arXiv AI August 17, 2026 By Fatema Tuj Johora Faria, Mukaffi Bin Moin, M. F. Mridha, Jubayer Al Mahmud

TeachMateGPT: A Multi-Agent Knowledge-Grounded Framework for Pedagogical Assessment Generation from Science Curriculum Materials

arXiv:2608. 13708v1 Announce Type: cross Abstract: Automatically generating textbook-grounded assessment items can reduce science teachers' workload, but existing retrieval-augmented generation (RAG) systems rely on flat retrieval, support only single-question generation, lack safeguards against weak evidence, and are ill-suited to low-resource, board-exam-structured curricula.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv Machine Learning

Jun 8

Elmes*: Automated Construction of Fine-Grained Evaluation Rubrics for Large Language Models in Long-Tail Educational Scenarios

arXiv:2606. 06546v1 Announce Type: new Abstract: Evaluating large language models (LLMs) for education requires measuring how models teach, not only what they know.

By Tao Liu, Ye Lu, Ruohua Zhang, Siyu Song, Wentao Liu, Aimin Zhou, Hao Hao

llms agents benchmarks safety

arXiv AI

Jul 14

Automated Textbook Auditing with Multi-Agent LLM Systems

arXiv:2607. 11276v1 Announce Type: cross Abstract: Ensuring the quality of educational materials requires more than standard proofreading: textbooks must be audited for factual accuracy, domain-specific technical correctness, and linguistic quality simultaneously -- a task that general-purpose grammar checkers cannot address.

By Ciprian Cristescu, Adrian-Marius Dumitran, Angela-Liliana Dumitran, Gabriel Stefan

llms agents safety

arXiv AI

Jul 29

Comparing RAG and GraphRAG for Page-Level Retrieval Question Answering on a Math Textbook

arXiv:2509. 16780v3 Announce Type: replace-cross Abstract: Large language models (LLMs) show promise as educational aids but often lack alignment with specific course materials.

By Eason Chen, Chuangji Li, Eric Li, Zimo Xiao, Jionghao Lin, Kenneth R. Koedinger

llms rag nlp safety

arXiv AI

Jun 6

EGTR-Review: Efficient Evidence-Grounded Scientific Peer Review Generation via Multi-Agent Teacher Distillation

arXiv:2606. 06025v1 Announce Type: cross Abstract: Scientific peer review generation has attracted increasing attention for reducing reviewing burdens and providing timely feedback.

By Xinpeng Qiu, Wang Yihu, Zhifeng Liu, Xiaochen Wang, Jimin Wang

llms agents fine-tuning efficiency

arXiv AI

Jun 12

Constructing Evaluation Datasets for Procedural Reasoning: Balancing Naturalness, Grounding, and Multi-Hop Coverage

arXiv:2606. 12767v1 Announce Type: new Abstract: Evaluating procedural reasoning in AI-supported learning systems requires question-answer datasets that are both learner-like and grounded in the instructional knowledge the system is expected to use.

By Sarah Elshabrawy, Rahul K. Dass, Ashok K. Goel

arXiv AI

Jun 16

LearnOpt: Recovering the Latent Cognitive Structure of Standardized Examinations via Knowledge Graphs and Constrained Optimization

arXiv:2606. 15349v1 Announce Type: cross Abstract: Standardized examinations are typically treated as uniform syllabus coverage problems.

By Joy Bose, Om Thomas

llms safety

Related stories

Elmes*: Automated Construction of Fine-Grained Evaluation Rubrics for Large Language Models in Long-Tail Educational Scenarios

Automated Textbook Auditing with Multi-Agent LLM Systems

Comparing RAG and GraphRAG for Page-Level Retrieval Question Answering on a Math Textbook

EGTR-Review: Efficient Evidence-Grounded Scientific Peer Review Generation via Multi-Agent Teacher Distillation

Constructing Evaluation Datasets for Procedural Reasoning: Balancing Naturalness, Grounding, and Multi-Hop Coverage

LearnOpt: Recovering the Latent Cognitive Structure of Standardized Examinations via Knowledge Graphs and Constrained Optimization