Today's large language models (LLMs) exhibit many impressive skills but remain imperfect in key

Classical methods for AMR depend on heuristics or expensive error estimators, hindering their use for complex simulations.

Deep reinforcement learning (RL) is a powerful approach to complex decision making. However, one issue that limits its practical application is its brittleness, sometimes failing to train in the presence of small changes in the environment.

Surprisingly, applying over 20 established estimators to the dataset produces inconsistent results in evaluating the nonprofit's efficacy.

Temporal graph learning is crucial for dynamic networks where nodes and edges evolve over time and new nodes continuously join the system. Inductive representation learning in such settings faces two major challenges: effectively representing unseen nodes and mitigating noisy or redundant graph information. We propose GTGIB, a versatile framework that integrates Graph Structure Learning (GSL) with Temporal Graph Information Bottleneck (TGIB). We design a novel two-step GSL-based structural enhancer to enrich and optimize node neighborhoods and demonstrate its effectiveness and efficiency through theoretical proofs and experiments. The TGIB refines the optimized graph by extending the information bottleneck principle to temporal graphs, regularizing both edges and features based on our derived tractable TGIB objective function via variational approximation, enabling stable and efficient optimization. GTGIB-based models are evaluated to predict links on four real-world datasets; they outperform existing methods in all datasets under the inductive setting, with significant and consistent improvement in the transductive setting.

The role of Artificial Intelligence (AI) in education is undergoing a rapid transformation, moving beyond its historical function as an instructional tool towards a new potential as an active participant in the learning process. This shift is driven by the emergence of agentic AI, autonomous systems capable of proactive, goal-directed action. However, the field lacks a robust conceptual framework to understand, design, and evaluate this new paradigm of human-AI interaction in learning. This paper addresses this gap by proposing a novel conceptual framework (the APCP framework) that charts the transition from AI as a tool to AI as a collaborative partner. We present a four-level model of escalating AI agency within human-AI collaborative learning: (1) the AI as an Adaptive Instrument, (2) the AI as a Proactive Assistant, (3) the AI as a Co-Learner, and (4) the AI as a Peer Collaborator. Grounded in sociocultural theories of learning and Computer-Supported Collaborative Learning (CSCL), this framework provides a structured vocabulary for analysing the shifting roles and responsibilities between human and AI agents. The paper further engages in a critical discussion of the philosophical underpinnings of collaboration, examining whether an AI, lacking genuine consciousness or shared intentionality, can be considered a true collaborator. We conclude that while AI may not achieve authentic phenomenological partnership, it can be designed as a highly effective functional collaborator. This distinction has significant implications for pedagogy, instructional design, and the future research agenda for AI in education, urging a shift in focus towards creating learning environments that harness the complementary strengths of both human and AI. For decades, the integration of Artificial Intelligence in Education (AIED) has been a subject of intense research and development, promising to transform teaching and learning (Yan, Greiff, Teuber and Gašević, 2024; Giannakos, Azevedo, Brusilovsky, Cukurova, Dimitriadis, Hernandez-Leo, Järvelä, Mavrikis and Rienties, 2025; Chen, Zou, Xie, Cheng and Liu, 2022). Historically, this promise has been pursued primarily through the lens of individualization and efficiency. The predominant applications of AIED have been Intelligent Tutoring Systems (ITS) and adaptive learning platforms, which leverage AI to provide personalized instruction, real-time feedback, and customized learning pathways (Ouyang and Jiao, 2021; Kulik and Fletcher, 2016). These systems, often built on cognitive and mastery-learning principles, have demonstrated effectiveness in specific, well-defined domains (Kulik and Fletcher, 2016). However, they have also faced criticism for frequently replicating traditional, teacher-centric pedagogical models, where knowledge is transmitted to a passive learner (Ouyang and Jiao, 2021; Kulik and Fletcher, 2016).