arxiv: 2604.09120 · v1 · submitted 2026-04-10 · 💻 cs.SE

Recognition: no theorem link

The Role of LLMs in Collaborative Software Design

Victoria Jackson , Yoonha Cha , Rafael Prikladnicki , Andr\'e van der Hoek

Authors on Pith no claims yet

Pith reviewed 2026-05-10 17:52 UTC · model grok-4.3

classification 💻 cs.SE

keywords LLMcollaborative software designempirical studyhuman-AI collaborationsoftware engineeringdesign processpair programming

0 comments

The pith

Shared use of one LLM instance helps design pairs build shared understanding while separate instances can cause context drift.

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

This paper reports an exploratory lab study in which 18 pairs of software professionals used an LLM in any way they chose while designing a university bicycle parking application. The central finding is that LLM use takes on two distinct joint patterns: sharing a single instance tends to keep the pair aligned on ideas and requirements, whereas each person running their own instance sometimes produces drifting contexts that the pair must then reconcile. Reliance on the model ranged from complete non-use to treating it as an information source or a content generator, with participants routinely inspecting and reflecting on its outputs to extract design insights even as early suggestions occasionally narrowed the range of ideas considered.

Core claim

In a controlled laboratory setting, 18 pairs of software professionals were given free rein to incorporate an LLM into the collaborative design of a campus bicycle parking application. The study observed that joint use of the LLM fell into two main patterns: when the pair worked with a shared instance, the common output helped maintain and develop a shared understanding of the design; when each partner used a separate instance, the outputs sometimes diverged enough to produce context drift that required extra coordination. Across both patterns, professionals scrutinized LLM responses for value, often gaining design insights, yet early acceptance of the model's suggestions occasionally curta-

What carries the argument

The two observed patterns of joint LLM use—shared single-instance versus parallel separate-instance—which either support or disrupt the maintenance of common ground during collaborative design.

If this is right

Shared-instance LLM use can help maintain shared understanding between design partners.
Parallel-instance use can introduce context drift that requires additional coordination.
Scrutiny of LLM outputs frequently produces design insights regardless of usage pattern.
Early anchoring on LLM suggestions can reduce the breadth of design exploration.

Where Pith is reading between the lines

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

Future design tools could add explicit support for switching between shared and private LLM sessions to reduce drift.
Professional training might include explicit tactics for avoiding premature commitment to early LLM outputs.
The same usage patterns could be tested in longer-duration or multi-person design sessions to see whether drift effects scale.

Load-bearing premise

The patterns of shared and parallel LLM use and their effects on understanding and drift, observed in a controlled lab task with 18 pairs, will appear in the same form during real-world collaborative software design work.

What would settle it

Repeating the same observation protocol with professional pairs working on live industry design projects in their usual environments and checking whether shared-instance alignment and parallel-instance drift still occur at comparable rates.

Figures

Figures reproduced from arXiv: 2604.09120 by Andr\'e van der Hoek, Rafael Prikladnicki, Victoria Jackson, Yoonha Cha.

read the original abstract

While much prior work examines Large Language Models (LLMs) for solo development tasks (e.g., coding), far less is known about how LLMs shape collaborative group work in software engineering. This study focuses on one such collaborative task, namely software design. It presents the results of an exploratory laboratory study of 18 pairs of software professionals who could use an LLM however they saw fit, to design a University campus bicycle parking application. Our findings reveal that introducing an LLM leads to distinct patterns of joint use: shared-instance use facilitated shared understanding, whereas parallel use across separate instances sometimes led to ''context drift''. We also observe wide variation in reliance, from non-use to treating the LLM as an information source or producer. Across these modes, professionals scrutinized and reflected on LLM responses, often yielding design insights; however, early anchoring sometimes curtailed exploration. We provide implications for tools to aid designers while retaining the human-centricity important to design.

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.

