|
| 1 | +- [TanStack Start](https://tanstack.com/start/latest) |
| 2 | + - [[Web development]], [[React]] |
| 3 | +- [The Origins of Cauchy’s Rigorous Calculus (Dover Books on Mathematics) by Judith V. Grabiner (PDF) | sci-books.com](https://sci-books.com/the-origins-of-cauchys-rigorous-calculus-dover-books-on-mathematics-b00iaduptk/) |
| 4 | + - [[Calculus]] |
| 5 | +- [Calculus | Differential and Integral Calculus - GeeksforGeeks](https://www.geeksforgeeks.org/maths/math-calculus/) |
| 6 | + - [[Calculus]] |
| 7 | + - [Real-Life Applications of Differentiation - GeeksforGeeks](https://www.geeksforgeeks.org/maths/real-life-applications-of-differentiation/#) |
| 8 | +- The essence of calculus - YouTube https://m.youtube.com/watch?v=WUvTyaaNkzM&list=PLZHQObOWTQDMsr9K-rj53DwVRMYO3t5Yr |
| 9 | + - [[Calculus]] |
| 10 | +- [Navigating the Jagged Frontier](https://drphilippahardman.substack.com/p/defining-and-navigating-the-jagged?publication_id=926556&post_id=177492282&isFreemail=true&r=1gwis&triedRedirect=true) |
| 11 | + - [[Learning Design]], [[Artificial intelligence in education]], [[Learning objective]], [[Course design]], [[Multiple choice test]] |
| 12 | +- [[2508.16659] Enabling Multi-Agent Systems as Learning Designers: Applying Learning Sciences to AI Instructional Design](https://arxiv.org/abs/2508.16659) |
| 13 | + - [[Learning Design]], [[AI agents]], [[Learning sciences]], [[Artificial intelligence in education]], [[Pedagogical content knowledge]], [[Prompt engineering]], [[Secondary education]], [[STEM education]], [[Applying psychology to education]], [[AI evaluation]], [[Bias in algorithms]], [[Faculty perception]], [[Instructional quality]], [[Quality Matters]], [[Evaluating teaching]] |
| 14 | + - >LLMs, such as ChatGPT and Gemini which are among the most widely accessible to teachers, do not come preloaded with the depth of pedagogical theory needed to design truly effective activities; second, although sophisticated prompt engineering can bridge this gap, most teachers lack the time or expertise and find it difficult to encode such pedagogical nuance into their requests. |
| 15 | + - >We embed the well-established Knowledge-Learning-Instruction (KLI) framework into a Multi-Agent System (MAS) to act as a sophisticated instructional designer. |
| 16 | + - >Teachers strongly preferred the activities from the collaborative MAS-CMD, describing them as significantly more creative, contextually relevant, and classroom-ready. |
| 17 | + - >Teachers did not just rate the MAS-CMD outputs higher; they articulated why. Their praise centered on specific, high-value attributes that the rubric may not fully weigh: creativity (“so creative,” “fantastic idea”), deep contextual relevance (the “urban planning theme makes the geometry meaningful”), and, crucially, teacher-centric utility (the inclusion of a “worksheet and exit ticket” was “Super helpful”). |
| 18 | + - >LLMs are known to exhibit systematic biases, including a preference for longer outputs, a tendency to favor the first option in a comparison, and a potential preference for outputs generated by models from the same developer family |
| 19 | + - >the LLM judge reached a “ceiling effect” on several criteria, such as Foundational Alignment and Inclusivity, where all systems scored near the maximum, limiting the rubric’s ability to differentiate the outputs meaningfully |
| 20 | + - >The key contribution is showing that embedding learning science principles directly into AI architectures is an effective way to produce pedagogically sound materials. This approach bridges the “prompting gap,” shifting AI from a content generator to a pedagogical partner. Findings also highlight that MAS architecture matters: a collaborative, discussion-based model outperformed a sequential one in producing innovative, coherent designs. |
