PaperMentor: A Human-Centered Multi-Agent Writing Tutor for AI Research Papers on Overleaf
Abstract
A human-centered writing assistant system called PaperMentor integrates expert research advice with specialized agents to provide actionable feedback during manuscript drafting, outperforming AI baselines in usability and relevance.
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
Community
PaperMentor is a human-centered multi-agent writing tutor that delivers expert-level, actionable feedback as native inline comments on Overleaf, helping early-career researchers improve their AI papers during drafting while leaving all revisions to the authors. It combines a curated library of 40+ expert skill files with 12 specialized agents covering aspects like methods, results, formatting, and terminology, and in a user study (n=14) significantly outperformed a GPT-5.2 baseline without the skill library on validity and actionability.
This paper is accepted to the ACL 2026 Demo track. You can try the live demo at https://overleafmentor.ai.toronto.edu/ and find the code at https://github.com/jiarui-liu/overleaf.
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- ReviewGrounder: Improving Review Substantiveness with Rubric-Guided, Tool-Integrated Agents (2026)
- EGTR-Review: Efficient Evidence-Grounded Scientific Peer Review Generation via Multi-Agent Teacher Distillation (2026)
- Can AI Review Improve Paper Drafting? An Empirical Study on 20 Computer Architecture Submissions (2026)
- Stop Automating Peer Review Without Rigorous Evaluation (2026)
- Can AI Be a Good Peer Reviewer? A Survey of Peer Review Process, Evaluation, and the Future (2026)
- GoodPoint: Learning Constructive Scientific Paper Feedback from Author Responses (2026)
- FOXGLOVE: Understanding Goal-Oriented and Anchored Writing Feedback from Experts and LLMs on Argumentative Essays (2026)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: @librarian-bot recommend
Get this paper in your agent:
hf papers read 2606.08857 Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper
Collections including this paper 0
No Collection including this paper