When AI Is Wrong on Purpose: How Students Respond to Buggy GenAI Code

• URL: http://arxiv.org/abs/2607.05068v1
• Date: Mon, 06 Jul 2026 13:36:05 GMT
• Title: When AI Is Wrong on Purpose: How Students Respond to Buggy GenAI Code
• Abstract summary: We investigate how prompt-centered programming activities can be adapted to better foster these practices.<n>Specifically, we explore an approach where realistic, runnable bugs are injected into otherwise correct solutions.
• Score: 18.653714524727153
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: As Generative AI (GenAI) becomes increasingly central to software development, CS education is integrating prompt-centered workflows where students describe intended program behavior in natural language to elicit code. However, professional practice requires careful review and verification of GenAI-generated code that may appear correct while containing subtle faults. This creates a challenge for CS1-level activities, where current models often solve tasks correctly and reduce students' incentive to closely inspect generated outputs. We investigate how prompt-centered programming activities can be adapted to better foster these practices. Specifically, we explore an approach where realistic, runnable bugs are injected into otherwise correct solutions, thus requiring students to read and repair generated outputs. We analyzed 2,636 sessions from 917 students, and examined behavior across instances of naturally occurring prompt-related failures and deliberately injected bugs within each session. Our findings show that students responded differently across bug sources. Deliberately injected bugs more often led to direct code edits and higher next-attempt success, suggesting localized repair of near-miss solutions. Prompt-related failures instead more often led students to refine prompts by clarifying constraints, updating function signatures, adding edge cases, or reframing the task. Student reflections reinforce the emphasis on review and repair, describing useful practice in code understanding, code review, and debugging, as well as a more careful verification mindset and greater awareness of GenAI limitations. Ultimately, prompt-related failures and injected bugs together support a pedagogically useful GenAI workflow, where students practice both specification refinement through prompts and debugging through code editing.

Related papers

• Understanding Student Perceptions, Mistakes, and Debugging Approaches when Solving Natural Language Programming Tasks [18.517538299978465]
  We studied attempts by more than 900 students to solve dialogue-based Prompt Problems.<n>Compared to traditional coding tasks, students found prompting easier, more enjoyable, and better targeted at developing problem-solving skills.<n>The most common mistakes are related to the omission of key details, suggesting both a failure to acknowledge their importance and over-reliance on AI to infer them.
  arXiv  Detail & Related papers  (2026-07-06T13:16:39Z)
• Interleaving Natural Language Prompting with Code Editing for Solving Programming Tasks with Generative AI Models [20.071141463392813]
  Students often rely on natural-language prompting and manual code editing to solve programming tasks.<n>We investigate how these two modes are combined in practice, and how their usage varies with task complexity and student ability.<n>Our analysis shows that students primarily use prompting to generate initial solutions, and then often enter short edit-run loops to refine their code following a failed execution.
  arXiv  Detail & Related papers  (2025-09-17T15:32:19Z)
• Do AI models help produce verified bug fixes? [62.985237003585674]
  Large Language Models are used to produce corrections to software bugs.<n>This paper investigates how programmers use Large Language Models to complement their own skills.<n>The results are a first step towards a proper role for AI and LLMs in providing guaranteed-correct fixes to program bugs.
  arXiv  Detail & Related papers  (2025-07-21T17:30:16Z)
• Learning Code-Edit Embedding to Model Student Debugging Behavior [2.1485350418225244]
  We propose an encoder-decoder-based model that learns meaningful code-edit embeddings between consecutive student code submissions.<n>It enables personalized next-step code suggestions that maintain the student's coding style while improving test case correctness.
  arXiv  Detail & Related papers  (2025-02-26T18:54:39Z)
• BugSpotter: Automated Generation of Code Debugging Exercises [22.204802715829615]
  This paper introduces BugSpotter, a tool to generate buggy code from a problem description and verify the synthesized bugs via a test suite. Students interact with BugSpotter by designing failing test cases, where the buggy code's output differs from the expected result as defined by the problem specification.
  arXiv  Detail & Related papers  (2024-11-21T16:56:33Z)
• Stepwise Verification and Remediation of Student Reasoning Errors with Large Language Model Tutors [78.53699244846285]
  Large language models (LLMs) present an opportunity to scale high-quality personalized education to all. LLMs struggle to precisely detect student's errors and tailor their feedback to these errors. Inspired by real-world teaching practice where teachers identify student errors and customize their response based on them, we focus on verifying student solutions.
  arXiv  Detail & Related papers  (2024-07-12T10:11:40Z)
• LLM Critics Help Catch Bugs in Mathematics: Towards a Better Mathematical Verifier with Natural Language Feedback [71.95402654982095]
  We propose Math-Minos, a natural language feedback-enhanced verifier. Our experiments reveal that a small set of natural language feedback can significantly boost the performance of the verifier.
  arXiv  Detail & Related papers  (2024-06-20T06:42:27Z)
• The Widening Gap: The Benefits and Harms of Generative AI for Novice Programmers [1.995977018536036]
  Novice programmers often struggle through programming problem solving due to a lack of metacognitive awareness and strategies. Many novices are now programming with generative AI (GenAI) Our findings show an unfortunate divide in the use of GenAI tools between students who accelerated and students who struggled.
  arXiv  Detail & Related papers  (2024-05-28T01:48:28Z)
• 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)
• Generation Probabilities Are Not Enough: Uncertainty Highlighting in AI Code Completions [54.55334589363247]
  We study whether conveying information about uncertainty enables programmers to more quickly and accurately produce code. We find that highlighting tokens with the highest predicted likelihood of being edited leads to faster task completion and more targeted edits.
  arXiv  Detail & Related papers  (2023-02-14T18:43:34Z)
• ProtoTransformer: A Meta-Learning Approach to Providing Student Feedback [54.142719510638614]
  In this paper, we frame the problem of providing feedback as few-shot classification. A meta-learner adapts to give feedback to student code on a new programming question from just a few examples by instructors. Our approach was successfully deployed to deliver feedback to 16,000 student exam-solutions in a programming course offered by a tier 1 university.
  arXiv  Detail & Related papers  (2021-07-23T22:41:28Z)

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.