Comprehension Debt in GenAI-Assisted Software Engineering Projects

• URL: http://arxiv.org/abs/2604.13277v1
• Date: Tue, 14 Apr 2026 20:14:26 GMT
• Title: Comprehension Debt in GenAI-Assisted Software Engineering Projects
• Abstract summary: This study investigates how GenAI tools contribute to Debt (CD) in the context of an undergraduate software engineering project.<n>We identify four CD accumulation patterns and one mitigating pattern in students' use of GenAI tools.<n>Our findings highlight the need for explicit pedagogical strategies to CD in software engineering education.
• Score: 1.1844977816228044
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Generative Artificial Intelligence (GenAI) tools (e.g., ChatGPT, Calude) have rapidly become integral to software development. These tools are especially attractive to students, as they can reduce cognitive load. However, their adoption also introduces a socio-cognitive risk: the accumulation of Comprehension Debt (CD). CD refers to the growing gap between what a development team knows about its codebase and what it actually needs to understand in order to maintain and modify it effectively. This qualitative study investigate how GenAI tools contribute to CD in the context of an undergraduate software engineering project. Our study is based on 621 reflective diaries from 207 students over eight weeks. We identify four CD accumulation patterns and one mitigating pattern in students' use of GenAI tools. The four accumulation patterns include: (1) AI-as-black-box code acceptance, (2) context-mismatch debt, (3) dependency-induced atrophy, and (4) verification-bypass. In contrast, the mitigating pattern involves students using GenAI as a comprehension scaffold, allowing them to build a deeper understanding of the code. We argue that CD is distinct from traditional technical debt because it resides in the collective cognition of development teams rather than in the codebase itself. Our findings highlight the need for explicit pedagogical strategies to mitigate CD in software engineering education, emphasizing verification practices, structured retrospectives, and active learning assessments.

