CoChat

Learning to Code with Context: A Study-Based Approach

Open access

The DOI matches its Crossref record; 23 of the 53 references it cites were found in a registry or an index, and 1 are not checked yet; none of the 10 sources its claims cite is checked for support yet.

Abstract

The rapid emergence of generative AI tools is transforming software development. Consequently, software engineering education must adapt to ensure that students not only learn traditional development methods but also understand how to use these new technologies effectively and responsibly. In particular, project-based courses provide an effective setting in which to explore and evaluate the integration of AI assistance into real-world development practices. This paper presents our approach and a user study conducted in the context of a university programming project in which students collaboratively developed computer games. The study investigates how participants used generative AI tools across different phases of the software development process, identifies the tasks for which these tools were perceived as most useful, and analyzes the challenges students encountered. Building on these insights, we further examine a repository-aware, locally deployed large language model (LLM) assistant designed to provide project-contextualized support. The system employs retrieval-augmented generation (RAG) to ground its responses in relevant documentation and source code, thereby enabling a qualitative analysis of model behavior, parameter sensitivity, and common failure modes. These findings deepen our understanding of context-aware AI support in educational software projects and inform the future integration of AI-based assistance into software engineering curricula.

Checked 2026-10-11 · 1 reference not checked yet

Overview

CoChat Summary

## TL;DR

This paper studies AI use in a university programming project and finds that students use generative AI most in coding/testing, but text-heavy tasks benefit more than code comprehension or diagram work. It then shows that a locally deployed, repository-aware RAG assistant can produce more usable, repository-aligned outputs than generic assistants.

## Key findings

  • Among 38 participants, 34 used AI tools during the project, an adoption rate of 89.4%; 4 did not use AI, citing lack of need or personal reservations, and 1 also said they were unaware of the available tools.
  • AI use varied by phase: Preparation 22/38, Analysis 13/38, Design 10/38, and Coding & Testing 33/38; ChatGPT was used by all students who used AI tools, and GitHub Copilot was the next most common tool, especially in coding.
  • In the Preparation phase, comprehension was the most common AI task (n=9), but 6 of those 9 reported “inaccurate results” and 2 reported “missing context.”
  • In the repository-aware assistant evaluation, 42 runs were conducted across 15 sampling configurations and 6 model variants; the repository-aware setup “consistently produced usable, repository-aligned outputs,” and in most runs artifacts were integrated with limited follow-up corrections.
  • For sampling, Hallucination was the most frequent defect, occurring in 14 of 15 runs; the paper says the most stable configuration was T ≈ 0.5, top p = 0, yielding the fewest defects.
  • In the model sweep, every model except Mistral-7B showed at least one marked Hallucination instance; Mistral-7B was described as unsuitable because the run failed to produce complete solutions for both tasks.

## Methods

  • User study: structured questionnaire administered during the final team presentation of a university programming project; 38 participants out of 49 enrolled students participated, and the study asked about AI use across Preparation, Analysis, Design, and Coding & Testing phases plus overall usefulness and future intentions.
  • Case study: repository-aware, locally deployed LLM assistant grounded in project documentation and source code via Retrieval-Augmented Generation (RAG), running on a dedicated on-campus NVIDIA DGX-H100 system with Docker containers.
  • Evaluation: 42 single-run model/task configurations, with 15 sampling configurations and 6 model variants evaluated on 2 representative preparation tasks; outputs were analyzed against a predefined defect catalog.

## Limitations

  • The paper states that the case-study evaluation used a single-run protocol per configuration and task, which constrains reproducibility and the stability of observed effects.
  • The analysis relies on manual coding against a predefined defect catalog, and the paper says the lack of a standardized benchmark introduces subjectivity and potential coder bias.
  • External validity is constrained by only two tasks from a single project, and the paper notes that other architectures or task types may yield different patterns.
  • Evident from the text: the user study is self-reported questionnaire data from one course cohort, so the findings depend on participants’ recollections and perceptions rather than direct observation.

Model-written summary. Check it against the paper before relying on it.

Integrity signals

Registry

Crossref · 10.3390/software5020027

Cites

23 of 53 references verified0 citation errors · 29 not checkable

Statistics

Nothing to recompute.

Verification

Claims the paper makes

0 Valid · 0 Not valid · 10 Not checked · 198 Own results and interpretations

98 more claims

Create a free account to see all 208 claims and to verify the 10 references still open.

See all claims — free account
  • It may state two separate claims as one. 64
  • Probably not a substantial claim. 71

Create a free account to see these claims.

