pith. machine review for the scientific record. sign in

arxiv: 2604.24373 · v1 · submitted 2026-04-27 · 💻 cs.SE

Recognition: unknown

Exploring Creativity in Human-Human-LLM Collaborative Software Design

Victoria Jackson , Grischa Liebel , Rafael Prikladnicki , Andre van der Hoek
Authors on Pith no claims yet

Pith reviewed 2026-05-08 03:29 UTC · model grok-4.3

classification 💻 cs.SE
keywords software designcreativitylarge language modelshuman-AI collaborationcollaborative designdesign processesLLM support
0
0 comments X

The pith

LLMs generate novel ideas in software design but humans drive creativity through experience, empathy, and intentional use.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper studies how creativity shows up when pairs of software designers collaborate on a design task with optional access to an LLM. In the 90-minute lab exercise with 18 pairs of professionals, creativity appeared in every group's process and in most final documents. Humans supplied the main creative force via their background knowledge, ability to empathize with users, and analogies, while the LLM mostly supplied fresh ideas or filled out existing ones. Sometimes the LLM pushed designs toward unnecessary complexity or off-track discussions. The work indicates that LLMs can help creative design work only when people deliberately steer the interaction rather than treat the model as an equal partner.

Core claim

Across all 18 observed pairs, creativity emerged naturally during the design process without any priming to be creative. Thirteen pairs produced design documents judged to contain creative elements. The authors trace most of this creativity to human designers drawing on prior experience, empathy for stakeholders, and analogical thinking. The LLM contributed by offering new ideas and expanding on human suggestions, yet in several cases it also introduced overly elaborate proposals or prolonged unproductive side paths. The central conclusion is that LLMs can augment collaborative software design creativity provided the human participants remain intentional about how and when they consult the模型

What carries the argument

Observation of idea generation and attribution during human-human-LLM design sessions, distinguishing human-sourced creativity (experience, empathy, analogies) from LLM-sourced contributions (novel ideas, elaboration) and LLM hindrances (complexity, digressions).

If this is right

  • Design teams should treat LLMs as idea generators rather than primary creators and actively decide when to query them.
  • Professional training could include explicit practice in prompting LLMs to stay aligned with human creative direction.
  • Tool builders may need interfaces that make clear which ideas came from the LLM so humans can evaluate and steer them.
  • In longer projects, periodic human-only reflection sessions could counteract any LLM-induced digressions observed in the lab.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • Interface designers might add simple attribution tags or confidence signals so teams can quickly separate human and model contributions.
  • The same patterns could apply to other creative collaborative domains such as product management or architectural sketching.
  • If intentional use proves learnable, curricula for software engineering students could incorporate short modules on effective LLM collaboration during design.

Load-bearing premise

A short laboratory session with a custom LLM interface and unprimed participants captures the same creativity dynamics that occur in real, extended software design projects.

What would settle it

A follow-up study in actual company settings that measures creativity metrics in teams that never use LLMs versus teams that do, and finds no difference or a negative effect when intentional engagement strategies are absent.

Figures

Figures reproduced from arXiv: 2604.24373 by Andre van der Hoek, Grischa Liebel, Rafael Prikladnicki, Victoria Jackson.

Figure 1
Figure 1. Figure 1: Number of creative elements included in the design view at source ↗
read the original abstract

While the use of Large Language Models (LLMs) in programming has been extensively studied, there is limited understanding of how LLMs support collaborative work where creativity plays a central role. Software design, as a collaborative and creative activity, provides a valuable context for exploring the influence of LLMs on creativity. This study investigates how and where creativity naturally emerges when software designers collaborate with an LLM during a design task. In a laboratory setting simulating a workplace environment, 18 pairs of software professionals with design experience were asked to complete a design task. Each pair had 90 minutes to produce a software design based on a set of requirements, with optional access to a custom LLM interface. Pairs were not primed to be creative. We find that creativity was present in all pairs in design processes, with 13 producing design documents containing creativity. We primarily attribute creativity to the human designers, driven by traits such as prior experience, empathy, and the use of analogies. The LLM contributed by producing novel ideas and elaborating human ideas. However, in some cases, the LLM appeared to hinder creativity by suggesting complex solutions or adding to unproductive digressions. LLMs can support creativity in collaborative software design, but human insights remain central. To effectively augment human creativity, designers must be intentional in their engagement with LLMs.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

