A 30-day, knowledge-tracing-grounded simulated learner benchmark for tutoring agents finds that no base model or harness alone determines quality and that almost all tested combinations plateau within days.
In Findings of the Association for Computational Linguistics: EMNLP 2024, 13641–13650
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CY 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
EduClaw-Bench: A Long-Horizon Benchmark for Pedagogical LLM Agents with Simulated Learners
A 30-day, knowledge-tracing-grounded simulated learner benchmark for tutoring agents finds that no base model or harness alone determines quality and that almost all tested combinations plateau within days.