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).
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: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...
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:2607. 08255v1 Announce Type: new Abstract: Large language models increasingly serve as teachers generating training data for smaller students.
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.
arXiv:2509. 14257v3 Announce Type: replace-cross Abstract: Large Language Model agents achieve strong performance on multi-step reasoning and tool-use tasks, but their impressive capabilities typically rely on extremely large backbones.
D‑Skill is a framework that distills the behavioral advantage of a large language‑model teacher into an interpretable natural‑language skill document, using only paired rollouts and no weight updates. The skill is constructed offline from fixed trajectories, then provided to a smaller student model at inference time. Across benchmarks such as SpreadsheetBench‑Verified, ALFWorld, and chess puzzles, D‑Skill closes 75‑95% of the teacher‑student performance gap and reduces inference cost by 5.7×–8.3× compared to the teacher.
arXiv:2608.21668v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to simulate students at different mastery levels. These simulations can generate synthetic training...
EVOL is a framework that uses a knowledge‑tracing simulator to generate per‑learner expert demonstrations via evolutionary search, and then trains a deployment‑free policy that distills these demonstrations into a feed‑forward learner. The method employs an asymmetric actor‑critic architecture, where the actor plans blindly as in real deployment while the critic has access to privileged simulator state during training. Across three educational datasets and varying path lengths, EVOL outperforms eight baselines and shows that the quality of evolutionary experts, rather than the imitation objective, drives final performance.
arXiv:2609.17474v1 Announce Type: cross Abstract: Large language model (LLM) distillation aims to transfer the capabilities of a powerful teacher to a smaller student. Direct imitation, however, can...
PEARL is a framework that trains Socratic tutoring agents using pedagogically aligned reinforcement learning. It introduces a controllable student simulator to model diverse cognitive states, a reward model that jointly evaluates pedagogical quality and correctness, and a stable multi‑objective RL approach to balance competing tutoring goals. Experiments demonstrate that PEARL competes with both open‑source tutoring systems and leading proprietary LLMs.