ErrorRadar is a new benchmark of 2,500 multimodal K-12 math problems for MLLM error step identification and categorization, where GPT-4o trails human experts by ~10%.
hub
Large language models for education: A survey and outlook
22 Pith papers cite this work, alongside 32 external citations. Polarity classification is still indexing.
22
Pith papers citing it
32
external citations · external index
hub tools
citation-role summary
background 3
citation-polarity summary
roles
background 3representative citing papers
Randomized experiment finds AI draft assistance raises feedback provision by teaching assistants 10.8 percentage points without harming quality.
LLM agents inject CWEs into student-authored code to generate personalized security examples; in a 71-student deployment, participants rated them more relevant than textbook cases but quantitative differences remained limited.
Participatory design with 20 Afghan women reveals that safe GenAI learning companions must prioritize privacy, cultural fit, and genuine learning support, with the process itself linked to higher aspirations and agency.
MisEdu-RAG builds concept and instance hypergraphs for two-stage retrieval of pedagogical knowledge and student errors, improving feedback quality on the MisstepMath benchmark by 10.95% token-F1 and up to 15.3% on response dimensions.
ReMe enables LLM agents to evolve via multi-faceted experience distillation, context-adaptive reuse, and utility-based memory refinement, achieving new SOTA results on BFCL-V3 and AppWorld while letting an 8B model beat a 14B memoryless baseline.
An accurate and trusted AI system cannot achieve human-level reasoning because there exist tasks easily solvable by humans but not by the system.
A unified framework and large-scale comparison of graph-based RAG methods on QA tasks yields new high-performing variants obtained by recombining existing components.
ArchRAG proposes attributed-community hierarchical indexing and LLM clustering to improve accuracy and lower token usage in graph-based retrieval-augmented generation.
LectūraAgents proposes a hierarchical multi-agent system with adaptive embodied teaching and the TASA algorithm for personalized AI-assisted learning, reporting gains in content quality, teaching actions, and personalization over baselines via expert educator validation on sample courses.
LFTutor combines LLMs with intent-driven Socratic questioning to tutor laypeople on logical fallacies and outperforms standard LLM baselines in automatic and human evaluations.
A two-year deployment across 120 schools shows that LLM-teacher collaboration improves K-12 writing quality via labor division, with a ceiling effect from excessive LLM linguistic expansion.
ARIA is a multimodal RAG framework that filters domain-specific questions with 97.5% accuracy and outperforms ChatGPT-5 on pedagogical quality for a university civil engineering course.
Hybrid pipeline using YOLO vision and ngspice verification raises circuit analysis accuracy from Gemini's 79.52% baseline to 97.59%, with similar gains on hand-drawn diagrams.
The paper analyzes CPU bottlenecks in agentic AI serving, selects representative workloads, and demonstrates that CPU-aware scheduling optimizations COMB and MAS can reduce P50 latency by up to 1.7x and total latency by up to 2.49x on two hardware systems.
Structured integration of LLMs in astronomy education, including a domain-specific tutor and documentation requirements, leads to improved AI literacy and reduced student reliance on AI over the semester.
ELEVATE is a framework and prototype for deploying LLM-powered 3D avatar tutors locally on consumer hardware with a three-stratum design separating interaction, execution, and governance layers.
The Amico dual-mode prototype in Italy and China provides initial evidence for a set of design principles and observable indicators that enable AI to serve as a relational bridge supporting human-centered pedagogical accompaniment in vocational contexts.
GPT-5 leads English CS certifications, Qwen-Plus leads Chinese ones, DeepSeek-R1 is most balanced, and Llama-3.3 lags in higher reasoning and robustness, with performance dropping on complex questions.
A workshop proposal to reflect on HCI's core identity and the importance of human elements in the era of generative AI.
LLMs can improve education by serving as tutors and collaborators that help students develop resolving strategies instead of providing direct solutions.
citing papers explorer
-
ErrorRadar: Benchmarking Complex Mathematical Reasoning of Multimodal Large Language Models Via Error Detection
ErrorRadar is a new benchmark of 2,500 multimodal K-12 math problems for MLLM error step identification and categorization, where GPT-4o trails human experts by ~10%.
-
AI Assistance for Discretionary Work: Increasing Feedback Provision in Higher Education
Randomized experiment finds AI draft assistance raises feedback provision by teaching assistants 10.8 percentage points without harming quality.
-
Towards Personalizing Secure Programming Education with LLM-Injected Vulnerabilities
LLM agents inject CWEs into student-authored code to generate personalized security examples; in a 71-student deployment, participants rated them more relevant than textbook cases but quantitative differences remained limited.
-
Designing Safe and Accountable GenAI as a Learning Companion with Women Banned from Formal Education
Participatory design with 20 Afghan women reveals that safe GenAI learning companions must prioritize privacy, cultural fit, and genuine learning support, with the process itself linked to higher aspirations and agency.