Desk Editor's Note private letter to a colleague

This paper gives a first empirical look at how pairs of designers actually share or split LLM use during a software design session, with shared instances supporting common ground and parallel ones risking drift.

read the letter

The main takeaway is that the authors ran an exploratory lab study with 18 pairs of software professionals designing a university bike parking app, letting them use an LLM any way they wanted. They observed two main joint-use patterns: when the pair worked from one shared LLM instance it helped them stay aligned on the design, but when each ran their own instance it sometimes produced context drift where their ideas diverged. They also saw wide differences in how much people leaned on the LLM at all, from ignoring it to treating it as an information source or idea generator, and noted that reflection on its outputs often produced useful design points even while early anchoring sometimes narrowed the options explored. This moves the conversation past the solo-developer LLM studies that dominate the citations, and the observations are reported plainly from the session data. The paper does well by keeping claims descriptive and acknowledging the exploratory frame rather than overstating. The qualitative reporting feels honest about what they saw in the recordings and notes. The soft spots are the small sample, the single contrived task, and the lab setting, all of which make it unclear how far the patterns travel to real industry teams or other design problems. There are no quantitative measures or controls, so the links between use mode and shared understanding remain observational. Methods details on how the sessions were coded and analyzed would strengthen it, and the implications for tool design stay high-level. This work is for HCI and empirical software engineering researchers who care about how tools actually get used in groups. A reader looking for concrete examples of LLM collaboration behaviors will find usable material here. It deserves a serious referee because the patterns are new enough to be worth discussing and refining, even if the study will need clearer limitations and analysis steps in revision. I would send it out for review.

Referee Report

2 major / 3 minor

Summary. The paper describes an exploratory laboratory study involving 18 pairs of software professionals who used an LLM to collaboratively design a University campus bicycle parking application. Key findings include distinct patterns of joint LLM use—shared-instance use that facilitated shared understanding versus parallel use across separate instances that sometimes caused context drift—along with variations in reliance on the LLM (from non-use to treating it as information source or producer), the benefits of scrutinizing LLM responses for design insights, and the risk of early anchoring curtailing exploration. Implications for designing tools that support collaborative design while preserving human-centricity are discussed.

Significance. If these observations are robust, the work offers timely empirical insights into LLM-supported collaborative software design, an area less explored than individual coding tasks. The identification of specific usage patterns and their potential impacts provides a foundation for future research and tool development in software engineering. The exploratory qualitative approach yields rich, context-specific details but, due to the small sample and controlled setting, the findings should be interpreted as generating hypotheses rather than definitive conclusions about real-world practices.

major comments (2)

[Methods] Methods: The study is framed as examining the effects of 'introducing an LLM' on collaborative patterns, yet it lacks a control condition without LLM access; this makes it difficult to isolate whether the observed joint-use patterns (shared vs. parallel) and outcomes like context drift are attributable to the LLM rather than to the design task or pair interactions.
[Results] Results: The central distinctions between shared-instance use (facilitating shared understanding) and parallel use (leading to context drift) are illustrated via examples, but without reported coding scheme details, inter-rater reliability, or counts of how many of the 18 pairs exhibited each pattern, the prevalence and consistency of these associations remain unclear.

minor comments (3)

[Abstract] Abstract: The phrasing 'introducing an LLM leads to distinct patterns' implies a causal effect from the LLM's presence; rewording to 'when using an LLM, distinct patterns of joint use emerged' would better align with the observational design.
[Discussion] Discussion: The implications section could more explicitly connect proposed tool features (e.g., for mitigating context drift) back to specific observed behaviors in the study sessions.
[Limitations] The paper would benefit from a dedicated limitations subsection that directly addresses the generalizability of findings from this specific task and professional participant pool to broader collaborative software design contexts.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We are grateful to the referee for the constructive feedback and the recommendation for minor revision. We address each major comment below.

read point-by-point responses

Referee: [Methods] Methods: The study is framed as examining the effects of 'introducing an LLM' on collaborative patterns, yet it lacks a control condition without LLM access; this makes it difficult to isolate whether the observed joint-use patterns (shared vs. parallel) and outcomes like context drift are attributable to the LLM rather than to the design task or pair interactions.

Authors: We thank the referee for this important point. The study was intentionally exploratory, aiming to observe and characterize how pairs of professionals use an LLM when it is introduced into a collaborative design task, rather than to test causal effects through a controlled comparison. The design allowed participants to use the LLM as they saw fit, including the option of non-use, which revealed the range of reliance patterns. While we agree that a no-LLM control would help isolate LLM-specific effects, our focus was on the dynamics within LLM-supported sessions. We will revise the manuscript to better emphasize the exploratory and observational nature of the study and to explicitly discuss this limitation in the Discussion section. revision: partial
Referee: [Results] Results: The central distinctions between shared-instance use (facilitating shared understanding) and parallel use (leading to context drift) are illustrated via examples, but without reported coding scheme details, inter-rater reliability, or counts of how many of the 18 pairs exhibited each pattern, the prevalence and consistency of these associations remain unclear.

