Kwame 2.0: Human-in-the-Loop Generative AI Teaching Assistant for Large Scale Online Coding Education in Africa

• URL: http://arxiv.org/abs/2603.29159v1
• Date: Tue, 31 Mar 2026 02:19:28 GMT
• Title: Kwame 2.0: Human-in-the-Loop Generative AI Teaching Assistant for Large Scale Online Coding Education in Africa
• Abstract summary: We present Kwame 2.0, a bilingual (English-French) generative AI teaching assistant built using retrieval-augmented generation.<n>We deployed the system in a 15-month longitudinal study spanning 15 cohorts with 3,717 enrollments across 35 African countries.
• Score: 0.548014499873554
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Providing timely and accurate learning support in large-scale online coding courses is challenging, particularly in resource-constrained contexts. We present Kwame 2.0, a bilingual (English-French) generative AI teaching assistant built using retrieval-augmented generation and deployed in a human-in-the-loop forum within SuaCode, an introductory mobile-based coding course for learners across Africa. Kwame 2.0 retrieves relevant course materials and generates context-aware responses while encouraging human oversight and community participation. We deployed the system in a 15-month longitudinal study spanning 15 cohorts with 3,717 enrollments across 35 African countries. Evaluation using community feedback and expert ratings shows that Kwame 2.0 provided high-quality and timely support, achieving high accuracy on curriculum-related questions, while human facilitators and peers effectively mitigated errors, particularly for administrative queries. Our findings demonstrate that human-in-the-loop generative AI systems can combine the scalability and speed of AI with the reliability of human support, offering an effective approach to learning assistance for underrepresented populations in resource-constrained settings at scale.

Related papers

• Closing the Loop: An Instructor-in-the-Loop AI Assistance System for Supporting Student Help-Seeking in Programming Education [21.729610894273563]
  We present a hybrid help framework that integrates AI-generated hints with an escalation mechanism.<n>We observed that out of the total 673 AI-generated hints, students rated 146 (22%) as unhelpful.<n>This finding suggests that when AI support fails, even instructors with expertise may need to pay greater attention to avoid making mistakes.
  arXiv  Detail & Related papers  (2025-10-16T08:57:05Z)
• Training LLM Agents to Empower Humans [67.80021254324294]
  We propose a new approach to tuning assistive language models based on maximizing the human's empowerment.<n>Our empowerment-maximizing method, Empower, only requires offline text data.<n>We show that agents trained with Empower increase the success rate of a simulated human programmer on challenging coding questions by an average of 192%.
  arXiv  Detail & Related papers  (2025-10-15T16:09:33Z)
• Generative AI in Computer Science Education: Accelerating Python Learning with ChatGPT [1.1169959897721926]
  This study evaluates the effectiveness of integrating generative AI, specifically OpenAIs ChatGPT, into a self-paced Python programming module within a sixteen-week professional training course on applied generative AI.
  arXiv  Detail & Related papers  (2025-05-24T03:13:46Z)
• Sakshm AI: Advancing AI-Assisted Coding Education for Engineering Students in India Through Socratic Tutoring and Comprehensive Feedback [1.9841192743072902]
  Existing AI tools for programming education struggle with key challenges, including the lack of Socratic guidance.<n>This study examines 1170 registered participants, analyzing platform logs, engagement trends, and problem-solving behavior to assess Sakshm AI's impact.
  arXiv  Detail & Related papers  (2025-03-16T12:13:29Z)
• ReLearn: Unlearning via Learning for Large Language Models [64.2802606302194]
  We propose ReLearn, a data augmentation and fine-tuning pipeline for effective unlearning.<n>This framework introduces Knowledge Forgetting Rate (KFR) and Knowledge Retention Rate (KRR) to measure knowledge-level preservation.<n>Our experiments show that ReLearn successfully achieves targeted forgetting while preserving high-quality output.
  arXiv  Detail & Related papers  (2025-02-16T16:31:00Z)
• Two-Timescale Model Caching and Resource Allocation for Edge-Enabled AI-Generated Content Services [55.0337199834612]
  Generative AI (GenAI) has emerged as a transformative technology, enabling customized and personalized AI-generated content (AIGC) services. These services require executing GenAI models with billions of parameters, posing significant obstacles to resource-limited wireless edge. We introduce the formulation of joint model caching and resource allocation for AIGC services to balance a trade-off between AIGC quality and latency metrics.
  arXiv  Detail & Related papers  (2024-11-03T07:01:13Z)
• Learning Task Decomposition to Assist Humans in Competitive Programming [90.4846613669734]
  We introduce a novel objective for learning task decomposition, termed value (AssistV)<n>We collect a dataset of human repair experiences on different decomposed solutions.<n>Under 177 hours of human study, our method enables non-experts to solve 33.3% more problems, speeds them up by 3.3x, and empowers them to match unassisted experts.
  arXiv  Detail & Related papers  (2024-06-07T03:27:51Z)
• Leveraging AI to Advance Science and Computing Education across Africa: Challenges, Progress and Opportunities [1.2691047660244332]
  We describe our work developing and deploying AI in Education tools in Africa for science and computing education. SuaCode is an AI-powered app that enables Africans to learn to code using their smartphones. AutoGrad is an automated grading, and feedback tool for graphical and interactive coding assignments. Kwame for Science is a web-based AI teaching assistant that provides instant answers to students' science questions.
  arXiv  Detail & Related papers  (2024-02-12T04:10:09Z)
• Real-World Deployment and Evaluation of Kwame for Science, An AI Teaching Assistant for Science Education in West Africa [0.769672852567215]
  Africa has a high student-to-teacher ratio which limits students' access to teachers for educational question answering. We extended Kwame, a bilingual AI teaching assistant for coding education, adapted it for science education, and deployed it as a web app. We deployed Kwame for Science in the real world over 8 months and had 750 users across 32 countries (15 in Africa) and 1.5K questions asked.
  arXiv  Detail & Related papers  (2023-02-21T16:20:17Z)
• Human Decision Makings on Curriculum Reinforcement Learning with Difficulty Adjustment [52.07473934146584]
  We guide the curriculum reinforcement learning results towards a preferred performance level that is neither too hard nor too easy via learning from the human decision process. Our system is highly parallelizable, making it possible for a human to train large-scale reinforcement learning applications. It shows reinforcement learning performance can successfully adjust in sync with the human desired difficulty level.
  arXiv  Detail & Related papers  (2022-08-04T23:53:51Z)
• Personalized Education in the AI Era: What to Expect Next? [76.37000521334585]
  The objective of personalized learning is to design an effective knowledge acquisition track that matches the learner's strengths and bypasses her weaknesses to meet her desired goal. In recent years, the boost of artificial intelligence (AI) and machine learning (ML) has unfolded novel perspectives to enhance personalized education.
  arXiv  Detail & Related papers  (2021-01-19T12:23:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.