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

Each contradiction between two passages listed here was confirmed by an independent check.

1 of 1

Citations

Cites

  • Perceived usefulness, perceived ease of use, and user acceptance of information technology

    Davis, F. D. (1989) · MIS Quarterly · doi:10.2307/249008 · Cited by 68,483 · cited 1×

    “Its design was informed by the Technology Acceptance Model (TAM) [46], particularly the constructs of perceived usefulness, ease of use, and behavioral intention.”
  • Competition-level code generation with AlphaCode

    Li, Y., Choi, D., Chung, J., Kushman, N., Schrittwieser, J., Leblond, R., Eccles, T., Keeling, J., Gimeno, F., Dal Lago, A., et al. (2022) · Science · doi:10.1126/science.abq1158 · Cited by 1,043 · cited 1×

    “Models such as DeepMind’s A LPHA C ODE [27], Google’s P A LM [28], Microsoft’s C ODE BERT [29], and OpenAI’s C HAT GPT and C ODEX [30] generate syntactically correct and functionally meaningful code from natural-language prompts.”
  • Retrieval-Augmented Generation for Large Language Models: A Survey

    Gao, Y., Xiong, Y., Gao, X., Jia, K., Pan, J., Bi, Y., Dai, Y., Sun, J., Wang, M., & Wang, H. (2023) · arXiv · doi:10.48550/arxiv.2312.10997 · Cited by 876

  • A Survey of Automated Assessment Approaches for Programming Assignments

    Ala-Mutka, K. M. (2005) · Computer Science Education · doi:10.1080/08993400500150747 · Cited by 546

  • Automatic test-based assessment of programming: A review

    Douce, C., Livingstone, D., & Orwell, J. (2005) · Journal on Educational Resources in Computing · doi:10.1145/1163405.1163409 · Cited by 416 · cited 1×

    “The case study therefore sought to determine which LLMs are capable of answering the selected programming queries correctly and to what extent smaller models with fewer parameters can do so.”
  • A survey on deep learning for software engineering

    Yang, Y., Xia, X., Lo, D., & Grundy, J. (2022) · ACM Computing Surveys · doi:10.1145/3505243 · Cited by 223

  • On the Robustness of Code Generation Techniques: An Empirical Study on GitHub Copilot

    Mastropaolo, A., Pascarella, L., Guglielmi, E., Ciniselli, M., Scalabrino, S., Oliveto, R., & Bavota, G. (2023) · 2023 IEEE/ACM 45th International Conference on Software Engineering (ICSE) · doi:10.1109/icse48619.2023.00181 · Cited by 138 · cited 2×

    “The widespread availability of generative AI tools, such as C HAT GPT and GitHub’s C OPILOT [1], is also affecting software development practices.”
  • Using AI-based coding assistants in practice: State of affairs, perceptions, and ways forward

    Sergeyuk, A., Golubev, Y., Bryksin, T., & Ahmed, I. (2025) · Information and Software Technology · doi:10.1016/j.infsof.2024.107610 · Cited by 101 · cited 1×

    “This task-oriented interpretation is consistent with recent findings showing that developers use AI-based coding assistants unevenly across software development activities and stages [49].”
  • Does using artificial intelligence assistance accelerate skill decay and hinder skill development without performers’ awareness?

    Macnamara, B. N., Berber, I., Çavuşoğlu, M. C., Krupinski, E. A., Nallapareddy, N., Nelson, N. E., Smith, P. J., Wilson-Delfosse, A. L., & Ray, S. (2024) · Cognitive Research: Principles and Implications · doi:10.1186/s41235-024-00572-8 · Cited by 97 · cited 1×

    “To mitigate the widely discussed effect of skill degradation [2,3], it will not simply provide complete solutions; instead, like a human tutor, it will offer hints and guide students toward solving problems independently.”
  • Software engineering education in the era of conversational AI: current trends and future directions

    Sengul, C., Neykova, R., & Destefanis, G. (2024) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2024.1436350 · Cited by 83 · cited 1×

    “The case study therefore sought to determine which LLMs are capable of answering the selected programming queries correctly and to what extent smaller models with fewer parameters can do so.”
  • How Far Are We? The Triumphs and Trials of Generative AI in Learning Software Engineering

    Choudhuri, R., Liu, D., Steinmacher, I., Gerosa, M., & Sarma, A. (2024) · Proceedings of the IEEE/ACM 46th International Conference on Software Engineering · doi:10.1145/3597503.3639201 · Cited by 72 · cited 2×