-
MisEdu-RAG: A Misconception-Aware Dual-Hypergraph RAG for Novice Math Teachers
MisEdu-RAG builds concept and instance hypergraphs for two-stage retrieval of pedagogical knowledge and student errors, improving feedback quality on the MisstepMath benchmark by 10.95% token-F1 and up to 15.3% on response dimensions.
-
Remember Me, Refine Me: A Dynamic Procedural Memory Framework for Experience-Driven Agent Evolution
ReMe enables LLM agents to evolve via multi-faceted experience distillation, context-adaptive reuse, and utility-based memory refinement, achieving new SOTA results on BFCL-V3 and AppWorld while letting an 8B model beat a 14B memoryless baseline.
-
Limitations on Accurate, Trusted, Human-level Reasoning
An accurate and trusted AI system cannot achieve human-level reasoning because there exist tasks easily solvable by humans but not by the system.
-
In-depth Analysis of Graph-based RAG in a Unified Framework
A unified framework and large-scale comparison of graph-based RAG methods on QA tasks yields new high-performing variants obtained by recombining existing components.
-
ArchRAG: Attributed Community-based Hierarchical Retrieval-Augmented Generation
ArchRAG proposes attributed-community hierarchical indexing and LLM clustering to improve accuracy and lower token usage in graph-based retrieval-augmented generation.
-
Lect\=uraAgents: A Multi-Agent Framework for Adaptive Personalized AI-Assisted Learning and Embodied Teaching
LectūraAgents proposes a hierarchical multi-agent system with adaptive embodied teaching and the TASA algorithm for personalized AI-assisted learning, reporting gains in content quality, teaching actions, and personalization over baselines via expert educator validation on sample courses.
-
Tackling the Root of Misinformation by Teaching Laypeople about Logical Fallacies via Socratic Questioning and Critical Argumentation
LFTutor combines LLMs with intent-driven Socratic questioning to tutor laypeople on logical fallacies and outperforms standard LLM baselines in automatic and human evaluations.
-
Double-Edged Sword or Sharp Tool? Designing and Evaluating Triadic LLM-Teacher Collaboration for K-12 Writing at Scale
A two-year deployment across 120 schools shows that LLM-teacher collaboration improves K-12 writing quality via labor division, with a ceiling effect from excessive LLM linguistic expansion.
-
ARIA: Adaptive Retrieval Intelligence Assistant -- A Multimodal RAG Framework for Domain-Specific Engineering Education
ARIA is a multimodal RAG framework that filters domain-specific questions with 97.5% accuracy and outperforms ChatGPT-5 on pedagogical quality for a university civil engineering course.
-
Enhancing Large Language Model-Based Systems for End-to-End Circuit Analysis Problem Solving
Hybrid pipeline using YOLO vision and ngspice verification raises circuit analysis accuracy from Gemini's 79.52% baseline to 97.59%, with similar gains on hand-drawn diagrams.
-
Towards Understanding, Analyzing, and Optimizing Agentic AI Execution: A CPU-Centric Perspective
The paper analyzes CPU bottlenecks in agentic AI serving, selects representative workloads, and demonstrates that CPU-aware scheduling optimizations COMB and MAS can reduce P50 latency by up to 1.7x and total latency by up to 2.49x on two hardware systems.
-
Teaching Astronomy with Large Language Models
Structured integration of LLMs in astronomy education, including a domain-specific tutor and documentation requirements, leads to improved AI literacy and reduced student reliance on AI over the semester.
-
ELEVATE: Designing Human-Centered GenAI Virtual Tutors for Scalable and Inclusive Education
ELEVATE is a framework and prototype for deploying LLM-powered 3D avatar tutors locally on consumer hardware with a three-stratum design separating interaction, execution, and governance layers.
-
Design Principles and Observable Indicators for AI-Enabled Pedagogical Accompaniment: Evidence from the Amico Dual-Mode Prototype in Italy and China
The Amico dual-mode prototype in Italy and China provides initial evidence for a set of design principles and observable indicators that enable AI to serve as a relational bridge supporting human-centered pedagogical accompaniment in vocational contexts.
-
Are LLMs Ready for Computer Science Education? A Cross-Domain, Cross-Lingual and Cognitive-Level Evaluation Using Professional Certification Exams
GPT-5 leads English CS certifications, Qwen-Plus leads Chinese ones, DeepSeek-R1 is most balanced, and Llama-3.3 lags in higher reasoning and robustness, with performance dropping on complex questions.
-
What is (H)CI: Why Does the "Human'' Matter?
A workshop proposal to reflect on HCI's core identity and the importance of human elements in the era of generative AI.
-
Beyond Answers: How LLMs Can Pursue Strategic Thinking in Education
LLMs can improve education by serving as tutors and collaborators that help students develop resolving strategies instead of providing direct solutions.
- Memory in the LLM Era: Modular Architectures and Strategies in a Unified Framework