3 major / 2 minor

Summary. The paper reports a qualitative laboratory study in which 18 pairs of software professionals with design experience completed a 90-minute collaborative software design task with optional access to a custom LLM interface. Participants were not primed to be creative. The authors observe that creativity appeared in the design processes of all pairs and in the final design documents of 13 pairs, attributing it primarily to human traits such as prior experience, empathy, and analogy use, while noting that the LLM sometimes contributed novel ideas and sometimes hindered progress through overly complex suggestions or digressions. The central conclusion is that LLMs can support creativity in collaborative software design but human insights remain central, and that designers must engage intentionally with LLMs to augment creativity effectively.

Significance. If the qualitative observations hold, the work supplies one of the first empirical accounts of LLM involvement in creative, collaborative software design—an under-studied intersection of SE and HCI. The documented patterns of both helpful and hindering LLM behaviors, together with the emphasis on human-driven creativity, provide concrete starting points for tool designers and for subsequent controlled experiments that could test the intentional-engagement hypothesis.

major comments (3)
  1. [Abstract and §5] Abstract and §5 (Discussion/Conclusion): The prescriptive claim that 'designers must be intentional in their engagement with LLMs' to augment creativity is not supported by the experimental design. The study employed a single unprimed condition with optional LLM access and no baseline (no-LLM) arm or manipulation of engagement style; therefore the step from observed hindrance cases to a causal or prescriptive recommendation remains post-hoc interpretation rather than a tested contrast.
  2. [§3] §3 (Method): No coding scheme, decision rules, or inter-rater reliability statistics are reported for the identification of 'creativity' in design processes and documents. The key quantitative claims—creativity present in all 18 pairs and in 13 final documents—therefore cannot be evaluated for reproducibility or robustness.
  3. [§4] §4 (Findings): The attribution of creativity primarily to human traits (experience, empathy, analogies) versus LLM contributions is presented without a systematic contrast or coding that distinguishes the two sources; this weakens the central claim that human insights 'remain central.'
minor comments (2)
  1. [§3] The 90-minute laboratory task with a custom interface is described only at a high level; a clearer account of task realism, participant briefing, and how the optional LLM was presented would help readers assess ecological validity.
  2. [§6] The paper would benefit from an explicit limitations subsection that directly addresses the absence of a no-LLM baseline and the single-condition design.

Simulated Author's Rebuttal

3 responses · 0 unresolved

We thank the referee for the constructive and detailed feedback. The comments help clarify the boundaries of our exploratory qualitative study and improve transparency in reporting. We address each major comment below, indicating planned revisions where appropriate.

read point-by-point responses

  1. Referee: [Abstract and §5] Abstract and §5 (Discussion/Conclusion): The prescriptive claim that 'designers must be intentional in their engagement with LLMs' to augment creativity is not supported by the experimental design. The study employed a single unprimed condition with optional LLM access and no baseline (no-LLM) arm or manipulation of engagement style; therefore the step from observed hindrance cases to a causal or prescriptive recommendation remains post-hoc interpretation rather than a tested contrast.

    Authors: We agree that the study design is observational and exploratory, consisting of a single condition without a no-LLM baseline or experimental manipulation of engagement style. The language in the abstract and §5 regarding intentional engagement derives from post-hoc patterns in the qualitative data, such as participants who actively directed the LLM toward specific needs versus cases of passive acceptance leading to overly complex or digressive suggestions. We acknowledge this does not provide causal evidence. We will revise the abstract and §5 to reframe the statement as an observation-based suggestion for designers and a hypothesis warranting future controlled studies, rather than a prescriptive requirement. revision: partial

  2. Referee: [§3] §3 (Method): No coding scheme, decision rules, or inter-rater reliability statistics are reported for the identification of 'creativity' in design processes and documents. The key quantitative claims—creativity present in all 18 pairs and in 13 final documents—therefore cannot be evaluated for reproducibility or robustness.

