Automatically generating high-quality mathematical problems that align with educational objectives is a crucial task in NLP-based educational technology. Traditional generation methods focus primarily on textual quality, but they often overlook educational objectives. Moreover, these methods address only single-dimensional, simple question generation, failing to meet complex, multifaceted educational requirements. To address these challenges, we constructed and annotated EduMath, a dataset of 16k mathematical questions with multi-dimensional educational objectives. Based on this dataset, we developed EQGEVAL, which incorporates three evaluation dimensions and is designed to assess the ability of models to generate educational questions. Drawing inspiration from teachers' problem design processes, we propose the Educational Question Planning with self-Reflection (EQPR) method for educational mathematical question generation, following a "plan-evaluate-optimize" approach. Specifically, by combining planning algorithm based on Monte Carlo Tree Search with the generative capabilities of Large Language Models, we continuously optimize questions through iterative feedback. This self-optimization mechanism ensures that the generated questions both fit the educational context and strategically achieve specific basic educational objectives. Through extensive experiments based on EQGEVAL, we have demonstrated that EQPR achieves significant improvements in generating questions that meet multi-dimensional educational objectives.

LLM chatbot interfaces allow students to get instant, interactive assistance with homework, but doing so carelessly may not advance educational objectives. In this study, an interactive homework help system based on DeepSeek R1 is developed and first implemented for students enrolled in a large computer science beginning programming course. In addition to an assist button in a well-known code editor, our assistant also has a feedback option in our command-line automatic evaluator. It wraps student work in a personalized prompt that advances our educational objectives without offering answers straight away. We have discovered that our assistant can recognize students' conceptual difficulties and provide ideas, plans, and template code in pedagogically appropriate ways. However, among other mistakes, it occasionally incorrectly labels the correct student code as incorrect or encourages students to use correct-but-lesson-inappropriate approaches, which can lead to long and frustrating journeys for the students. After discussing many development and deployment issues, we provide our conclusions and future actions.

Every year, the OECD Forum brings together experts, academics and thought leaders from the private and public sector to discuss key economic and social challenges on the international agenda. The theme of this year's Forum was "World in EMotion" – a theme that reflects the profound changes brought about by globalisation, shifting politics and digitalisation, and the challenges and opportunities that they present. Nowhere are these changes more rapid – and perhaps far-reaching – than in the field of artificial intelligence (AI), and its implications for values and ethics. I attended a very interesting panel on this subject, alongside Peter Gluckman, Chair of the International Network for Government Science Advice in New Zealand; Geoff Mulgan, Chief Executive of NESTA in the UK; Eric Salobir head of Optic; Pallaw Sharma, Senior Vice President at Johnson & Johnson; and Jess Whittlestone, Research Associate at the Centre for the Future of Intelligence at Cambridge University. As Pallaw explained, technology and AI are not magic powers; they are just extraordinary amplifiers and accelerators that add speed and accuracy.