arXiv Computation and Language
StudentSim: Training LLM-based Student Simulators
Read the original on arXiv Computation and Language →The Flow has not summarised this story yet — read it at arXiv Computation and Language.
Related stories
arXiv AI
Aug 5
EduClaw-Bench: A Long-Horizon Benchmark for Pedagogical LLM Agents with Simulated Learners
arXiv:2608. 03206v1 Announce Type: cross Abstract: Large language models (LLMs) power educational applications from tutoring to essay scoring, but each is a point solution to a single task, and only recently have these point solutions been integrated into agents operating over a learning management system (LMS).
arXiv Machine Learning
Sep 14
Simulating Disengaged Students to Evaluate LLM-based Tutors
The paper introduces Disengagement-Aware Student Simulators (DAS2), a protocol that models five learner-engagement states—engaged, gaming, wheel-spinning, off-task, and mixed—to evaluate AI tutor performance before deployment. Using annotated tutoring sessions from ASSISTments09, DAS2’s rule-based labels matched human consensus in 81% of cases, and conditioning simulations on intended states narrowed the correctness-rate gap between simulated and authentic sessions for gaming and wheel-spinning behaviors. The study also compares five AI tutors across these states, finding stable relative rankings but state-specific performance differences, and notes that automated evaluation does not fully align with human judgment.
arXiv AI
Sep 24
StudentBench: AI and human tutoring yield equivalent GRE learning gains
arXiv:2609.28470v1 Announce Type: new Abstract: Artificial intelligence offers an unprecedented opportunity to augment human capabilities, yet progress at the frontier has focused primarily on advanc...
arXiv Machine Learning
Oct 15
HACHIMI-II: From Role-Play to Learner Behavior Modeling for Faithful Student Simulation
HACHIMI-II redefines student simulation by modeling a learner’s behavior rather than relying on a language model’s role‑play. It builds a student model from the learner’s history, infers their current state, and uses this to constrain the next simulated action. Across item‑response and dialogue datasets, HACHIMI-II achieves markedly smaller ability gaps and more accurate error reproduction than leading baselines.
arXiv AI
Jul 10
Compete Then Collaborate: Frontier AI Teachers Build a Verifiable Curriculum to Improve a Coding Student Beyond Imitation
arXiv:2607. 08255v1 Announce Type: new Abstract: Large language models increasingly serve as teachers generating training data for smaller students.
arXiv Computation and Language
Sep 28
Recursive Self-Improvement via On-Policy Distillation for Reasoning
The paper introduces a recursive self-improvement framework for language models that replaces an external teacher with a frozen copy of the student, enabling dynamic co-evolution (DCE) and self-refined concise learning (SRCL). DCE allows the privileged teacher to evolve alongside the student, while SRCL trains on shorter, verified rewrites to reduce verbosity. Experiments show that the combined DCE+SRCL approach outperforms traditional on‑policy self‑distillation across multiple model sizes and math benchmarks, achieving significant accuracy gains and shorter outputs.