    Authors: This is a fair critique for enhancing methodological transparency in qualitative work. We will expand §3 to describe the coding scheme in detail: creativity was operationalized drawing on definitions emphasizing novelty and usefulness in the context of the design task. For processes, we coded session transcripts and recordings for instances where pairs generated ideas that reframed requirements or introduced non-obvious solutions. For documents, we assessed final outputs against the provided requirements for elements exceeding standard functional decomposition. Decision rules specified that a pair exhibited creativity if at least one clear instance appeared in the process or document. Analysis was conducted by two researchers who reviewed materials independently and resolved discrepancies through discussion to reach consensus. We will explicitly report this process and include example excerpts to allow evaluation of the claims. revision: yes

  3. Referee: [§4] §4 (Findings): The attribution of creativity primarily to human traits (experience, empathy, analogies) versus LLM contributions is presented without a systematic contrast or coding that distinguishes the two sources; this weakens the central claim that human insights 'remain central.'

    Authors: We value this observation for strengthening the central argument. While our thematic analysis involved tracing idea origins during collaborative sessions—distinguishing human-initiated elements (e.g., analogies drawn from prior experience or empathetic consideration of user needs) from LLM-suggested ones—we agree that a more explicit, systematic contrast is warranted. In revision, we will augment §4 with additional coding categories and a summary table or breakdown showing the distribution of creative contributions by source, supported by representative quotes. This will more clearly illustrate how human traits drove integration and advancement of ideas, with the LLM playing a supplementary role in most cases. revision: partial

Circularity Check

0 steps flagged

No circularity in qualitative empirical study

full rationale

This paper reports a qualitative laboratory study with 18 designer pairs completing a 90-minute design task under optional LLM access. Creativity observations, LLM contributions, and hindrances are presented as direct empirical findings from session data and post-task analysis, with no equations, fitted parameters, derivations, or self-referential definitions. The conclusion that designers must be intentional follows interpretively from observed patterns rather than reducing to an input by construction, and no self-citation chains, uniqueness theorems, or ansatz smuggling appear in the reported chain. The study is self-contained as an observational report against external benchmarks of real-world design.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

The claims rest on qualitative interpretation of observed behaviors and artifacts in a controlled lab setting, assuming creativity can be identified and attributed without a formal definition provided in the abstract.

axioms (1)
  • domain assumption Creativity can be reliably identified and attributed to human or LLM contributions in design processes and documents
    The study reaches conclusions on sources of creativity without detailing a formal definition or validation of the attribution approach.

pith-pipeline@v0.9.0 · 5535 in / 1250 out tokens · 88134 ms · 2026-05-08T03:29:54.934292+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

62 extracted references · 36 canonical work pages · 1 internal anchor

  1. [1]

    Aamir Amin, Shuib Basri, Mobashar Rehman, Luiz Fernando Capretz, Rehan Akbar, Abdul Rehman Gilal, and Muhammad Farooq Shabbir. 2020. The impact of personality traits and knowledge collection behavior on programmer creativity. Information and Software Technology128 (2020), 106405. doi:10.1016/j.infsof. 2020.106405

    work page doi:10.1016/j.infsof 2020

  2. [2]

    Margaret A. Boden. 2004.The Creative Mind: Myths and Mechanisms. Vol. 2. Routledge, London

    2004

  3. [3]

    Sebastian G Bouschery, Vera Blazevic, and Frank T Piller. 2023. Augmenting human innovation teams with artificial intelligence: Exploring transformer- based language models.Journal of Product Innovation Management40, 2 (2023), 139–153. Exploring Creativity in Human-Human-LLM Collaborative Software Design