| 21 | + - [The Knowledge‐Learning‐Instruction Framework: Bridging the Science‐Practice Chasm to Enhance Robust Student Learning - Koedinger - 2012 - Cognitive Science - Wiley Online Library](https://onlinelibrary.wiley.com/doi/10.1111/j.1551-6709.2012.01245.x) |
| 22 | +- [Toward a New Instructional Design Methodology in the Era of Generative AI | SpringerLink](https://link.springer.com/chapter/10.1007/978-3-031-98476-1_1) |
| 23 | + - [[ADDIE]], [[Instructional design]], [[Artificial intelligence in education]], [[Personalized learning]] |
| 24 | + - [From ADDIE to ADGIE: A learning design framework reimagined for the AI era | Media | Blify](https://www.blify.co/library/articles/from-addie-to-adgie-learning-design-framework) |
| 25 | +- [[2510.05417] Exploring Student Choice and the Use of Multimodal Generative AI in Programming Learning](https://arxiv.org/abs/2510.05417) |
| 26 | + - [[Multimodal AI]], [[Computer science education]], [[Artificial intelligence in education]], [[Gemini]], [[Code generation]] |
| 27 | +- [[2505.08588] Small but Significant: On the Promise of Small Language Models for Accessible AIED](https://arxiv.org/abs/2505.08588) |
| 28 | + - [[Local AI]], [[Artificial intelligence in education]], [[Multiple choice test]], [[Knowledge graph]], [[Question bank]], [[Curriculum map]], [[Semantic web]] |
| 29 | + - [Automated Generation and Tagging of Knowledge Components from Multiple-Choice Questions | Proceedings of the Eleventh ACM Conference on Learning @ Scale](https://dl.acm.org/doi/10.1145/3657604.3662030) |
| 30 | + - [[2505.06469] KCluster: An LLM-based Clustering Approach to Knowledge Component Discovery](https://arxiv.org/abs/2505.06469) |
| 31 | + - >The core idea is that language models can induce a novel measure of question similarity, which a clustering algorithm can use to identify groups of similar questions that are likely to share the same KC |
| 32 | + - >We derive a formula for question congruity, our novel measure of question similarity mathematically equivalent to the pointwise mutual information (PMI) [7] between two questions, and describe an algorithm that uses Phi-2 to calculate various required probabilities. |
| 33 | +- [Mapping student-AI interaction dynamics in multi-agent learning environments: Supporting personalized learning and reducing performance gaps - ScienceDirect](https://www.sciencedirect.com/science/article/abs/pii/S0360131525002404) |
| 34 | + - [[AI agents]], [[Student-content interaction]], [[Human-computer interaction]], [[Personalized learning]], [[Artificial intelligence in education]], [[Prior knowledge]], [[Achievement]], [[Course recipe]], [[Adaptive learning]], [[Pedagogical agent]], [[MOOC]] |
| 35 | + - [[2506.02993] Mapping Student-AI Interaction Dynamics in Multi-Agent Learning Environments: Supporting Personalised Learning and Reducing Performance Gaps](https://arxiv.org/abs/2506.02993) |
| 36 | +- >Multiple agents work collaboratively to facilitate the entire process of course design, instruction, and management. The interface agents in MAIC system include teacher and student agents, while the back-end agents consist of analytical agents such as the Classroom Situation Analysis Agent, Learning Situation Analysis Agent, and Classroom Director Agent. For course design the instructors upload relevant course materials, and the agents utilize a range of models such as |
