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.
By Qikai Chang, Zhenrong Zhang, Linbo Chen, Pengfei Hu, Jianshu Zhang, Youhui Guo, Jun Du
arXiv:2606. 12281v1 Announce Type: cross Abstract: In Decentralized Training and Decentralized Execution (DTDE) for cooperative Multi-Agent Reinforcement Learning (MARL), action-advising-based knowledge sharing promotes interpretable and scalable cooperation among agents.
By Jinyuan Zu, Xiaowei Lv, Yongcai Wang, Deying Li, Yunjun Han, Wenping Chen, Fengyi Zhang, Naiqi Wu
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.
By Xianghui Meng, Jionghao Lin
arXiv:2608. 04148v1 Announce Type: cross Abstract: Agentic AI is increasingly used to coordinate planning, implementation, review, and testing in software development, yet it often offers limited transparency into its decisions and interactions.
By Zihan Fang, Yueke Zhang, Yu Huang
arXiv:2604. 04251v2 Announce Type: replace Abstract: Intelligent tutoring systems increasingly rely on reinforcement learning to personalise instruction, yet optimising for observable engagement signals can systematically decouple learner activity from genuine knowledge acquisition.
By Oluseyi Olukola, Nick Rahimi
arXiv:2607. 25446v1 Announce Type: new Abstract: Multi-agent frameworks built on large language models (LLMs) routinely entangle three logically distinct concerns: who is on the team (organization), how members align (coordination), and which algorithm fuses their work (collaboration protocol).
By Huan Chen, Xiang Song, Jian Jin, Pan Ren, Liang-Jie Zhang
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).
By Unggi Lee, Sookbun Lee, Yeil Jeong, Eunjoo Lee, Minchul Shin, Hoilym Kwon
arXiv:2606. 03461v1 Announce Type: new Abstract: Stronger code agents are commonly assumed to be superior teachers for post-training, yet this assumption remains poorly disentangled from task difficulty, harness design, and student capacity.
By Sidi Yang, Chaofan Tao, Jierun Chen, Tiezheng Yu, Ruoyu Wang, Yuxin Jiang, Yiming Du, Wendong Xu, Jing Xiong, Taiqiang Wu, Lifeng Shang, Xiaohui Li, Ngai Wong, Haoli Bai
arXiv:2606. 30774v1 Announce Type: new Abstract: We study when natural-language feedback produces improvement beyond the gains obtainable from repeated attempts alone.
By Bart{\l}omiej Cupia{\l}, Jan {\L}ojek, Miko{\l}aj Garstecki, Szymon Pob{\l}ocki, Alicja Ziarko, Piotr Mi{\l}o\'s
arXiv:2608. 07509v1 Announce Type: cross Abstract: LLMs are increasingly used for conversational tutoring, but effective tutoring requires more than correct answers.
By Fares Fawzi, Jiaxu Zhao, Tanya Nazaretsky, Tanja K\"aser
The study analyzes 20,462 student turns from 1,260 sessions with a guided LLM chemistry tutor, identifying 6,630 impasse turns categorized as conceptual errors, expressed uncertainty, or help‑seeking. Three tutoring conditions—baseline, no‑direct‑answer, and guided—were simulated, revealing that the baseline tutor often gave direct answers, the no‑direct‑answer tutor always asked follow‑up questions, and the guided tutor varied its responses based on context. Impasse trajectories showed that each additional impasse turn reduced the likelihood of recovery, while addressing errors became increasingly beneficial compared to repeated scripted questioning.
By Bakhtawar Ahtisham, Kirk Vanacore, Alessandra Napoli, Josh Arens, Ksenia Ionova, Clayton Cohn, Shima Salehi, Rene Kizilcec
arXiv:2607. 13370v1 Announce Type: cross Abstract: This paper is an extension of a paper presented at the ICAART 2026 conference, which introduced LEA (Learning Engagement Assistant), an adaptive AI tutoring agent combining course-specific Retrieval-Augmented Generation (RAG) with structured Knowledge Component (KC) models across integrated Chat, Tutor, and Quiz modes.
By Teri Rumble, Javad Zarrin, P. George Lovell, Ruth Falconer