    2023

  4. [4]

    Brooks Jr

    Frederick P. Brooks Jr. 2010.The Design of Design: Essays From a Computer Scientist. Pearson Education Inc

    2010

  5. [5]

    Nigel Cross. 2025. Creative Cognition in Design I: The Creative Leap. In Designerly Ways of Knowing and Thinking. Springer London, London, 45–62. doi:10.1007/978-1-4471-7541-4_4

    work page doi:10.1007/978-1-4471-7541-4_4 2025

  6. [6]

    Nigel Cross. 2025. Creative Cognition in Design II: Co-evolution of Problem and Solution. InDesignerly Ways of Knowing and Thinking. Springer London, London, 63–73. doi:10.1007/978-1-4471-7541-4_5

    work page doi:10.1007/978-1-4471-7541-4_5 2025

  7. [7]

    2013.Creativity: Flow and the Psychology of Discovery and Invention

    Mihaly Csikszentmihalyi. 2013.Creativity: Flow and the Psychology of Discovery and Invention. HarperCollins, NY, USA

    2013

  8. [8]

    Bill Elliott. 2007. Anything is possible: Managing feature creep in an innovation rich environment. In2007 IEEE International Engineering Management Conference. IEEE, IEEE, 304–307

    2007

  9. [9]

    Jeanette Falk, Yiyi Chen, Janet Rafner, Mike Zhang, Johannes Bjerva, and Alexan- der Nolte. 2025. How Do Hackathons Foster Creativity? Towards Automated Evaluation of Creativity at Scale. InProceedings of the 2025 CHI Conference on Human Factors in Computing Systems (CHI ’25). Association for Computing Ma- chinery, New York, NY, USA, Article 198, 23 pages...

    work page doi:10.1145/3706598.3713447 2025

  10. [10]

    Jonas Frich, Lindsay MacDonald Vermeulen, Christian Remy, Michael Mose Biskjaer, and Peter Dalsgaard. 2019. Mapping the landscape of creativity support tools in HCI. InProceedings of the 2019 CHI conference on human factors in computing systems. Association for Computing Machinery, 1–18

    2019

  11. [11]

    Kiev Gama, Cleidson R. B. de Souza, Alexander Nolte, and George Valença. 2025. A C-Level Perspective on the Role of Developers in the Creative Process of Software Startups: Fostering Developer Creativity and Participation in Innovation.IEEE Software42, 3 (2025), 98–106. doi:10.1109/MS.2025.3541435

    work page doi:10.1109/ms.2025.3541435 2025

  12. [12]

    Luca Grilli and Mattia Pedota. 2024. Creativity and artificial intelligence: A multilevel perspective.Creativity and Innovation Management33, 2 (2024), 234– 247

    2024

  13. [13]

    Wouter Groeneveld, Laurens Luyten, Joost Vennekens, and Kris Aerts. 2021. Exploring the Role of Creativity in Software Engineering. In2021 IEEE/ACM 43rd International Conference on Software Engineering: Software Engineering in Society (ICSE-SEIS). IEEE, 1–9. doi:10.1109/ICSE-SEIS52602.2021.00009

    work page doi:10.1109/icse-seis52602.2021.00009 2021

  14. [14]

    Yuanning Han, Ziyi Qiu, Jiale Cheng, and RAY LC. 2024. When Teams Embrace AI: Human Collaboration Strategies in Generative Prompting in a Creative Design Task. InProceedings of the 2024 CHI Conference on Human Factors in Computing Systems(Honolulu, HI, USA)(CHI ’24). Association for Computing Machinery, New York, NY, USA, Article 176, 14 pages. doi:10.114...

    work page doi:10.1145/3613904.3642133 2024

  15. [15]

