arXiv subjects

Emma Söderberg

Publications and source records attributed to Emma Söderberg.

9 recordsLinked to original sources

arXiv2026

Helpful but Fallible: Developer Experiences of AI Tools Under a Coordinated Industrial Roll-out

AI-enabled software development tools (AI-devtools) are being industrially adopted under strong expectations of productivity gains, yet developers' experiences of such roll-outs are underexplored. Organizations commit budgets, evaluate staff, and revise practice on a partial picture, since the evidence base is mainly tool evaluations, productivity metrics, and surveys, with few qualitative in-situ accounts of ongoing, coordinated roll-outs. We report a case study of a coordinated roll-out of AI-devtools at a large Swedish telecommunications company, investigating how developers experience the roll-out and how they anticipate their profession will change. We conducted semi-structured interviews with 12 software professionals across three sites, analyzed with process coding and thematic analysis, and interpreted through the extended Technology Acceptance Model (TAM2) as a post-hoc analytical lens. Our findings on use cases, productivity, frustrations, and tool limitations corroborate prior survey work. Beyond corroboration, the interviews surface a management-developer expectation gap that maps onto the TAM2 constructs of subjective norm and voluntariness, and show that participants weigh perceived risk heavily, a factor that TAM2 and similar acceptance models do not represent. AI-devtools emerge as helpful but fallible assistants whose value is shaped by organizational expectations, system scale, and developers' skills.

cs.SE↗

arXiv2026

Trust-Calibrated Code Review: A Participatory Design Study of Review Workflows for LLM-Generated Multi-File Changes

Background: Developers increasingly review multi-file code changes generated by LLM-based agents, yet no validated end-to-end workflow or IDE tooling design exists for this scenario. Aims: We investigate (RQ1) the challenges developers face when reviewing LLM-generated multi-file changes and (RQ2) how developers envision effective workflows for this task. Method: In collaboration with JetBrains, we conducted a participatory design study structured using the double-diamond design process with Discover, Define, Develop, and Deliver phases. Industry practitioners participated in the Discover phase (N=17); seven of these returned for the Develop phase. The Define phase was an author-led synthesis. The Deliver phase produced a conceptual design and a high-fidelity semi-interactive prototype evaluated through a follow-up survey with N=43 practitioners. Results: Participants identified trust-calibration as the central challenge. The study yielded a three-level review workflow (overview, file-analysis, code snippet review) supported by seven design constructs (chunk, risk-per-line, risk-per-file, judge, walk-through, zooming in/out, and security cage). In the validation survey, all three workflow levels scored above the neutral midpoint (means 3.50--3.91 on a five-point scale). Of the respondents, 63% expected reduced overall review effort, and 52% reduced trust-assessment effort, relative to their current tools. These findings suggest that the design constructs indicate a positive direction for future tool development. Conclusions: Reviewing LLM-generated multi-file changes is a trust-calibration problem rather than a diffing problem. The three-level workflow and the seven constructs we report give tool designers a conceptual framework for building AI-ready code review tools that surface risk and confidence signals at the granularity at which developers allocate attention.

cs.SE↗

arXiv2026

GazePrinter: Visualizing Expert Gaze to Guide Novices in a New Codebase

Program comprehension is an essential activity in software engineering. Not only does it often challenge professionals, but it can also hinder novices from advancing their programming skills. Gaze, an emerging modality in developer tools, has so far primarily been utilized to improve our understanding of programmers' visual attention and as a means to reason about programmers' cognitive processes. There has been limited exploration of integrating gaze-based assistance into development environments to support programmers, despite the tight links between attention and gaze. We also know that joint attention is important in collaboration, further suggesting that there is value in exploring collective gaze. In this paper, we investigate the effect of visualizing gaze patterns gathered from experts to novice programmers to assist them with program comprehension in a new codebase. To this end, we present GazePrinter, designed to provide gaze-orienting visual cues informed by experts to aid novices with program comprehension. We present the results of a mixed-methods study conducted with 40 novices to study the effects of using GazePrinter for program comprehension tasks. The study included a survey, a controlled experiment, and interviews. We found that visualization of expert gaze can have a significant effect on novice programmers' behavior in terms of which path they take through the code base; with GazePrinter, novices took a path closer to the path taken by experts. We also found indications of reduced time and cognitive load among novices using GazePrinter.

cs.SE↗

arXiv2026

Echoes of AI: Investigating the Downstream Effects of AI Assistants on Software Maintainability

[Context] AI assistants, like GitHub Copilot and Cursor, are transforming software engineering. While several studies highlight productivity improvements, their impact on maintainability requires further investigation. [Objective] This study investigates whether co-development with AI assistants affects software maintainability, specifically how easily other developers can evolve the resulting source code. [Method] We conducted a two-phase controlled experiment involving 151 participants, 95% of whom were professional developers. In Phase 1, participants added a new feature to a Java web application, with or without AI assistance. In Phase 2, a randomized controlled trial, new participants evolved these solutions without AI assistance. [Results] Phase 2 revealed no significant differences in subsequent evolution with respect to completion time or code quality. Bayesian analysis suggests that any speed or quality improvements from AI use were at most small and highly uncertain. Observational results from Phase 1 corroborate prior research: using an AI assistant yielded a 30.7% median reduction in completion time, and habitual AI users showed an estimated 55.9% speedup. [Conclusions] Overall, we did not detect systematic maintainability advantages or disadvantages when other developers evolved code co-developed with AI assistants. Within the scope of our tasks and measures, we observed no consistent warning signs of degraded code-level maintainability. Future work should examine risks such as code bloat from excessive code generation and cognitive debt as developers offload more mental effort to assistants.