| 37 | + multimodal understanding and knowledge structure extraction to draft teaching slides and lecture scripts. The instructor could further collaborate with agents to optimize the slides and scripts. Once the preparation is completed, the course is conducted by AI teaching agents which utilize highly human-like natural speech, closely mimicking the tone and delivery of real classroom teacher. Students listened the lecture while interacting with multiple AI peers. Four types of AI peers are designed to provide students with a more simulated learning environment-- Sparker, Questioner, Thinker and Notetaker |
| 38 | + - [[2409.03512] From MOOC to MAIC: Reshaping Online Teaching and Learning through LLM-driven Agents](https://arxiv.org/abs/2409.03512) |
| 39 | +- [[2505.08083] LLMs to Support K-12 Teachers in Culturally Relevant Pedagogy: An AI Literacy Example](https://arxiv.org/abs/2505.08083) |
| 40 | + - [[Culturally responsive pedagogy]], [[AI literacy]], [[Inclusive teaching]], [[Prompt engineering]], [[AI assistant]], [[Learning Design]], [[streamlit]], [[Artificial intelligence in education]] |
| 41 | + - [AIED2025Wang.pdf](https://dev.stamper.org/publications/AIED2025Wang.pdf) |
| 42 | +- [Culturally Responsive Teaching Checklist - Re-imagining Migration](https://reimaginingmigration.org/resource-items/cultural-responsive-teaching-checklist/) |
| 43 | + - [[Culturally responsive pedagogy]], [[Checklist]] |
| 44 | +- [OSF | What Instructors Learn When Teaching Design Thinking to Beginners](https://osf.io/preprints/edarxiv/t4dbu_v1) |
| 45 | + - [[Design thinking]], [[Service learning]], [[Authentic learning]] |
| 46 | +- [OSF | Development of an Empathic AI Chatbot for Detecting and Responding to Student Frustration in Learning Contexts](https://osf.io/preprints/edarxiv/g97m5_v1) |
| 47 | + - [[Frustration]], [[Chatbot]], [[Empathy]], [[Intelligent tutoring system]], [[Emotion]], [[Affect]], [[Student satisfaction]] |
| 48 | +- [Reviving academic integrity: Part I - Dishonesty as a Design Challenge](https://humanist.ghost.io/reviving-academic-integrity-part-i-dishonesty-as-a-design-challenge/) |
| 49 | + - [[Academic Integrity]], [[Cheating]], [[Artificial intelligence in education]], [[Self-efficacy]], [[Extrinsic motivation]], [[Course policy]] |
| 50 | + - >list of conditions that promote cheating: |
| 51 | + work that seems pointless per se and feels unsatisfying, a hoop to jump through in order to get to an extrinsic reward like a good grade or a diploma; |
| 52 | + a sense of do-or-die urgency, because the stakes of success or failure are high, because the work must be done very quickly, and/or parents or others are putting a lot of pressure on the learner not to fail; |
| 53 | + a perception that others are cheating all the time so it's normalized; |
| 54 | + or a lack of confidence in one's own ability to do the assignment, or that their own work has value (i.e. self-efficacy). |
| 55 | + - [GenAI and Academic Integrity](https://sites.google.com/ucsd.edu/crafting-a-genai-and-ai-policy) |
| 56 | + - [GenAI and Academic Integrity - Documentation](https://sites.google.com/ucsd.edu/crafting-a-genai-and-ai-policy/documentation) |
| 57 | +- [Should Teachers Switch to AI-Powered Browsers? A Hands-On Review of 5 New Tools](https://davidpblross.substack.com/p/should-teachers-switch-to-ai-powered?triedRedirect=true) |
| 58 | + - [[Browser AI]], [[Artificial intelligence in education]] |
| 59 | +- [Benchmark Data Collection | Center for Educational Data Science and Innovation](https://edsi.umd.edu/projects/benchmark-data-collection) |
| 60 | + - [[Data sets]], [[Mathematics education]], [[Artificial intelligence in education]], [[Class observation]], [[Video]] |
| 61 | +- [[2404.02444] The Promises and Pitfalls of Using Language Models to Measure Instruction Quality in Education](https://arxiv.org/abs/2404.02444) |
