Interleaving Natural Language Prompting with Code Editing for Solving Programming Tasks with Generative AI Models

• URL: http://arxiv.org/abs/2509.14088v1
• Date: Wed, 17 Sep 2025 15:32:19 GMT
• Title: Interleaving Natural Language Prompting with Code Editing for Solving Programming Tasks with Generative AI Models
• Authors: Victor-Alexandru Pădurean, Paul Denny, Andrew Luxton-Reilly, Alkis Gotovos, Adish Singla,
• Abstract summary: 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.
• Score: 20.071141463392813
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Nowadays, computing students often rely on both natural-language prompting and manual code editing to solve programming tasks. Yet we still lack a clear understanding of how these two modes are combined in practice, and how their usage varies with task complexity and student ability. In this paper, we investigate this through a large-scale study in an introductory programming course, collecting 13,305 interactions from 355 students during a three-day laboratory activity. 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. We find that manual editing becomes more frequent as task complexity increases, but most edits remain concise, with many affecting a single line of code. Higher-performing students tend to succeed using prompting alone, while lower-performing students rely more on edits. Student reflections confirm that prompting is helpful for structuring solutions, editing is effective for making targeted corrections, while both are useful for learning. These findings highlight the role of manual editing as a deliberate last-mile repair strategy, complementing prompting in AI-assisted programming workflows.

Related papers

• DebugTA: An LLM-Based Agent for Simplifying Debugging and Teaching in Programming Education [32.673843958049254]
  In programming and Teaching (DT) task, students receive assistance in correcting their erroneous code.<n>We propose DebugTA, a novel teaching agent with specialized tools for standard code retrieval, variable substitution to align reference code, and an external compiler for real-time code analysis.<n>We show that DebugTA consistently improves teaching effectiveness while significantly reducing computational costs.
  arXiv  Detail & Related papers  (2025-10-13T07:17:18Z)
• Exploring Direct Instruction and Summary-Mediated Prompting in LLM-Assisted Code Modification [10.964060011243234]
  This paper presents a study of using large language models (LLMs) in modifying existing code.<n>"prompting" serves as the primary interface for developers to communicate intents to LLMs.<n>This study investigates two prompting strategies for LLM-assisted code modification.
  arXiv  Detail & Related papers  (2025-08-02T23:52:49Z)
• Grammar-Guided Evolutionary Search for Discrete Prompt Optimisation [63.97051732013936]
  We propose an evolutionary search approach to automated discrete prompt optimisation consisting of two phases.<n>In the first phase, grammar-guided genetic programming is invoked to synthesise prompt-creating programmes.<n>In the second phase, local search is applied to explore the neighbourhoods of best-performing programmes.
  arXiv  Detail & Related papers  (2025-07-14T14:34:15Z)
• Integrating Natural Language Prompting Tasks in Introductory Programming Courses [3.907735250728617]
  This report explores the inclusion of two prompt-focused activities in an introductory programming course. The first requires students to solve computational problems by writing natural language prompts, emphasizing problem-solving over syntax. The second involves students crafting prompts to generate code equivalent to provided fragments, to foster an understanding of the relationship between prompts and code.
  arXiv  Detail & Related papers  (2024-10-04T01:03:25Z)
• KIWI: A Dataset of Knowledge-Intensive Writing Instructions for Answering Research Questions [63.307317584926146]
  Large language models (LLMs) adapted to follow user instructions are now widely deployed as conversational agents. In this work, we examine one increasingly common instruction-following task: providing writing assistance to compose a long-form answer. We construct KIWI, a dataset of knowledge-intensive writing instructions in the scientific domain.
  arXiv  Detail & Related papers  (2024-03-06T17:16:44Z)
• InstructEdit: Instruction-based Knowledge Editing for Large Language Models [39.2147118489123]
  We develop an instruction-based editing technique, termed InstructEdit, which facilitates the editor's adaptation to various task performances simultaneously using simple instructions. Experiments involving holdout unseen task illustrate that InstructEdit consistently surpass previous strong baselines.
  arXiv  Detail & Related papers  (2024-02-25T15:46:33Z)
• On the Robustness of Editing Large Language Models [57.477943944826904]
  Large language models (LLMs) have played a pivotal role in building communicative AI, yet they encounter the challenge of efficient updates. This work seeks to understand the strengths and limitations of editing methods, facilitating practical applications of communicative AI.
  arXiv  Detail & Related papers  (2024-02-08T17:06:45Z)
• TEMPERA: Test-Time Prompting via Reinforcement Learning [57.48657629588436]
  We propose Test-time Prompt Editing using Reinforcement learning (TEMPERA) In contrast to prior prompt generation methods, TEMPERA can efficiently leverage prior knowledge. Our method achieves 5.33x on average improvement in sample efficiency when compared to the traditional fine-tuning methods.
  arXiv  Detail & Related papers  (2022-11-21T22:38:20Z)
• CINS: Comprehensive Instruction for Few-shot Learning in Task-oriented Dialog Systems [56.302581679816775]
  This paper proposes Comprehensive Instruction (CINS) that exploits PLMs with task-specific instructions. We design a schema (definition, constraint, prompt) of instructions and their customized realizations for three important downstream tasks in ToD. Experiments are conducted on these ToD tasks in realistic few-shot learning scenarios with small validation data.
  arXiv  Detail & Related papers  (2021-09-10T03:23:06Z)
• 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.