Are Agents Ready to Teach? A Multi-Stage Benchmark for Real-World Teaching Workflows

TL;DR

EduAgentBench is a comprehensive benchmark designed to evaluate language agents' ability to perform complex, real-world teaching tasks, highlighting current models' strengths and limitations in pedagogical judgment and workflow execution.

Contribution

The paper introduces EduAgentBench, the first holistic, theory-grounded benchmark for assessing the full scope of teaching capabilities in language agents.

Findings

Models perform well in bounded pedagogical judgment.

Models fall short in situated multi-turn tutoring.

Models are limited in autonomous teaching workflow execution.

Abstract

Language agents are increasingly deployed in complex professional workflows, with tutoring emerging as a particularly high-stakes capability that remains largely unmeasured in existing benchmarks. Effective tutor agents require more than producing correct answers or executing accurate tool calls: a robust tutor must diagnose learner state, adapt support over time, make pedagogically justified decisions grounded in educational evidence, and execute interventions within realistic learning-management systems. We introduce EduAgentBench, a source-grounded benchmark for holistically evaluating tutor agents across the full scope of teaching work. It contains 150 quality-controlled tasks across three capability surfaces: professional pedagogical judgment, situated multi-turn tutoring, and Canvas-style teaching workflow completion. Tasks are constructed through a pedagogical-insight-driven pipeline and evaluated with complementary verification signals and human review. Across a comprehensive evaluation of frontier models, our findings reveal that current models are generally capable of bounded pedagogical judgment, but still fall short of professional teaching standards in situated tutoring and autonomous teaching-workflow execution. To our knowledge, EduAgentBench is the first theory-grounded and realistic benchmark for evaluating the holistic teaching capability of tutor agents, providing a measurement foundation for developing future tutor agents that can support realistic teaching work.