The paper introduces a cost‑aware framework that treats each prompt type as an arm in a multi‑armed bandit controller, enabling adaptive selection of optimal prompting strategies during inference for automated essay scoring. Experiments on IELTS Writing Task 2 essays demonstrate that this bandit-driven approach achieves comparable scoring accuracy to exhaustive grid search while reducing LLM calls by 78.4%. The study also presents the first cost‑reliability learning curves for essay scoring, offering actionable insights for educational technology platforms balancing operational costs against assessment validity.
By Olga Manakina, Igor Bogdanov
PersonaPath is a new benchmark for knowledge‑centric personalized learning path planning, pairing 2,000 learner personas with a hierarchical knowledge graph of 347 textbooks, 1,751 units, and 4,092 concepts across 77 subjects. The study evaluates large language models on this benchmark, finding that even the best model achieves only a 29.5% final pass rate in Basic Education and fails to exceed 44.7% in tailoring paths to individual learners, highlighting a significant adaptivity gap. This work underscores the challenge of moving beyond exercise‑centric recommendation toward goal‑oriented, curriculum‑scale guidance.
By Yu Liu, Zeming Liu, Tianle Zhang, Zihao Cheng, Yuhang Guo, Kehai Chen, Min Zhang, Yunhong Wang, Haifeng Wang
The paper introduces TIZSKT, a zero‑shot cross‑domain knowledge tracing model that separates behavioral sequence modeling from domain‑local historical evidence construction. It uses text as an index via a frozen text encoder and unsupervised per‑domain projection to build question addresses, then aggregates a student’s past outcomes into a question‑specific historical correctness summary. Experiments on three public datasets show that TIZSKT outperforms baselines in mean AUC and accuracy, with ablations confirming the importance of text addressing and cross‑segment continuation.
By Yin Yi, Haiping Ma, Siyu Song, Ziwen Wang, Shangshang Yang
Large language models (LLMs) have been widely applied to automated essay scoring (AES) and automated feedback generation (AFG). However, existing studies rely primarily on prompt engineering or supervised fine-tuning, while systematic research on reinforcement learning (RL) post-training and automated evaluation of feedback quality remains limited.
arXiv:2607. 19219v1 Announce Type: cross Abstract: Large language models (LLMs) have been widely applied to automated essay scoring (AES) and automated feedback generation (AFG).
By Xuefeng Jin, Jiashuo Zhang, Teng Cao, Bin Yang
The paper introduces ReVeR, a pointwise rubric reward model that derives hard rules and graded principles directly from instructions, avoiding response-induced bias. It employs tool-augmented judges and label‑blind distillation to create ReVeR‑Traces, a large dataset of rubric reasoning and judging trajectories. Experiments show ReVeR surpasses pairwise rubric models in preference accuracy, especially for instruction following, and reveal that higher preference accuracy does not always lead to better downstream policies.
Despite rapid advances in large language models (LLMs), their deployment in the sports and health domain remains high-risk due to the absence of domain-specific evaluation benchmarks. Existing general...
arXiv:2604. 22770v2 Announce Type: replace-cross Abstract: Most digital language learning curricula rely on discrete-item quizzes that test recall rather than applied conversational proficiency.
By Nicy Scaria, Silvester John Joseph Kennedy, Deepak Subramani
arXiv:2610.19380v1 Announce Type: new
Abstract: User feedback enables LLMs to refine reusable personalized skills, but often mixes persistent preferences with request-specific corrections. Indiscrimi...
By Li Wang, Chen Zhang, Yirong Yang, Xingyu Chen, Jinkun Zhao, Tianhao Peng, Wenjun Wu
The paper introduces a human‑in‑the‑loop framework for AI‑assisted scoring of short written responses in a large‑scale national assessment. Using data from two recent test editions with about 5,000 student responses each, the authors validate that AI‑generated scores align moderately to highly with human raters across multiple rubric dimensions. The framework includes a correction workflow that flags cases needing human review, thereby reducing manual workload while maintaining assessment quality.
By Mar\'ia Eugenia Curi, Germ\'an Capdehourat, Isabel Amigo, Magdalena Romano, Rosana Serra, Adri\'an Silveira, Andr\'es Peri
arXiv:2604. 26962v3 Announce Type: replace-cross Abstract: Education is one of the most promising real-world applications for Large Language Models (LLMs).
By Bingxi Zhao, Jiahao Zhang, Xubin Ren, Zirui Guo, Tianzhe Chu, Yi Ma, Chao Huang
Reinforcement learning (RL) is vital for optimizing video generation models, with a robust reward model (RM) serving as the cornerstone. However, existing video reward models often produce unstable sc...