| 62 | + - [[Instructional quality]], [[Evaluating teaching]], [[Artificial intelligence in education]], [[Natural language processing]] |
| 63 | +- [Faculty Development and Gen AI Playbook - Every Learner Everywhere](https://www.everylearnereverywhere.org/resources/faculty-development-and-gen-ai-playbook/) |
| 64 | + - [[Educational development]], [[Artificial intelligence in education]] |
| 65 | + - [Teaching with AI @ Auburn (Canvas Course)](https://biggio.auburn.edu/programs/professional-development-programs/teaching-with-ai-auburn) |
| 66 | +- [How Schools Can Build Effective Virtual Tutoring | National Student Support Accelerator](https://nssa.stanford.edu/one-pagers/how-schools-can-build-effective-virtual-tutoring) |
| 67 | + - [[Tutoring]] |
| 68 | + - [Understanding Disruptions: Causes of and Variation in Lost Instructional Time | National Student Support Accelerator](https://nssa.stanford.edu/studies/understanding-disruptions-causes-and-variation-lost-instructional-time) |
| 69 | + - [The Power of Personalized Attention: Comparing Pedagogical Approaches in Small Group and One-on-One Early Literacy Tutoring | National Student Support Accelerator](https://nssa.stanford.edu/studies/power-personalized-attention-comparing-pedagogical-approaches-small-group-and-one-one-early) |
| 70 | + - [How new research into virtual tutoring could help schools improve it - Chalkbeat](https://www.chalkbeat.org/2025/10/22/virtual-tutoring-research-highlights-ways-to-improve-it-for-students/) |
| 71 | +- [A New Kind of Web App](https://www.carlassmann.com/blog/new-kind-of-web-app) |
| 72 | + - [[Local first software]], [[PWA]] |
| 73 | + - [GitHub - ccssmnn/tilly: Tilly is a relationship journal. An offline capable PWA that feels really good. It has an AI agent for maximum convenience.](https://github.com/ccssmnn/tilly) |
| 74 | +- [Affinity | Professional Creative Software, Free for Everyone](https://www.affinity.studio/) |
| 75 | + - [[Photo editing]], [[Graphic design]] |
| 76 | +- [How to Build a CRUD App with TanStack Start and TanStackDB (with RxDB Integration)](https://www.freecodecamp.org/news/how-to-build-a-crud-app-with-tanstack-start-and-tanstackdb-with-rxdb-integration/) |
| 77 | + - [[Local first software]] |
| 78 | +- [Microsoft Word - CRM_ELA_1 page.doc - M1-Slide_22_DOK_Hess_Cognitive_Rigor.pdf](https://static.pdesas.org/content/documents/M1-Slide_22_DOK_Hess_Cognitive_Rigor.pdf) |
| 79 | + - [[Bloom's taxonomy]], [[Rigor]] |
| 80 | + - [Hess Rigor Maximizer - ChatGPT](https://chatgpt.com/g/g-68f9219eaf588191bb83b7ac0e2cc353-hess-rigor-maximizer) |
| 81 | +- [ChatGPT Harm Reduction for Writing Assignments](https://docs.google.com/document/d/1jHFFVDGAfgu-4jt8wX6ypEJWeR5Brws5fiI6DK6d8Hc/mobilebasic) |
| 82 | + - [[Writing]], [[Cheating]], [[Artificial intelligence in education]] |
| 83 | +- [pixeltable/pixeltable: Pixeltable — Data Infrastructure providing a declarative, incremental approach for multimodal AI workloads.](https://github.com/pixeltable/pixeltable) |
| 84 | + - [[Multimodal AI]], [[Database]], [[AIOps]], [[Python]] |
| 85 | +- [[2508.05728] CLAPP: The CLASS LLM Agent for Pair Programming](https://arxiv.org/abs/2508.05728) |
| 86 | + - [[Computer science education]], [[programming]], [[AI agents]], [[AI assistant]], [[streamlit]], [[langchain]], [[Retrieval augmented generation]], [[Astronomy education]] |
| 87 | + - [santiagocasas/clapp: CLAPP: CLASS LLM Agent for Pair Programming](https://github.com/santiagocasas/clapp) |
| 88 | +- [[2504.13892] TALLMesh: a simple application for performing Thematic Analysis with Large Language Models](https://arxiv.org/abs/2504.13892) |
| 89 | + - [[Thematic analysis]], [[LLM]], [[streamlit]], [[Qualitative Data Analysis]], [[Research tools]] |
| 90 | +- |
0 commit comments