Authors: We acknowledge that the qualitative analysis details could be more transparent. The patterns were derived from a thematic analysis of session videos and transcripts, with authors iteratively coding for usage modes and outcomes. In the revision, we will include a more detailed description of the coding process, the scheme for classifying shared vs. parallel use, and the counts of pairs falling into each category. We will also report inter-rater reliability metrics from the analysis. This will provide better evidence for the prevalence of the observed associations. revision: yes

Circularity Check

0 steps flagged

No significant circularity: purely empirical qualitative study

full rationale

The paper reports an exploratory laboratory study with 18 pairs of software professionals performing a design task while using an LLM as they saw fit. All claims describe observed patterns (shared-instance vs. parallel use, context drift, reliance variation, scrutiny of outputs) drawn directly from session data and qualitative analysis. No equations, fitted parameters, predictions, derivations, or mathematical reductions appear. No load-bearing self-citations, uniqueness theorems, or ansatzes are invoked to justify central results. The work is self-contained as descriptive observation; findings do not reduce to their own inputs by construction.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

This is a qualitative empirical study with no mathematical derivations, free parameters, axioms, or invented entities; relies on observational data and thematic analysis.

pith-pipeline@v0.9.0 · 5463 in / 1113 out tokens · 31333 ms · 2026-05-10T17:52:06.927134+00:00 · methodology

discussion (0)

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

Exploring Creativity in Human-Human-LLM Collaborative Software Design
cs.SE 2026-04 unverdicted novelty 5.0

Creativity in human-LLM collaborative software design emerges primarily from human traits and interactions, with LLMs providing supplementary novel ideas but occasionally hindering progress.

Reference graph

Works this paper leans on

53 extracted references · 35 canonical work pages · cited by 1 Pith paper

[1]

Bardha Ahmeti, Maja Linder, Raffaela Groner, and Rebekka Wohlrab. 2024. Ar- chitecture Decision Records in Practice: An Action Research Study. InSoftware Architecture(2024), Matthias Galster, Patrizia Scandurra, Tommi Mikkonen, Pablo Oliveira Antonino, Elisa Yumi Nakagawa, and Elena Navarro (Eds.). Springer Nature Switzerland, Cham, 333–349. doi:10.1007/9...

work page doi:10.1007/978-3-031-70797-1_22 2024
[2]

Sebastian Baltes and Stephan Diehl. 2014. Sketches and Diagrams in Practice. In Proceedings of the 22nd ACM SIGSOFT International Symposium on Foundations of Software Engineering(2014-11-11). ACM, Hong Kong China, 530–541. doi:10. 1145/2635868.2635891

work page arXiv 2014
[3]

Albert Bandura. 1982. Self-efficacy mechanism in human agency.American psychologist37, 2 (1982), 122

1982
[4]

James, and Nadia Polikarpova

Shraddha Barke, Michael B. James, and Nadia Polikarpova. 2023. Grounded Copilot: How Programmers Interact with Code-Generating Models.Proceedings of the ACM on Programming Languages7 (2023), 78:85–78:111. Issue OOPSLA1. doi:10.1145/3586030

work page doi:10.1145/3586030 2023
[5]

Christian Bird, Denae Ford, Thomas Zimmermann, Nicole Forsgren, Eirini Kalliamvakou, Travis Lowdermilk, and Idan Gazit. 2023. Taking Flight with Copilot: Early Insights and Opportunities of AI-powered Pair-Programming Tools.Queue20, 6 (2023), Pages 10:35–Pages 10:57. doi:10.1145/3582083

work page doi:10.1145/3582083 2023
[6]

Virginia Braun and Victoria Clarke. 2006. Using Thematic Analysis in Psy- chology.Qualitative Research in Psychology3, 2 (2006), 77–101. doi:10.1191/ 1478088706qp063oa

2006
[7]

Brooks Jr

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

2010
[8]

Inha Cha and Richmond Y. Wong. 2025. Understanding Socio-technical Factors Configuring AI Non-Use in UX Work Practices. InProceedings of the 2025 CHI Conference on Human Factors in Computing Systems (CHI ’25). Association for Computing Machinery, New York, NY, USA, Article 1110, 17 pages. doi:10.1145/ 3706598.3713140

work page arXiv 2025
[9]