    Gonzalez, Darío Andrés Silva Moran, Steven I

    Jessica He, Stephanie Houde, Gabriel E. Gonzalez, Darío Andrés Silva Moran, Steven I. Ross, Michael Muller, and Justin D. Weisz. 2024. AI and the Future of Collaborative Work: Group Ideation with an LLM in a Virtual Canvas. In Proceedings of the 3rd Annual Meeting of the Symposium on Human-Computer Interaction for Work(Newcastle upon Tyne, United Kingdom)...

    work page doi:10.1145/3663384.3663398 2024

  16. [16]

    James D Herbsleb. 2007. Global software engineering: The future of socio- technical coordination. Infuture of software engineering (FOSE’07). IEEE, 188– 198

    2007

  17. [17]

    Xinyi Hou, Yanjie Zhao, Yue Liu, Zhou Yang, Kailong Wang, Li Li, Xiapu Luo, David Lo, John Grundy, and Haoyu Wang. 2024. Large Language Models for Software Engineering: A Systematic Literature Review.ACM Trans. Softw. Eng. Methodol.33, 8 (Dec. 2024). doi:10.1145/3695988

    work page doi:10.1145/3695988 2024

  18. [18]

    Stephanie Houde, Kristina Brimijoin, Michael Muller, Steven I Ross, Dario Andres Silva Moran, Gabriel Enrique Gonzalez, Siya Kunde, Morgan A Foreman, and Justin D Weisz. 2025. Controlling AI Agent Participation in Group Conversations: A Human-Centered Approach. InProceedings of the 30th International Conference on Intelligent User Interfaces. Association ...

    2025

  19. [19]

    Sarah Inman, Sarah D’Angelo, and Bogdan Vasilescu. 2024. Developer Produc- tivity for Humans, Part 8: Creativity in Software Engineering.IEEE Software41, 2 (March 2024), 11–16. doi:10.1109/MS.2023.3340831

    work page doi:10.1109/ms.2023.3340831 2024

  20. [20]

    Sarah Inman, Ambar Murillo, Sarah D’Angelo, Adam Brown, and Collin Green

  21. [21]

    doi:10.1109/MS.2025.3534085

    Seamful AI for Creative Software Engineering: Use in Software Develop- ment Workflows.IEEE Software42, 3 (2025), 59–66. doi:10.1109/MS.2025.3534085

    work page doi:10.1109/ms.2025.3534085 2025

  22. [22]

    Zorana Ivcevic and Mike Grandinetti. 2024. Artificial intelligence as a tool for creativity.Journal of Creativity34, 2 (2024), 100079

    2024

  23. [23]

    Victoria Jackson, Yoonha Cha, Rafael Prikladnick, and André van der Hoek

  24. [24]

    The Role of LLMs in Collaborative Software Design.arXiv preprint arXiv:2604.09120(2026)

    work page internal anchor Pith review Pith/arXiv arXiv 2026

  25. [25]

    Victoria Jackson, Grischa Liebel, Rafael Prikladnicki, and André van der Hoek

  26. [26]

    https://doi.org/10.5281/zenodo.19002870

    Supplementary data. https://doi.org/10.5281/zenodo.19002870

    work page doi:10.5281/zenodo.19002870

  27. [27]

    Victoria Jackson, Bogdan Vasilescu, Daniel Russo, Paul Ralph, Maliheh Izadi, Rafael Prikladnicki, Sarah D’angelo, Sarah Inman, Anielle Andrade, and André van der Hoek. 2024. The Impact of Generative AI on Creativity in Software Development: A Research Agenda.ACM Trans. Softw. Eng. Methodol.(Dec. 2024). doi:10.1145/3708523

    work page doi:10.1145/3708523 2024

  28. [28]

    Rodi Jolak, Andreas Wortmann, Grischa Liebel, Eric Umuhoza, and Michel R. V. Chaudron. 2023. Design thinking and creativity of colocated versus globally distributed software developers.Journal of Software: Evolution and Process(2023). doi:10.1002/smr.2377

    work page doi:10.1002/smr.2377 2023

  29. [29]

