के लिए प्रोत्साहित करते हैं। एक व्यापक अंत-उत्तर मानव-एलएलएम सहयोग में, एक मानक एलएलएम मूल लाइन की तुलना में, हम CoWriter को पेश करते हैं, एक सक्रिय एजेंट योजना जो संज्ञानात्मक विज्ञान से विशेषज्ञ मानव (co-)संपादक पद्धति

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