Mauro Cherubini, Gina Venolia, Rob DeLine, and Amy J. Ko. 2007. Let’s Go to the Whiteboard: How and Why Software Developers Use Drawings. InProceedings of the SIGCHI Conference on Human Factors in Computing Systems(2007-04-29). ACM, San Jose California USA, 557–566. doi:10.1145/1240624.1240714

work page doi:10.1145/1240624.1240714 2007
[10]

Herbert H Clark and Susan E Brennan. 1991. Grounding in communication. (1991)

1991
[11]

Creswell and Cheryl N

John W. Creswell and Cheryl N. Poth. 2018.Qualitative Inquiry & Research Design (4 ed.). SAGE Publications

2018
[12]

Javier Cámara, Javier Troya, Lola Burgueño, and Antonio Vallecillo. 2023. On the Assessment of Generative AI in Modeling Tasks: An Experience Report with ChatGPT and UML.Software and Systems Modeling22, 3 (2023), 781–793. doi:10.1007/s10270-023-01105-5

work page doi:10.1007/s10270-023-01105-5 2023
[13]

Rudra Dhar, Karthik Vaidhyanathan, and Vasudeva Varma. 2024. Can LLMs Generate Architectural Design Decisions? - An Exploratory Empirical Study. In 2024 IEEE 21st International Conference on Software Architecture (ICSA). IEEE, Hyderabad, India, 79–89. doi:10.1109/ICSA59870.2024.00016

work page doi:10.1109/icsa59870.2024.00016 2024
[14]

Fast semi-iterative finite ele- ment Poisson solvers for tensor core GPUs based on prehandling

J. Andrés Díaz-Pace, Antonela Tommasel, and Rafael Capilla. 2024. Helping Novice Architects to Make Quality Design Decisions Using an LLM-Based Assis- tant. InSoftware Architecture(2024), Matthias Galster, Patrizia Scandurra, Tommi Mikkonen, Pablo Oliveira Antonino, Elisa Yumi Nakagawa, and Elena Navarro (Eds.). Springer Nature Switzerland, Cham, 324–332....

work page doi:10.1007/978-3-031- 2024
[15]

2003.Domain-Driven Design: Tackling Complexity in the Heart of Software

Eric Evans. 2003.Domain-Driven Design: Tackling Complexity in the Heart of Software. Addison-Wesley Professional

2003
[16]

Fabian Fagerholm, Michael Felderer, Davide Fucci, Michael Unterkalmsteiner, Bogdan Marculescu, Markus Martini, Lars Göran Wallgren Tengberg, Robert Feldt, Bettina Lehtelä, Balázs Nagyváradi, and Jehan Khattak. 2022. Cognition in Software Engineering: A Taxonomy and Survey of a Half-Century of Research. ACM Comput. Surv.54, 11s, Article 226 (Sept. 2022), 3...

work page doi:10.1145/3508359 2022
[17]

Davide Falessi, Giovanni Cantone, Rick Kazman, and Philippe Kruchten. 2011. Decision-making techniques for software architecture design: A comparative survey.ACM Comput. Surv.43, 4, Article 33 (Oct. 2011), 28 pages. doi:10.1145/ 1978802.1978812

work page arXiv 2011
[18]

Alessio Ferrari, Sallam Abualhaija, and Chetan Arora. 2024. Model Generation with LLMs: From Requirements to UML Sequence Diagrams. In2024 IEEE 32nd International Requirements Engineering Conference Workshops (REW)(2024-06). IEEE, Reykjavik, Iceland, 291–300. doi:10.1109/REW61692.2024.00044

work page doi:10.1109/rew61692.2024.00044 2024
[19]

Figma. 2025. The Online Collaborative Whiteboard for Teams. https://www. figma.com/figjam/

2025
[20]

Hans-Georg Fill, Peter Fettke, and Julius Köpke. 2023. Conceptual Modeling and Large Language Models: Impressions From First Experiments With ChatGPT. Enterprise Modelling and Information Systems Architectures (EMISAJ)18 (2023), 1–15. doi:10.18417/emisa.18.3

work page doi:10.18417/emisa.18.3 2023
[21]

2004.Is Design Dead?martinfowler.com

Martin Fowler. 2004.Is Design Dead?martinfowler.com. https://martinfowler. com/articles/designDead.html

2004
[22]

Tony Gorschek, Ewan Tempero, and Lefteris Angelis. 2014. On the Use of Software Design Models in Software Development Practice: An Empirical Investigation. Journal of Systems and Software95 (2014), 176–193. doi:10.1016/j.jss.2014.03.082

work page doi:10.1016/j.jss.2014.03.082 2014
[23]