    “Choudhuri et al. [39] report no significant improvements in productivity or self-efficacy when using C HAT - GPT and highlight issues such as incomplete guidance and fabricated responses.”
  • Revolutionizing learning − A journey into educational games with immersive and AI technologies

    Rapaka, A., Dharmadhikari, S. C., Kasat, K., Mohan, C. R., Chouhan, K. S., & Gupta, M. (2024) · Entertainment Computing · doi:10.1016/j.entcom.2024.100809 · Cited by 59 · cited 1×

    “A recent experiment by Rapaka et al. [45] examines two versions of an educational game.”
  • “The case study therefore sought to determine which LLMs are capable of answering the selected programming queries correctly and to what extent smaller models with fewer parameters can do so.”
  • An organizational theory for multi-agent interactions integrating human agents, LLMs, and specialized AI

    Borghoff, U. M., Bottoni, P., & Pareschi, R. (2025) · Discover Computing · doi:10.1007/s10791-025-09667-2 · Cited by 27

    Self-citation
  • Perceived Impact of AI-Based Tooling on Software Development Code Quality

    Martinović, B., & Rozić, R. (2025) · SN Computer Science · doi:10.1007/s42979-024-03608-4 · Cited by 26 · cited 1×

    “The case study therefore sought to determine which LLMs are capable of answering the selected programming queries correctly and to what extent smaller models with fewer parameters can do so.”
  • Artificial Intelligence in Software Engineering: Perspectives and Challenges

    Bhandari, K., Kumar, K., & Sangal, A. L. (2023) · International Conference on Secure Cyber Computing and Communications (ICSCCC) · doi:10.1109/icsccc58608.2023.10176436 · Cited by 24 · cited 1×

    “The case study therefore sought to determine which LLMs are capable of answering the selected programming queries correctly and to what extent smaller models with fewer parameters can do so.”
  • Generative AI: Redefining the Future of Software Engineering

    Carleton, A. D., Falessi, D., Zhang, H., & Xia, X. (2024) · IEEE Software · doi:10.1109/ms.2024.3441889 · Cited by 22 · cited 1×

    “The case study therefore sought to determine which LLMs are capable of answering the selected programming queries correctly and to what extent smaller models with fewer parameters can do so.”
  • The use of artificial intelligence in military intelligence: an experimental investigation of added value in the analysis process

    Nitzl, C., Cyran, A., Krstanovic, S., & Borghoff, U. M. (2025) · Frontiers in Human Dynamics · doi:10.3389/fhumd.2025.1540450 · Cited by 18 · cited 1×

    “The case study therefore sought to determine which LLMs are capable of answering the selected programming queries correctly and to what extent smaller models with fewer parameters can do so.”
    Self-citation
  • Nurturing Code Quality: Leveraging Static Analysis and Large Language Models for Software Quality in Education

    Alomar, E. (2025) · ACM Transactions on Computing Education · doi:10.1145/3722229 · Cited by 17 · cited 1×

    “AlOmar [41] shows that students remain cautious about relying on C HAT GPT for tasks such as code review.”
  • The Potential of Artificial Intelligence as a Method of Software Developer's Productivity Improvement

    Moroz, E. A., Grizkevich, V. O., & Novozhilov, I. M. (2022) · IEEE Conference of Russian Young Researchers in Electrical and Electronic Engineering · doi:10.1109/elconrus54750.2022.9755659 · Cited by 15 · cited 1×

    “Moroz et al. [38] further observe that developers often use these tools to explore multiple solution strategies rather than to obtain a single correct answer.”
  • Influence of Large Language Models on Programming Assignments – A user study

    Piscitelli, A., Costagliola, G., Rosa, M. D., & Fuccella, V. (2024) · International Conference on Education Technology and Computer · doi:10.1145/3702163.3702168 · Cited by 10 · cited 1×

    “The case study therefore sought to determine which LLMs are capable of answering the selected programming queries correctly and to what extent smaller models with fewer parameters can do so.”
  • Beyond Prompt Chaining: The TB-CSPN Architecture for Agentic AIPreprint

    Borghoff, U. M., Bottoni, P., & Pareschi, R. (2025) · Preprints.org · doi:10.20944/preprints202507.1294.v1 · Cited by 4

    Self-citation
  • Encouraging Students’ Responsible Use of GenAI in Software Engineering Education: An Explanatory Model and Two Institutional ApplicationsPreprint

    Garousi, V., Jafarov, Z., Mövsümova, A., Namazov, A., & Mirzayev, H. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5932827 · Cited by 3

  • Deskilling and upskilling with AI systems

    Crowston (2025) · Inf. Res.

