1 citations · 1 across the 10 of their papers we have counts for
3 papers · 1 filter
When Should Users Check? Modeling Confirmation Frequency inMulti-Step Agentic AI Tasks
Jieyu Zhou, Aryan Roy, Sneh Gupta +2
Existing AI agents typically execute multi-step tasks autonomously and only allow user confirmation at the end. During execution, users have little control, making the confirm-at-e…
Beyond Final Answers: Evaluating Large Language Models for Math Tutoring
Adit Gupta, Jennifer Reddig, Tommaso Calo +2
Researchers have made notable progress in applying Large Language Models (LLMs) to solve math problems, as demonstrated through efforts like GSM8k, ProofNet, AlphaGeometry, and Mat…
AI2T: Building Trustable AI Tutors by Interactively Teaching a Self-Aware Learning Agent
Daniel Weitekamp, Erik Harpstead, Kenneth Koedinger
AI2T is an interactively teachable AI for authoring intelligent tutoring systems (ITSs). Authors tutor AI2T by providing a few step-by-step solutions and then grading AI2T's own pr…