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
[24]

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 (CHIWORK ’24). Association for Compu...

work page doi:10.1145/3663384.3663398 2024
[25]

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, Article 220 (Dec. 2024), 79 pages. doi:10.1145/3695988

work page doi:10.1145/3695988 2024
[26]

Victoria Jackson, Yoonha Cha, Rafael Prikladnicki, and André van der Hoek. 2026. Supplementary data for The Role of LLMs in Collaborative Software Design. https://doi.org/10.5281/zenodo.19219581

work page doi:10.5281/zenodo.19219581 2026
[27]

Victoria Jackson, Rafael Prikladnicki, André van der Hoek, and Lisa Marshall. 2023. Team Creativity in a Hybrid Software Development World: Eight Approaches. IEEE Software40, 2 (2023), 60–69. doi:10.1109/MS.2022.3229353

work page doi:10.1109/ms.2022.3229353 2023
[28]

Chaudron

Rodi Jolak, Andreas Wortman, Grischa Liebel, Eric Umuhoza, and Michel R.V. Chaudron. 2019. The Design Thinking Of Co-Located vs. Distributed Software Developers: Distance Strikes Again. In2019 ACM/IEEE 14th International Con- ference on Global Software Engineering (ICGSE)(2019-05). IEEE, Montreal, QC, Canada, 106–116

2019
[29]

Udo-Imeh, Bonan Kou, and Tianyi Zhang

Samia Kabir, David N. Udo-Imeh, Bonan Kou, and Tianyi Zhang. 2024. Is Stack Overflow Obsolete? An Empirical Study of the Characteristics of ChatGPT An- swers to Stack Overflow Questions. InProceedings of the 2024 CHI Conference on Human Factors in Computing Systems(Honolulu, HI, USA)(CHI ’24). Asso- ciation for Computing Machinery, New York, NY, USA, Arti...

work page doi:10.1145/3613904.3642596 2024
[30]

Eunsuk Kang and Mary Shaw. 2024. tl;dr: Chill, y’all: AI Will Not Devour SE. InProceedings of the 2024 ACM SIGPLAN International Symposium on New Ideas, New Paradigms, and Reflections on Programming and Software(Pasadena, CA, USA)(Onward! ’24). Association for Computing Machinery, New York, NY, USA, 303–315. doi:10.1145/3689492.3689816

work page doi:10.1145/3689492.3689816 2024
[31]

Ranim Khojah, Mazen Mohamad, Philipp Leitner, and Francisco Gomes de Oliveira Neto. 2024. Beyond Code Generation: An Observational Study of Chat- GPT Usage in Software Engineering Practice.Proc. ACM Softw. Eng.1 (2024), 81:1819–81:1840. Issue FSE. doi:10.1145/3660788

work page doi:10.1145/3660788 2024
[32]

LaToza, Marian Petre, and André van der Hoek

Nicolas Mangano, Thomas D. LaToza, Marian Petre, and André van der Hoek
[33]

doi:10.1109/TSE.2014

How Software Designers Interact with Sketches at the Whiteboard.IEEE Transactions on Software Engineering41, 2 (2015), 135–156. doi:10.1109/TSE.2014. 2362924

work page doi:10.1109/tse.2014 2015
[34]

Mellor, Anthony N

Stephen J. Mellor, Anthony N. Clark, and Takao Futagami. 2003. Guest Editors’ Introduction: Model-Driven Development.IEEE Software20, 05 (2003), 14–18. doi:10.1109/MS.2003.1231145

work page doi:10.1109/ms.2003.1231145 2003
[35]

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

work page doi:10.1109/tse.2021.3112503 2022
[36]

2023.Generative Artificial Intelligence for Software Engineering – A Research Agenda

Anh Nguyen-Duc, Beatriz Cabrero-Daniel, Adam Przybylek, Chetan Arora, Dron Khanna, Tomas Herda, Usman Rafiq, Jorge Melegati, Eduardo Guerra, Kai-Kristian Kemell, Mika Saari, Zheying Zhang, Huy Le, Tho Quan, and Pekka Abrahamsson. 2023.Generative Artificial Intelligence for Software Engineering – A Research Agenda. arXiv:2310.18648 [cs] doi:10.48550/arXiv....

work page doi:10.48550/arxiv.2310.18648 2023
[37]