cs.SE↗

arXiv2026

Code for Machines, Not Just Humans: Quantifying AI-Friendliness with Code Health Metrics

We are entering a hybrid era in which human developers and AI coding agents work in the same codebases. While industry practice has long optimized code for human comprehension, it is increasingly important to ensure that LLMs with different capabilities can edit code reliably. In this study, we investigate the concept of ``AI-friendly code'' via LLM-based refactoring on a dataset of 5,000 Python files from competitive programming. We find a meaningful association between CodeHealth, a quality metric calibrated for human comprehension, and semantic preservation after AI refactoring. Our findings confirm that human-friendly code is also more compatible with AI tooling. These results suggest that organizations can use CodeHealth to guide where AI interventions are lower risk and where additional human oversight is warranted. Investing in maintainability not only helps humans; it also prepares for large-scale AI adoption.

cs.SE↗

arXiv2025

Code Review as Decision-Making -- Building a Cognitive Model from the Questions Asked During Code Review

Code review is a well-established and valued practice in the software engineering community contributing to both code quality and interpersonal benefits. However, there are challenges in both tools and processes that give rise to misalignments and frustrations. Recent research seeks to address this by automating code review entirely, but we believe that this risks losing the majority of the interpersonal benefits such as knowledge transfer and shared ownership. We believe that by better understanding the cognitive processes involved in code review, it would be possible to improve tool support, with out without AI, and make code review both more efficient, more enjoyable, while increasing or maintaining all of its benefits. In this paper, we conduct an ethnographic think-aloud study involving 10 participants and 34 code reviews. We build a cognitive model of code review bottom up through thematic, statistical, temporal, and sequential analysis of the transcribed material. Through the data, the similarities between the cognitive process in code review and decision-making processes, especially recognition-primed decision-making, become apparent. The result is the Code Review as Decision-Making (CRDM) model that shows how the developers move through two phases during the code review; first an orientation phase to establish context and rationale and then an analytical phase to understand, assess, and plan the rest of the review. Throughout the process several decisions must be taken, on writing comments, finding more information, voting, running the code locally, verifying continuous integration results, etc. Analysis software and process-coded data publicly available at: https://doi.org/10.5281/zenodo.15758266

cs.SE↗

arXiv2025

ACE: Automated Technical Debt Remediation with Validated Large Language Model Refactorings

The remarkable advances in AI and Large Language Models (LLMs) have enabled machines to write code, accelerating the growth of software systems. However, the bottleneck in software development is not writing code but understanding it; program understanding is the dominant activity, consuming approximately 70% of developers' time. This implies that improving existing code to make it easier to understand has a high payoff and - in the age of AI-assisted coding - is an essential activity to ensure that a limited pool of developers can keep up with ever-growing codebases. This paper introduces Augmented Code Engineering (ACE), a tool that automates code improvements using validated LLM output. Developed through a data-driven approach, ACE provides reliable refactoring suggestions by considering both objective code quality improvements and program correctness. Early feedback from users suggests that AI-enabled refactoring helps mitigate code-level technical debt that otherwise rarely gets acted upon.

cs.SE↗

arXiv2025

Study of the Use of Property Probes in an Educational Setting

Context: Developing compilers and static analysis tools ("language tools") is a difficult and time-consuming task. We have previously presented *property probes*, a technique to help the language tool developer build understanding of their tool. A probe presents a live view into the internals of the compiler, enabling the developer to see all the intermediate steps of a compilation or analysis rather than just the final output. This technique has been realized in a tool called CodeProber. Inquiry: CodeProber has been in active use in both research and education for over two years, but its practical use has not been well studied. CodeProber combines liveness, AST exploration and presenting program analysis results on top of source code. While there are other tools that specifically target language tool developers, we are not aware of any that has the same design as CodeProber, much less any such tool with an extensive user study. We therefore claim there is a lack of knowledge how property probes (and by extension CodeProber) are used in practice. Approach: We present the results from a mixed-method study of use of CodeProber in an educational setting, with the goal to discover if and how property probes help, and how they compare to more traditional techniques such as test cases and print debugging. In the study, we analyzed data from 11 in-person interviews with students using CodeProber as part of a course on program analysis. We also analyzed CodeProber event logs from 24 students in the same course, and 51 anonymized survey responses across two courses where CodeProber was used. Knowledge: Our findings show that the students find CodeProber to be useful, and they make continuous use of it during the course labs. We further find that the students in our study seem to partially or fully use CodeProber instead of other development tools and techniques, e.g. breakpoint/step-debugging, test cases and print debugging. Grounding: Our claims are supported by three different data sources: 11 in-person interviews, log analysis from 24 students, and surveys with 51 responses. Importance: We hope our findings inspire others to consider live exploration to help language tool developers build understanding of their tool.

cs.PL↗

arXiv2024

Does Co-Development with AI Assistants Lead to More Maintainable Code? A Registered Report

[Background/Context] AI assistants like GitHub Copilot are transforming software engineering; several studies have highlighted productivity improvements. However, their impact on code quality, particularly in terms of maintainability, requires further investigation. [Objective/Aim] This study aims to examine the influence of AI assistants on software maintainability, specifically assessing how these tools affect the ability of developers to evolve code. [Method] We will conduct a two-phased controlled experiment involving professional developers. In Phase 1, developers will add a new feature to a Java project, with or without the aid of an AI assistant. Phase 2, a randomized controlled trial, will involve a different set of developers evolving random Phase 1 projects - working without AI assistants. We will employ Bayesian analysis to evaluate differences in completion time, perceived productivity, code quality, and test coverage.

cs.SE↗