Related papers

• On Automated and Explainable Provenance of AI-Generated Code [56.818202904805446]
  We argue that the next generation of CodeGenAI tools must be built on a foundation of explainable provenance.<n>We describe a research program combining large-scale empirical studies with post-hoc causal and interpretability techniques.
  arXiv  Detail & Related papers  (2026-08-03T14:50:31Z)
• Quick Build, Careful Check? Generative AI Use in Hackathons [83.0493885475068]
  We report an exploratory interview study with participants at an AI-themed hackathon in central Europe.<n>We found that participants used GenAI for purposes beyond coding, including learning unfamiliar topics, brainstorming, and preparing documentation.<n>We also found that all participants converged on an unwritten practice of checking GenAI output before using it, yet their ability to actually verify was constrained by time pressure and limited domain knowledge.
  arXiv  Detail & Related papers  (2026-07-31T08:59:18Z)
• Patterns of Learner-AI Interaction and Academic Performance in an Object-Oriented Programming Course [0.0]
  This research paper examines how different forms of learner-AI interaction relate to learning outcomes in object-oriented programming (OOP) courses.<n>Survey data were collected from 210 undergraduate students enrolled in a first-year OOP course.
  arXiv  Detail & Related papers  (2026-05-26T07:48:00Z)
• Reshaping Undergraduate Computer Science Education in the Generative AI Era [85.78707817763434]
  Generative AI represents a turning point for Computer Science (CS) education.<n>To keep pace with advances in AI technology, CS curricula should consider a shift toward understanding and verifying AI-generated artifacts.<n>We believe that to effectively prepare future computer science graduates, capable of creating, solving problems, and managing, as well as co-creating, artifacts with AI.
  arXiv  Detail & Related papers  (2026-05-02T05:26:24Z)
• On the Role and Impact of GenAI Tools in Software Engineering Education [2.867517731896504]
  generative AI (GenAI) tools like ChatGPT and GitHub Copilot have transformed how software is learned and written.<n>In software engineering (SE) education, these tools offer new opportunities for support, but also raise concerns about over-reliance, ethical use, and impacts on learning.<n>This study investigates how undergraduate SE students use GenAI tools, focusing on the benefits, challenges, ethical concerns, and instructional expectations that shape their experiences.
  arXiv  Detail & Related papers  (2025-12-03T20:51:16Z)
• "Can you feel the vibes?": An exploration of novice programmer engagement with vibe coding [42.82674998306379]
  "vibe coding" refers to creating software via natural language prompts rather than direct code authorship.<n>This paper reports on a one-day educational hackathon investigating how novice programmers and mixed-experience teams engage with vibe coding.
  arXiv  Detail & Related papers  (2025-12-02T13:32:23Z)
• A Systematic Literature Review of the Use of GenAI Assistants for Code Comprehension: Implications for Computing Education Research and Practice [0.45880283710344066]
  We present a systematic literature review of approaches and tools that leverage generative artificial intelligence (GenAI) to enhance code comprehension.<n>Our review classifies GenAI-based approaches and tools, identifies methods used to study them, and summarizes the empirical evaluations of their effectiveness.
  arXiv  Detail & Related papers  (2025-10-19T01:01:49Z)
• Using Generative AI in Software Design Education: An Experience Report [0.6827423171182154]
  Students were required to use GenAI to help complete a team-based assignment.<n>Students identified numerous ways ChatGPT helped them in their design process.<n>We identified several key lessons for educators in how to deploy GenAI in a software design class effectively.
  arXiv  Detail & Related papers  (2025-06-26T18:40:16Z)
• Encouraging Students' Responsible Use of GenAI in Software Engineering Education: A Causal Model and Two Institutional Applications [0.4306143768014156]
  As generative AI (GenAI) tools become pervasive in education, concerns are rising about students using them to complete rather than learn.<n>This paper proposes and empirically applies a causal model to help educators scaffold responsible GenAI use in Software Engineering (SE) education.
  arXiv  Detail & Related papers  (2025-05-31T19:27:40Z)
• From Recall to Reasoning: Automated Question Generation for Deeper Math Learning through Large Language Models [44.99833362998488]
  We investigated the first steps for optimizing content creation for advanced math.<n>We looked at the ability of GenAI to produce high-quality practice problems that are relevant to the course content.
  arXiv  Detail & Related papers  (2025-05-17T08:30:10Z)
• Formal Mathematical Reasoning: A New Frontier in AI [60.26950681543385]
  We advocate for formal mathematical reasoning and argue that it is indispensable for advancing AI4Math to the next level.<n>We summarize existing progress, discuss open challenges, and envision critical milestones to measure future success.
  arXiv  Detail & Related papers  (2024-12-20T17:19:24Z)
• Genetic Auto-prompt Learning for Pre-trained Code Intelligence Language Models [54.58108387797138]
  We investigate the effectiveness of prompt learning in code intelligence tasks. Existing automatic prompt design methods are very limited to code intelligence tasks. We propose Genetic Auto Prompt (GenAP) which utilizes an elaborate genetic algorithm to automatically design prompts.
  arXiv  Detail & Related papers  (2024-03-20T13:37:00Z)
• Knowledge Infused Decoding [46.09844215234235]
  Knowledge Infused Decoding (KID) is a novel decoding algorithm for generative language models (LMs) KID dynamically infuses external knowledge into each step of the LM decoding. Human evaluation confirms KID's ability to generate more relevant and factual language for the input context.
  arXiv  Detail & Related papers  (2022-04-06T20:58:32Z)
• Investigating Explainability of Generative AI for Code through Scenario-based Design [44.44517254181818]
  generative AI (GenAI) technologies are maturing and being applied to application domains such as software engineering. We conduct 9 workshops with 43 software engineers in which real examples from state-of-the-art generative AI models were used to elicit users' explainability needs. Our work explores explainability needs for GenAI for code and demonstrates how human-centered approaches can drive the technical development of XAI in novel domains.
  arXiv  Detail & Related papers  (2022-02-10T08:52:39Z)

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.