    Kaufman and Ronald A

    James C. Kaufman and Ronald A. Beghetto. 2009. Beyond Big and Little: The Four C Model of Creativity.Review of General Psychology13, 1 (March 2009), 1–12. doi:10.1037/a0013688

    work page doi:10.1037/a0013688 2009

  30. [30]

    Anis Khedhaouria, Francesco Montani, and Roy Thurik. 2017. Time Pressure and Team Member Creativity within R&D Projects: The Role of Learning Orientation and Knowledge Sourcing.International Journal of Project Management35, 6 (2017), 942–954. doi:10.1016/j.ijproman.2017.04.002

    work page doi:10.1016/j.ijproman.2017.04.002 2017

  31. [31]

    Jingoog Kim and Mary Lou Maher. 2023. The effect of AI-based inspiration on human design ideation.International Journal of Design Creativity and Innovation 11, 2 (2023), 81–98

    2023

  32. [32]

    Jeongyeon Kim, Sangho Suh, Lydia B Chilton, and Haijun Xia. 2023. Metaphorian: leveraging large language models to support extended metaphor creation for science writing. InProceedings of the 2023 ACM Designing Interactive Systems Conference. ACM, 115–135

    2023

  33. [33]

    Miikka Kuutila, Mika Mäntylä, Umar Farooq, and Maëlick Claes. 2020. Time pressure in software engineering: A systematic review.Information and Software Technology121 (2020), 106257. doi:10.1016/j.infsof.2020.106257

    work page doi:10.1016/j.infsof.2020.106257 2020

  34. [34]

    Huiting Liu, Xiyuan Zhang, Jiangping Zhou, Yuancong Shou, Yang Yin, and Chunlei Chai. 2024. Cognitive Styles and Design Performances in Conceptual Design Collaboration with GenAI.International Journal of Technology and Design Education(2024). doi:10.1007/s10798-024-09937-y

    work page doi:10.1007/s10798-024-09937-y 2024

  35. [35]

    Ryan Louie, Andy Coenen, Cheng Zhi Huang, Michael Terry, and Carrie J Cai

  36. [36]

    InProceedings of the 2020 CHI Conference on Human Factors in Computing Systems

    Novice-AI music co-creation via AI-steering tools for deep generative models. InProceedings of the 2020 CHI Conference on Human Factors in Computing Systems. ACM, 1–13

    2020

  37. [37]

    Mary Lou Maher, Josiah Poon, and Sylvie Boulanger. 1996. Formalising Design Exploration as Co-Evolution. InAdvances in Formal Design Methods for CAD: Proceedings of the IFIP WG5.2 Workshop on Formal Design Methods for Computer- Aided Design, June 1995, John S. Gero and Fay Sudweeks (Eds.). Springer US, Boston, MA, 3–30. doi:10.1007/978-0-387-34925-1_1

    work page doi:10.1007/978-0-387-34925-1_1 1996

  38. [38]

    Neil Maiden, Sara Jones, Kristine Karlsen, Roger Neill, Konstantinos Zachos, and Alastair Milne. 2010. Requirements engineering as creative problem solving: A research agenda for idea finding. In2010 18th IEEE International Requirements Engineering Conference. IEEE, 57–66

    2010

  39. [39]

    Neil Maiden, Cornelius Ncube, and Suzanne Robertson. 2007. Can requirements be creative? experiences with an enhanced air space management system. In 29th International Conference on Software Engineering (ICSE’07). IEEE, 632–641

    2007

  40. [40]

    Neil Maiden, Konstantinos Zachos, Kostas Petrianakis, James Lockerbie, Chan- takan Chanpalangsri, Holger Ernst, and Seyfettin Kara. 2025. Beyond just generative AI for discovering software opportunities .IEEE Software42, 03 (Feb. 2025), 7–12. doi:10.1109/MS.2025.3540672

    work page doi:10.1109/ms.2025.3540672 2025

  41. [41]

