Learning in Blocks: A Skill-Driven Framework for Assessment-Centered Agentic AI in Education

Nicy Scaria, Silvester John Joseph Kennedy, Deepak Subramani
Proceedings of the Impactful and Responsible AI Systems for Education Workshop, PMLR 339:101-106, 2026.

Abstract

Generative AI is increasingly being positioned as a tutoring and learning-support technology, often through chatbot-based interfaces. While flexible, this design can make it difficult to constrain system behavior, align interactions with curriculum goals, and connect learner activity to demonstrated skill performance. This position paper proposes \textit{Learning in Blocks}, a skill-driven framework for AI-supported learning in which learners engage with structured assessments and practice tasks rather than open-ended conversation as the primary interface. The framework organizes learning into blocks of target and prerequisite skills. Bounded pedagogical agents support assessment generation, assessment evaluation, diagnostic recommendation, spaced review, and mastery-based progression. We argue that responsible AI in education should center structured evidence of learner skill. By integrating adaptive learning, formative assessment, multifaceted evaluation, spaced repetition, and mastery learning into a single loop, Learning in Blocks offers a design pattern for more transparent, auditable, and pedagogically aligned AI-supported learning.

Cite this Paper

BibTeX
@InProceedings{pmlr-v339-scaria26a, title = {Learning in Blocks: A Skill-Driven Framework for Assessment-Centered Agentic AI in Education}, author = {Scaria, Nicy and Kennedy, Silvester John Joseph and Subramani, Deepak}, booktitle = {Proceedings of the Impactful and Responsible AI Systems for Education Workshop}, pages = {101--106}, year = {2026}, editor = {Basu Mallick, Debshila and Woodhead, Simon and Wang, Zichao and Ananda, Muktha and Burstein, Jill and Murphy, April}, volume = {339}, series = {Proceedings of Machine Learning Research}, month = {28 Jun}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v339/main/assets/scaria26a/scaria26a.pdf}, url = {https://proceedings.mlr.press/v339/scaria26a.html}, abstract = {Generative AI is increasingly being positioned as a tutoring and learning-support technology, often through chatbot-based interfaces. While flexible, this design can make it difficult to constrain system behavior, align interactions with curriculum goals, and connect learner activity to demonstrated skill performance. This position paper proposes \textit{Learning in Blocks}, a skill-driven framework for AI-supported learning in which learners engage with structured assessments and practice tasks rather than open-ended conversation as the primary interface. The framework organizes learning into blocks of target and prerequisite skills. Bounded pedagogical agents support assessment generation, assessment evaluation, diagnostic recommendation, spaced review, and mastery-based progression. We argue that responsible AI in education should center structured evidence of learner skill. By integrating adaptive learning, formative assessment, multifaceted evaluation, spaced repetition, and mastery learning into a single loop, Learning in Blocks offers a design pattern for more transparent, auditable, and pedagogically aligned AI-supported learning.} }
Endnote
%0 Conference Paper %T Learning in Blocks: A Skill-Driven Framework for Assessment-Centered Agentic AI in Education %A Nicy Scaria %A Silvester John Joseph Kennedy %A Deepak Subramani %B Proceedings of the Impactful and Responsible AI Systems for Education Workshop %C Proceedings of Machine Learning Research %D 2026 %E Debshila Basu Mallick %E Simon Woodhead %E Zichao Wang %E Muktha Ananda %E Jill Burstein %E April Murphy %F pmlr-v339-scaria26a %I PMLR %P 101--106 %U https://proceedings.mlr.press/v339/scaria26a.html %V 339 %X Generative AI is increasingly being positioned as a tutoring and learning-support technology, often through chatbot-based interfaces. While flexible, this design can make it difficult to constrain system behavior, align interactions with curriculum goals, and connect learner activity to demonstrated skill performance. This position paper proposes \textit{Learning in Blocks}, a skill-driven framework for AI-supported learning in which learners engage with structured assessments and practice tasks rather than open-ended conversation as the primary interface. The framework organizes learning into blocks of target and prerequisite skills. Bounded pedagogical agents support assessment generation, assessment evaluation, diagnostic recommendation, spaced review, and mastery-based progression. We argue that responsible AI in education should center structured evidence of learner skill. By integrating adaptive learning, formative assessment, multifaceted evaluation, spaced repetition, and mastery learning into a single loop, Learning in Blocks offers a design pattern for more transparent, auditable, and pedagogically aligned AI-supported learning.
APA
Scaria, N., Kennedy, S.J.J. & Subramani, D.. (2026). Learning in Blocks: A Skill-Driven Framework for Assessment-Centered Agentic AI in Education. Proceedings of the Impactful and Responsible AI Systems for Education Workshop, in Proceedings of Machine Learning Research 339:101-106 Available from https://proceedings.mlr.press/v339/scaria26a.html.

Related Material