PaperMentor：一個以人為中心的多智能體寫作導師，專為在 Overleaf 上撰寫 AI 研究論文而設計

摘要

經驗豐富研究員提供的專家寫作回饋，對早期職業學者改進稿件至關重要，然而高品質回饋往往稀缺，因為審查研究論文需要大量人力。新興的AI驅動寫作助手大多專注於語法修正或模擬同儕審查並給出最終評分，卻無法提供具體可行的建議，幫助學生在撰寫過程中改善論文。我們提出PaperMentor，這是一套以人為本的寫作輔助系統，能將可行建議以Overleaf原生內嵌註解的形式呈現，同時將實際寫作完全交由人類作者處理。PaperMentor整合了一個專家技能庫，該庫從資深研究員的寫作建議中精心挑選，並搭配12個專門代理，涵蓋論文寫作的不同面向，例如格式合規性、措辭準確性及術語一致性。在一項用戶研究（n=14）中，90.6%的生成註解被評為可行，67.5%被評為有效，顯著優於未使用技能庫的GPT-5.2基準。我們以開放原始碼形式釋出PaperMentor供大眾使用。我們的程式碼在AGPL-3.0許可證下公開，網址為https://github.com/jiarui-liu/overleaf。

English

Expert writing feedback from experienced researchers is critical for early-career scholars to improve their manuscripts, yet high-quality feedback often remains scarce because reviewing research papers is labor-intensive. Emerging AI-powered writing assistants largely focus on grammar fixes or simulating peer review with final scores, yet they fall short of providing concrete, actionable suggestions that help students improve their papers during drafting. We present PaperMentor, a human-centered writing assistant system that delivers actionable suggestions as Overleaf-native inline comments while leaving the actual writing entirely to human authors. PaperMentor integrates an expert skill library carefully curated from established researchers' writing advice with 12 specialized agents covering different aspects of paper writing, such as formatting compliance, phrasing accuracy, and terminology consistency. In a user study (n=14), 90.6% of the generated comments were rated actionable and 67.5% were rated valid, significantly outperforming a GPT-5.2 baseline uswithout the skill library. We release PaperMentor as open source for public use. Our code is publicly available under the AGPL-3.0 license at https://github.com/jiarui-liu/overleaf