    Unresolved
  • Education 4.0 and 5.0: Integrating artificial intelligence (AI) for personalized and adaptive learning

    Rane (2023) · SSRN Electron. J.

    Unresolved
  • Navigating the Complexity of Generative AI Adoption in Software Engineering

    Russo (2024) · ACM Trans. Softw. Eng. Methodol.

    Unresolved
  • Nascimento, N., Alencar, P., and Cowan, D. (2023). Comparing Software Developers with ChatGPT: An Empirical Investigation. arXiv.

    (n.d.)

    Unresolved
  • Kaindl, H., Mannion, M., and Maciaszek, L.A. (2024). ChatGPT as a Software Development Bot: A Project-Based Study. Proceedings of the 19th International Conference on Evaluation of Novel Approaches to Software Engineering, ENASE 2024, Angers, France, 28–29 April 2024, SciTePress.

    (n.d.)

    Unresolved
  • Laakso, M., Monga, M., and Sheard, J. (2023). How ChatGPT Will Change Software Engineering Education. Proceedings of the 2023 Conference on Innovation and Technology in Computer Science Education V. 1, ITiCSE 2023, Turku, Finland, 7–12 July 2023, ACM.

    (n.d.)

    Unresolved
  • Automatic Program Assessment, Grading and Code Generation: Possible AI-Support in a Software Development Course

    Rutkowski (2024) · Proceedings of the Artificial Intelligence and Soft Computing—23rd International Conference, ICAISC 2024, Zakopane, Poland, 16–20 June 2024

    Unresolved
  • Schmidt, A., Väänänen, K., Goyal, T., Kristensson, P.O., Peters, A., Mueller, S., Williamson, J.R., and Wilson, M.L. (2023). Studying the effect of AI Code Generators on Supporting Novice Learners in Introductory Programming. Proceedings of the 2023 CHI Conference on Human Factors in Computing Syste

    (n.d.)

    Unresolved
  • Barnes, T., Garcia, D.D., Hawthorne, E.K., and Pérez-Quiñones, M.A. (2018). ArTEMiS: An Automatic Assessment Management System for Interactive Learning. Proceedings of the 49th ACM Technical Symposium on Computer Science Education, SIGCSE 2018, Baltimore, MD, USA, 21–24 February 2018, ACM.

    (n.d.)

    Unresolved
  • Automatic Grading of Computer Programs: A Machine Learning Approach

    Srikant (2013) · Proceedings of the 2013 12th International Conference on Machine Learning and Applications, Miami, FL, USA, 4–7 December 2013

    Unresolved
  • A fuzzy-based mechanism for automatic personalized assessment in an e-learning system for computer programming

    Chrysafiadi (2022) · Intell. Decis. Technol.

    Unresolved
  • Automatic Assessment of Learning Outcomes as a New Paradigm in Teaching a Programming Course: Engineering in Society 5.0

    Bucheli (2022) · Rev. Iberoam. Tecnol. Aprendiz.

    Unresolved
  • PaLM: Scaling Language Modeling with Pathways

    Chowdhery (2023) · J. Mach. Learn. Res.

    Unresolved
  • CodeBERT: A Pre-Trained Model for Programming and Natural Languages

    Cohn (2020) · Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2020, Online Event, 16–20 November 2020

    Unresolved
  • Sheard, J., and Denny, P. (2022). The Robots Are Coming: Exploring the Implications of OpenAI Codex on Introductory Programming. Proceedings of the ACE ’22: Australasian Computing Education Conference, Virtual Event, Australia, 14–18 February 2022, ACM.

    (n.d.)

    Unresolved
  • Gao, Y., Xiong, Y., Gao, X., Jia, K., Pan, J., Bi, Y., Dai, Y., Sun, J., Wang, M., and Wang, H. (2024). Retrieval-Augmented Generation for Large Language Models: A Survey. arXiv.

    (n.d.)

    Unresolved
  • Al-Onaizan, Y., Bansal, M., and Chen, Y. (2024). Fine-Tuning or Retrieval? Comparing Knowledge Injection in LLMs. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024, Miami, FL, USA, 12–16 November 2024, Association for Computational Linguistics.

    (n.d.)

    Unresolved
  • Huang, Y., and Huang, J. (2024). A Survey on Retrieval-Augmented Text Generation for Large Language Models. arXiv.

    (n.d.)

