Evidence-Decision-Feedback: Theory-Driven Adaptive Scaffolding for LLM Agents
Open accessThe 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.
The citation lists haven’t been fetched yet
References 23
- Authors
- Cohn, C., Guo, S., Rayala, S., Wang, H. D., Mohammed, N., Timalsina, U., Jain, S., Eeds, A., Deweese, M., Osborn Popp, P. J., Stanton, R., Walker, S. L., Ma, M., & Biswas, G.
- Affiliations
- Vanderbilt University (US)
- Corresponding author
- Cohn, Clayton
- ORCID
- Venue
- Lecture Notes in Computer Science
- Publisher
- Springer Nature Switzerland
- Published
- 2026-06-27
- Pages
- 1-16
- ISSN
- 0302-9743 (ISSN-L)
- 1611-3349
- OpenAlex
- W7166071742
- Cited by
- 0
- References
- 23
- FWCI
- 0.00
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- Lecture notes in computer science (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Science Foundation (2112635, 2327708)
- U.S. Department of Education
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Intelligent Tutoring Systems and Adaptive Learning
- Social Sciences › Psychology › Developmental and Educational Psychology › Innovative Teaching and Learning Methods
- Physical Sciences › Computer Science › Information Systems › Artificial Intelligence in Education
- Keywords
- LLM agents, educational agents, adaptive scaffolding, intelligent tutoring systems, agentic behavior, pedagogical decision-making, adaptive feedback, overreliance on AI, interpretable explanations, high school students
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