    Fairuz Nawer Meem, Justin Smith, and Brittany Johnson-Matthews. 2025. Why Do Software Practitioners Use ChatGPT for Software Development Tasks?. InPro- ceedings of the 33rd ACM International Conference on the Foundations of Software Engineering(Clarion Hotel Trondheim, Trondheim, Norway)(FSE Companion ’25). Association for Computing Machinery, New York, N...

    work page doi:10.1145/3696630.3731667 2025

  42. [42]

    Rahul Mohanani, Paul Ralph, Burak Turhan, and Vladimir Mandić. 2022. How Templated Requirements Specifications Inhibit Creativity in Software Engineer- ing.IEEE Transactions on Software Engineering48, 10 (Oct. 2022), 4074–4086. doi:10.1109/TSE.2021.3112503

    work page doi:10.1109/tse.2021.3112503 2022

  43. [43]

    Rahul Mohanani, Prabhat Ram, Ahmed Lasisi, Paul Ralph, and Burak Turhan

  44. [44]

    In2017 43rd Euromicro Conference on Software Engineering and Advanced Applications (SEAA)

    Perceptions of Creativity in Software Engineering Research and Prac- tice. In2017 43rd Euromicro Conference on Software Engineering and Advanced Applications (SEAA). IEEE, 210–217. doi:10.1109/SEAA.2017.21

    work page doi:10.1109/seaa.2017.21 2017

  45. [45]

    Rahul Mohanani, Burak Turhan, and Paul Ralph. 2021. Requirements Framing Affects Design Creativity.IEEE Transactions on Software Engineering47, 5 (May 2021), 936–947. doi:10.1109/TSE.2019.2909033

    work page doi:10.1109/tse.2019.2909033 2021

  46. [46]

    Stoyan Nikolov, Daniele Codecasa, Anna Sjövall, Maxim Tabachnyk, Satish Chandra, Siddharth Taneja, and Celal Ziftci. 2025. How is Google using AI for internal code migrations?. In2025 IEEE/ACM 47th International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP). IEEE, 481–492

    2025

  47. [47]

    Guilherme Vaz Pereira, Victoria Jackson, Rafael Prikladnicki, André van der Hoek, Luciane Fortes, Carolina Araújo, André Coelho, Ligia Chelli, and Diego Ramos

  48. [48]

    In2025 IEEE/ACM 47th International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP)

    Exploring GenAI in Software Development: Insights from a Case Study in a Large Brazilian Company. In2025 IEEE/ACM 47th International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP). IEEE, 330–341

  49. [49]

    Marian Petre and Mary Shaw. 2025. Contrasting to spark creativity in software development teams .IEEE Software42, 03 (Feb. 2025), 67–74. doi:10.1109/MS. 2025.3538670

    work page doi:10.1109/ms 2025

  50. [50]

    2016.Software Design Decoded: 66 Ways Experts Think

    Marian Petre and André van der Hoek. 2016.Software Design Decoded: 66 Ways Experts Think. MIT Press

    2016

  51. [51]

    Saima Ritonummi, Valtteri Siitonen, Markus Salo, Henri Pirkkalainen, and Anu Sivunen. 2023. Flow Experience in Software Engineering. InProceedings of the 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering(San Francisco, CA, USA)(ESEC/FSE 2023). Association for Computing Machinery, New York, NY,...

    work page doi:10.1145/3611643.3616263 2023

  52. [52]

    Mohammad Ronagh Nikghalb and Jinghui Cheng. 2025. Interrogating AI: Charac- terizing Emergent Playful Interactions with ChatGPT.Proc. ACM Hum.-Comput. Interact.9, 2, Article CSCW117 (May 2025), 23 pages. doi:10.1145/3711015

    work page doi:10.1145/3711015 2025

  53. [53]

    Runco and Garrett J

    Mark A. Runco and Garrett J. Jaeger. 2012. The Standard Definition of Creativity. Creativity Research Journal24, 1 (Jan. 2012), 92–96. doi:10.1080/10400419.2012. 650092

    work page doi:10.1080/10400419.2012 2012

  54. [54]

