Advancing the Science of Human and AI Tutoring through Shared Infrastructure

A Collaborative Workshop

Full-day Workshop as part of the Festival of Learning 2026 Festival of Learning 2026

High-quality tutoring is among the most impactful instructional interventions in education. However, these programs remain difficult to scale effectively, and the specific "moves" underlying quality tutoring are understudied due to historical data scarcity. Despite extensive research, progress is hindered by challenges in data de-identification, multimodal analysis, and the predictive modeling of student outcomes. The emergence of Artificial Intelligence is fundamentally shifting the capacity to scale and study tutoring, offering transformative potential alongside significant pitfalls. This workshop, led by the National Tutoring Observatory, the SCALE Initiative, and the LEVI HAT project, brings together researchers, providers, and practitioners to explore human and AI tutoring systems. Featuring sessions on open-source data, infrastructure benchmarks, and synthetic students, the workshop aims to foster collaboration that ensures the future of instruction is grounded in rigorous empirical science.

Date and time:

Sunday, June 28 (full day)

Location:

513, Yeongdong-daero, Gangnam-gu, Seoul 06164, Republic of Korea

Tentative Agenda

The workshop will feature overviews of major AI infrastructure projects from the NTO, SCALE Initiative, and LEVI HAT, followed by hands-on sessions where participants engage directly with tools for annotation, schema development, and tutoring discourse analytics. A second set of sessions will focus on tutoring providers, beginning with Third Space Learning’s perspective on the transition from human tutoring at scale to conversational AI tutoring. Organizations including Saga Education, UPchieve, and Carnegie Learning will then give interactive demos and presentations highlighting their platforms, research, pedagogical priorities, and real-world data capture practices. The workshop will conclude with panel discussions on the future of educational AI, including infrastructure development, ways AI can better support tutors and administrators, and the broader funding landscape. Together, these sessions are designed to connect technical innovation, practical implementation, and cross-sector strategy for advancing high-quality tutoring at scale.

Organizing Committee

Kirk Vanacore (Cornell University; National Tutoring Observatory)

Danielle R. Thomas (Carnegie Mellon University; National Tutoring Observatory; Personalized Learning Squared)

Ana Ribeiro (Stanford University; SCALE Initiative)

Julian Bernado (Stanford University; SCALE Initiative)

Chelsea Chandler (University of Colorado Boulder)

Candida Crawford (Third Space Learning)

Doug Pietrzak (National Tutoring Observatory; FreshCognate)

John Whitmer (Learning Data Insights)

Jason Godfrey (Accelerate)

Susanna Loeb (Stanford University; SCALE Initiative)

Kenneth R. Koedinger (Carnegie Mellon University; National Tutoring Observatory; Personalized Learning Squared)

Justin Reich (MIT; National Tutoring Observatory)

Rachel Slama (Cornell University; National Tutoring Observatory)

René F. Kizilcec (Cornell University; National Tutoring Observatory)

The International Conference on Learning Analytics & Knowledge Workshop

For questions about the LAK26 workshop, contact:

Kirk Vanacore: kpv27@cornell.edu

Rene Kizilcec: kizilcec@cornell.edu

About the National Tutoring Observatory

The NTO is a first-of-its-kind research infrastructure that advances the science of teaching by capturing and analyzing tutoring interactions at scale. Its two core components are: (1) the Million Tutor Moves (MTM) repository, a large collection of multimodal tutoring data—transcripts, video, audio, and metadata—linked to student outcomes; and (2) open-source tools for securely de-identifying and annotating these data. Together, they enable researchers, practitioners, and developers to identify which instructional moves and interaction patterns most effectively drive learning.

The NTO partners with leading tutoring providers (Saga Education, UPChieve, Carnegie Learning, Third Space Learning, PLUS, Eedi), teacher feedback platforms like TeachFX, and infrastructures such as Databrary and LearnSphere. These collaborations pool diverse datasets and advance community standards for interoperability, annotation, and responsible sharing. By lowering barriers to fine-grained tutoring data, the NTO empowers the learning analytics community to explore new questions of instructional effectiveness. For LAK participants, it offers datasets, workflows, and a collaborative hub for advancing tutoring research.

Page updated

Google Sites

Report abuse