ACE-TA: An Agentic Teaching Assistant for Grounded Q&A, Quiz Generation, and Code Tutoring

TL;DR

ACE-TA is an autonomous teaching assistant framework leveraging large language models to provide grounded Q&A, adaptive quizzes, and interactive coding guidance for programming education.

Contribution

It introduces a modular system integrating retrieval-based Q&A, quiz generation, and interactive coding support using pre-trained LLMs.

Findings

Provides precise, context-aligned explanations for programming concepts.

Generates adaptive, multi-topic assessments for higher-order understanding.

Guides students through coding with iterative feedback and sandboxed execution.

Abstract

We introduce ACE-TA, the Agentic Coding and Explanations Teaching Assistant framework, that autonomously routes conceptual queries drawn from programming course material to grounded Q&A, stepwise coding guidance, and automated quiz generation using pre-trained Large Language Models (LLMs). ACE-TA consists of three coordinated modules: a retrieval grounded conceptual Q&A system that provides precise, context-aligned explanations; a quiz generator that constructs adaptive, multi-topic assessments targeting higher-order understanding; and an interactive code tutor that guides students through step-by-step reasoning with sandboxed execution and iterative feedback.