    Benjamin Saunders, Julius Sim, Tom Kingstone, Shula Baker, Jackie Waterfield, Bernadette Bartlam, Heather Burroughs, and Clare Jinks. 2018. Saturation in qual- itative research: exploring its conceptualization and operationalization.Quality & Quantity52, 4 (2018), 1893–1907. doi:10.1007/s11135-017-0574-8

    work page doi:10.1007/s11135-017-0574-8 2018

  55. [55]

    Orit Shaer, Angelora Cooper, Osnat Mokryn, Andrew L Kun, and Hagit Ben Shoshan. 2024. AI-Augmented Brainwriting: Investigating the use of LLMs in group ideation. InProceedings of the 2024 CHI Conference on Human Factors in Computing Systems(Honolulu, HI, USA)(CHI ’24). Association for Computing Ma- chinery, New York, NY, USA, Article 1050, 17 pages. doi:1...

    work page doi:10.1145/3613904.3642414 2024

  56. [56]

    2022.Human-Centered AI(1 ed.)

    Ben Shneiderman. 2022.Human-Centered AI(1 ed.). Oxford University Press

    2022

  57. [57]

    Kaile Smith, Alan Pickering, and Joydeep Bhattacharya. 2022. The Creative Life: A Daily Diary Study of Creativity, Affect, and Well-Being in Creative Individuals. Creativity Research Journal34, 4 (Oct. 2022), 460–479. doi:10.1080/10400419.2022. 2122371 Publisher: Routledge

    work page doi:10.1080/10400419.2022 2022

  58. [58]

    Kelly, Saumya Pareek, Qiushi Zhou, and Eduardo Velloso

    Samangi Wadinambiarachchi, Ryan M. Kelly, Saumya Pareek, Qiushi Zhou, and Eduardo Velloso. 2024. The Effects of Generative AI on Design Fixation and Divergent Thinking. InProceedings of the 2024 CHI Conference on Human Factors in Computing Systems(2024-05-11)(CHI ’24). Association for Computing Machinery, Hawaii, USA, 1–18. doi:10.1145/3613904.3642919

    work page doi:10.1145/3613904.3642919 2024

  59. [59]

    Jialiang Wei, Anne-Lise Courbis, Thomas Lambolais, Gerard Dray, and Walid Maalej. 2025. On AI-Inspired UI-Design .IEEE Software42, 03 (Feb. 2025), 50–58. doi:10.1109/MS.2025.3536838

    work page doi:10.1109/ms.2025.3536838 2025

  60. [60]

    Proceedings of the Extended Abstracts of the CHI Conference on Human Factors in Computing Systems

    Justin D. Weisz, Shraddha Vijay Kumar, Michael Muller, Karen-Ellen Browne, Arielle Goldberg, Katrin Ellice Heintze, and Shagun Bajpai. 2025. Examining the Use and Impact of an AI Code Assistant on Developer Productivity and Experience in the Enterprise. InProceedings of the Extended Abstracts of the CHI Conference on Human Factors in Computing Systems (CH...

    work page doi:10.1145/3706599 2025

  61. [61]

    Zhikun Wu, Thomas Weber, and Florian Müller. 2025. One Does Not Simply Meme Alone: Evaluating Co-Creativity Between LLMs and Humans in the Gen- eration of Humor. InProceedings of the 30th International Conference on Intelligent User Interfaces (IUI ’25). Association for Computing Machinery, New York, NY, USA, 1082–1092. doi:10.1145/3708359.3712094

    work page doi:10.1145/3708359.3712094 2025

  62. [62]

    Albert Ziegler, Eirini Kalliamvakou, X Alice Li, Andrew Rice, Devon Rifkin, Shawn Simister, Ganesh Sittampalam, and Edward Aftandilian. 2024. Measuring GitHub Copilot’s Impact on Productivity.Commun. ACM67, 3 (2024), 54–63

    2024