CoachGPT: A Scaffolding-based Academic Writing Assistant
Open accessAbstract
Academic writing skills are crucial for students' success but can feel overwhelming without proper guidance and practice, particularly when writing in a second language. Traditionally, students ask instructors or search dictionaries, which are not universally accessible. Early writing assistants emerged as rule-based systems that focused on detecting misspellings, subject-verb disagreements, and basic punctuation errors but are inaccurate and lack contextual understanding. Machine learning-based assistants demonstrate a strong ability for language understanding but are expensive to train. Large language models (LLMs) have shown remarkable capabilities in generating responses in natural languages based on given prompts, but they have a fundamental limitation in education: they generate essays without teaching, which can have detrimental effects on learning when misused. To address this limitation, we develop CoachGPT, which leverages LLMs to assist academic writing for those with limited educational resources and those who prefer self-paced learning. CoachGPT is an AI agent-based web application that (1) takes instructions from experienced educators (2) converts instructions into sub-tasks, and (3) provides real-time feedback and suggestions using large language models. This unique scaffolding structure makes CoachGPT unique among existing writing assistants. Compared with existing writing assistants, CoachGPT provides a more immersed writing experience with personalized messages. Our user studies prove the usefulness of CoachGPT and the potential of large language models for academic writing.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
(1978) · Medical Entomology and Zoology · Cited by 53,488 · see citing works
Three Approaches to Qualitative Content Analysis
Hsieh, H.-F., & Shannon, S. E. (2005) · Qualitative Health Research · doi:10.1177/1049732305276687 · Cited by 44,601 · see citing works
Instructional Scaffolding in STEM Education
Belland, B. R. (2017) · doi:10.1007/978-3-319-02565-0 · Cited by 161 · see citing works
A REVIEW OF EMPIRICAL EVIDENCE ON SCAFFOLDING FOR SCIENCE EDUCATION
Lin, T., Hsu, Y., Lin, S., Changlai, M.-L., Yang, K.-Y., & Lai, T.-L. (2011) · International Journal of Science and Mathematics Education · doi:10.1007/s10763-011-9322-z · Cited by 132 · see citing works
The Prompt Report: A Systematic Survey of Prompt Engineering Techniques
Schulhoff, S., Ilie, M., Balepur, N., Kahadze, K., Liu, A., Si, C., Li, Y., Gupta, A., Han, H., Schulhoff, S., et al. (2024) · arXiv · doi:10.48550/arxiv.2406.06608 · Cited by 118 · see citing works
Vygotsky, Scaffolding, and the Role of Theory in Writing Center Work
Nordlof, J. (2014) · The Writing center journal · doi:10.7771/2832-9414.1785 · Cited by 77 · see citing works
Open knowledge interface: a digital assistant to support students in writing academic assignments
Resch, O., & Yankova, A. (2019) · Proceedings of the 1st ACM SIGSOFT International Workshop on Education through Advanced Software Engineering and Artificial Intelligence · doi:10.1145/3340435.3342723 · Cited by 26 · see citing works
Mahmoudi, F., & Buğra, C. (2020) · International online journal of education and teaching · Cited by 22 · see citing works
Proceedings of the 9th international conference on Artificial Intelligence and Soft Computing
Rutkowski, L., Tadeusiewicz, R., Zadeh, L. A., et al. (2006) · Cited by 19 · see citing works
Automated Focused Feedback Generation for Scientific Writing Assistance
Chamoun, E., Schlichktrull, M., & Vlachos, A. (2024) · arXiv · doi:10.48550/arxiv.2405.20477 · Cited by 17 · see citing works
Write-righter: An Academic Writing Assistant System
Liu, Y., Wang, X. E., Liu, M., et al. (2016) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v30i1.9823 · Cited by 9 · see citing works
Towards Explainable AI Writing Assistants for Non-native English SpeakersPreprint
Kim, Y., Lee, M., Kim, D., et al. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2304.02625 · Cited by 5 · see citing works
Flagged first, then by citations
Research works printed but not linked: 5
- [2]2. Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al. 2020. Language models are few-shot learners. Advances in neural information processing systems 33 (2020), 1877-1901.
- [5]5. Tira Nur Fitria. 2021. Grammarly as AI-powered English writing assistant: Students' alternative for writing English. Metathesis: Journal of English Language, Literature, and Teaching 5, 1 (2021), 65-78.
- [12]12. Justin Mücke, Daria Waldow, Luise Metzger, Philipp Schauz, Marcel Hoffman, Nicolas Lell, and Ansgar Scherp. 2023. Fine-Tuning Language Models for Scientific Writing Support. In International Cross-Domain Conference for Machine Learning and Knowledge Extraction. Springer, 301-318.
- [17]17. Tony Silva. 1993. Toward an understanding of the distinct nature of L2 writing: The ESL research and its implications. TESOL quarterly 27, 4 (1993), 657-677.
- [19]19. John Sweller, Paul Ayres, and Slava Kalyuga. 2011. Cognitive load theory. Springer, New York.
Cited by
Sorted by citations
Where Do I 'Add the Egg'?: Exploring Agency and Ownership in AI Creative Co-Writing Systems
Carrera, D., Thomas-Mitchell, J., & Wigdor, D. (2026) · Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3791952 · Cited by 3 · see citing works
“Agent-like interfaces were also common in HCI literature on AI co-writing, in both creative writing [24, 47, 56, 62] and other writing contexts [11, 13, 53, 66, 71, 74], featuring chat interfaces with avatars, personified agents, and streaming text that was similar to the reviewed commercial…”
- Authors
- Chen, F., Veng, S., Wilson, J., Li, X., & Fang, H.
- Affiliations
- University of Delaware (US)
- Venue
- Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval
- Publisher
- ACM
- Published
- 2025-07-13
- Pages
- 4051-4055
- OpenAlex
- W4412377995
- Cited by
- 6
- References
- 12
- Citations by year
- 2026: 5 · 2025: 1
- FWCI
- 6.86
- Type
- conference paper
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- AI Center of Excellence at the University of Delaware
- IFSA at the University of Delaware
- Topics
- Physical Sciences › Computer Science › Information Systems › Artificial Intelligence in Education
- Physical Sciences › Computer Science › Artificial Intelligence › Intelligent Tutoring Systems and Adaptive Learning
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Keywords
- academic writing support, large language models, scaffolding, writing instruction, AI agents, real-time feedback, second language writing, self-paced learning, low-resource education
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