    Unresolved
  • Ni, B., Liu, Z., Wang, L., Lei, Y., Zhao, Y., Cheng, X., Zeng, Q., Dong, L., Xia, Y., and Kenthapadi, K. (2025). Towards Trustworthy Retrieval Augmented Generation for Large Language Models: A Survey. arXiv.

    (n.d.)

    Unresolved
  • Shahriar, H., Alam, K., Ohsaki, H., Cimato, S., Capretz, M., Ahmed, S., Ahamed, S., Majumder, A., Haque, M., and Yoshihisa, T. (2025). Designing Reusable LLM-Enhanced Assignments: A Quality-Oriented Framework for Software Engineering Education. Proceedings of the 49th IEEE Annual Computers, Software

    (n.d.)

    Unresolved
  • Choppella, V., Karkare, A., Babu, C., and Chimalakonda, S. (2022). Programming Pedagogy and Assessment in the Era of AI/ML: A Position Paper. Proceedings of the COMPUTE 2022, Jaipur, India, 9–11 November 2022, ACM.

    (n.d.)

    Unresolved
  • Scharlau, B., McDermott, R., Pears, A., and Sabin, M. (2019). Fostering Program Comprehension in Novice Programmers—Learning Activities and Learning Trajectories. Proceedings of the Working Group Reports on Innovation and Technology in Computer Science Education, ITiCSE-WGR 2019, Aberdeen, Scotland,

    (n.d.)

    Unresolved
  • Pudari, R., and Ernst, N.A. (2023). From Copilot to Pilot: Towards AI Supported Software Development. arXiv.

    (n.d.)

    Unresolved
  • Generative artificial intelligence-supported programming education: Effects on learning performance, self-efficacy and processes

    Li (2025) · Australas. J. Educ. Technol.

    Unresolved
  • Mottok, J. (2023). Using Automatic Program Assessment in a Software Development Project Course. Proceedings of the 5th European Conference on Software Engineering Education, ECSEE 2023, Seeon/Bavaria, Germany, 19–21 June 2023, ACM.

    (n.d.)

    Unresolved
  • A cookbook for using model-view-controller user interface paradigmin smalltalk-80

    Krasner (1988) · J. Object-Oriented Program.

    Unresolved
  • Mottok, J., and Hagel, G. (2025). Generative AI in Student Software Development Projects: A User Study on Experiences and Self-Assessment. Proceedings of the 6th European Conference on Software Engineering Education, ECSEE 2025, Seeon/Bavaria, Germany, 2–4 June 2025, ACM.

    (n.d.)

    Unresolved
  • Coman, A., and Vasilache, S. (2025). Generative Artificial Intelligence in Agile Software Development Processes: A Literature Review Focused on User eXperience. Proceedings of the Social Computing and Social Media, Springer.

    (n.d.)

    Unresolved
  • Dobrovsky, A., Hofmann, M., and Borghoff, U.M. (2026). The Adoption Gap in Adaptive Learning Path Generation: An Analytical Review of Barriers and Operational Requirements. Front. Comput. Sci., 8, accepted.

    (n.d.)

    Unresolved

Research works printed but not linked: 1

  1. Borghoff, U.M., Minas, M., and Schopp, J. (2025). Learning to Code with Context: A Study-Based Approach. arXiv.

Metadata

Authors
Borghoff, U. M., Minas, M., & Schopp, J.
Affiliations
Universität der Bundeswehr München (DE)
Corresponding author
Borghoff, Uwe M.
Venue
Software
Publisher
MDPI AG
Published
2026-06-21
Volume
5
Issue
2
Pages
27
ISSN
2674-113X (ISSN-L)
OpenAlex
W4417142121
Cited by
0
References
52
FWCI
0.00
Type
journal article
Language
en
Open access
Locations
  • Software (publishedVersion, cc-by)
  • arXiv (Cornell University) (submittedVersion, cc-by)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion)
  • arXiv (Cornell University) (cc-by)
Topics
  • Physical Sciences › Computer Science › Computer Science Applications › Teaching and Learning Programming
  • Physical Sciences › Computer Science › Information Systems › Software Engineering Research
  • Social Sciences › Education › Artificial Intelligence in Education
Keywords
generative AI in software development, large language models, retrieval-augmented generation, AI-assisted programming, software engineering education, project-based learning, game development, student perceptions of AI tools, AI failure modes, parameter sensitivity

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

A language model drew the claims from the paper on 2026-10-11, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).

A second model labelled each claim on 2026-10-11 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.