Gary M Olson and Judith S Olson. 2000. Distance matters.Human–computer interaction15, 2-3 (2000), 139–178

2000
[38]

Guilherme Vaz Pereira, Victoria Jackson, Rafael Prikladnicki, André van der Hoek, Luciane Fortes, Carolina Araújo, André Coelho, Ligia Chelli, and Diego Ramos
[39]

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). 330–341. doi:10.1109/ICSE-SEIP66354.2025.00035

work page doi:10.1109/icse-seip66354.2025.00035 2025
[40]

Marian Petre. 2013. UML in Practice. In2013 35th International Conference on Software Engineering (ICSE)(2013-05). IEEE, San Franciso, CA, USA, 722–731. doi:10.1109/ICSE.2013.6606618

work page doi:10.1109/icse.2013.6606618 2013
[41]

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
[42]

2025.Qualtrics XM|The Leading Experience Management Sofwtare

Qualtrics. 2025.Qualtrics XM|The Leading Experience Management Sofwtare. Qualtrics. https://www.qualtrics.com/

2025
[43]

Maryam Razavian, Antony Tang, Rafael Capilla, and Patricia Lago. 2016. In Two Minds: How Reflections Influence Software Design Thinking.Journal of Software: Evolution and Process28, 6 (2016), 394–426. doi:10.1002/smr.1776

work page doi:10.1002/smr.1776 2016
[44]

2021.The Coding Manual For Qualitative Researchers(4 ed.)

Johnny Saldana. 2021.The Coding Manual For Qualitative Researchers(4 ed.). SAGE Publications. FSE Companion ’26, July 05–09, 2026, Montreal, QC, Canada Jackson, Cha, Prikladnicki, van der Hoek

2021
[45]

Murphy, and Thomas Fritz

Marie Salomon, Ekaterina Koshchenko, Agnia Sergeyuk, Reid Holmes, Gail C. Murphy, and Thomas Fritz. 2026. From Disruptions to Discussions: How GenAI Impacts Human Interactions in Software Development.IEEE Transactions on Software Engineering(2026), 1–16. doi:10.1109/TSE.2026.3655626

work page doi:10.1109/tse.2026.3655626 2026
[46]

Susan Leigh Star and James R Griesemer. 1989. Institutional ecology,translations’ and boundary objects: Amateurs and professionals in Berkeley’s Museum of Vertebrate Zoology, 1907-39.Social studies of science19, 3 (1989), 387–420

1989
[47]

Guide to the Software Engineering Body of Knowledge v4.0

SWEBOK 2024. Guide to the Software Engineering Body of Knowledge v4.0. https://ieeecs-media.computer.org/media/education/swebok/swebok-v4.pdf

2024
[48]

Antony Tang, Muhammad Ali Babar, Ian Gorton, and Jun Han. 2006. A survey of architecture design rationale.Journal of Systems and Software79, 12 (2006), 1792–1804. doi:10.1016/j.jss.2006.04.029

work page doi:10.1016/j.jss.2006.04.029 2006
[49]

Ruotong Wang, Ruijia Cheng, Denae Ford, and Thomas Zimmermann. 2024. Investigating and Designing for Trust in AI-powered Code Generation Tools. In Proceedings of the 2024 ACM Conference on Fairness, Accountability, and Trans- parency(Rio de Janeiro, Brazil)(FAccT ’24). Association for Computing Machinery, New York, NY, USA, 1475–1493. doi:10.1145/3630106.3658984

work page doi:10.1145/3630106.3658984 2024
[50]

Weisz, Shraddha Vijay Kumar, Michael Muller, Karen-Ellen Browne, Arielle Goldberg, Katrin Ellice Heintze, and Shagun Bajpai

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 arXiv 2025
[51]

Jim Whitehead. 2007. Collaboration in Software Engineering: A Roadmap. In Future of Software Engineering (FOSE ’07). IEEE, 214–225. doi:10.1109/FOSE.2007.4

work page doi:10.1109/fose.2007.4 2007
[52]

Wu, T.C.N

J. Wu, T.C.N. Graham, and P.W. Smith. 2003. A study of collaboration in software design. In2003 International Symposium on Empirical Software Engineering, 2003. ISESE 2003. Proceedings.IEEE, Rome, Italy, 304–313. doi:10.1109/ISESE.2003. 1237991

work page doi:10.1109/isese.2003 2003
[53]

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