Searcharxiv⌕ Search

arXiv subjects

Federica Sarro

Publications and source records attributed to Federica Sarro.

At least 19 recordsLinked to original sources

HerAgent: A Block-Level Checkpointing Harness for Coding-Agent Environment Setup

Modern coding agents rely on establishing executable software environments before they can perform software engineering tasks such as testing, debugging, and patch validation. Existing setup agents typically control progress at either single-command or whole-script granularity, making recovery either too local to remove polluted state or too coarse to preserve useful progress. We present HerAgent (Harness EnviRonment Setup Agent), a block-level harness for coding-agent environment setup. HerAgent's main contribution is semantic setup blocks: a single progress-control abstraction used for execution, validation, checkpointing, repair, and rollback. Evaluated against six prior agents on four environment-setup datasets, HerAgent improves setup success in every comparison, achieving the largest gains on Installamatic-Bench (52.0% to 85.0%) and SetupBench (46.3% to 70.4%). It also reduces setup costs by up to 94.5%, showing that block-level progress control improves reliability and efficiency.

cs.SE↗

Early Reflections on How Large Language Models are Reshaping Software Engineering Research

Large language models (LLMs) are radically reshaping software engineering (SE) research. Yet, their steep financial and computational costs raise questions about who participates in that change, and who does not. By analysing all 1,918 papers published in the ICSE 2019-2026 Research and SEIP tracks, we uncover a shifting and highly concentrated research landscape. China and the US dominate LLM-based SE research, appearing in 74% of LLM-based publications between 2023-2026, yet they diverge sharply in their use of commercial versus open-weight models. Beneath this national dominance lies extreme institutional concentration: just 5 institutions in China and 7 in the US appear in more than half of their respective nations' LLM-based output. In the US, only half of the unique institutions active in 2023-2026 participated in LLM-based research, whereas Singapore displays broader usage, with 11 of 15 active institutions participating in LLM-based work. Furthermore, across 2023-2026 Research-track papers, industry involvement is more prevalent in LLM-based work (23.4% vs 16.9%), and academia-only papers make up a smaller share (63.4% vs 70.9%). Crucially, we expose a gap in model usage across industry and academia. SEIP track papers lean strongly towards commercial LLMs, with 77.4% featuring them and 40.5% using them exclusively. In contrast, only 21.2% of Research-track work relies strictly on commercial models, making greater use of open-weight models that typically support more sustainable and reproducible experiments. However, this divide warrants reflection on the extent to which SE research aligns with industry practice.

cs.SE↗

TerminalWorld: Benchmarking Agents on Real-World Terminal Tasks

We introduce TerminalWorld, a scalable data engine that automatically reverse-engineers high-fidelity evaluation tasks from "in-the-wild" terminal recordings. Processing 80,870 terminal recordings, the engine yields a full benchmark of 1,530 validated tasks, spanning 18 real-world categories, ranging from short everyday operations to workflows exceeding 50 steps, and covering 1,280 unique commands. From these, we curate a Verified subset of 200 diverse, manually reviewed tasks. Comprehensive benchmarking on TerminalWorld-Verified across eight frontier models and six agents reveals that current systems still struggle with authentic terminal workflows, achieving a maximum pass rate of only 62.5%. Moreover, TerminalWorld captures real-world terminal capabilities distinct from existing expert-curated benchmarks (e.g., Terminal-Bench), with only a weak correlation to their scores (Pearson r=0.20). The automated engine makes TerminalWorld authentic and scalable by construction, enabling it to evaluate agents in real-world terminal environments as developer practices evolve.

cs.AI↗

Psychological Safety Framework in Pull-based Open Source Projects

Psychological safety (PS) refers to the belief that team members can speak up, ask questions, and make mistakes without fear of negative consequences. Although PS has been studied in traditional software teams, less is known about how it may appear in pull-based open-source software development, where contributors are self-directed and often collaborate voluntarily. This paper introduces a theory-informed framework for understanding how PS may be reflected in pull request (PR) interactions. We investigate the framework through a mixed-methods approach combining repository-based analysis and a survey of OSS contributors. First, we constructed a PS index using nine observable PR interaction indicators extracted from 60,685 PRs across 26 GitHub repositories. Second, we surveyed 57 OSS contributors about their perceived PS and experiences of corresponding PR interactions. All nine surveyed interaction indicators were significantly and positively associated with perceived PS. However, the repository-based index was not significantly associated with survey-reported PS. Contributors' open-ended responses further highlighted the importance of feedback quality, opportunities to participate, and how PR outcomes are interpreted. Together, our framework and mixed-methods findings provide initial insights into how PS may be reflected in PR interactions, highlighting the importance of both PR interaction patterns and contributors' experiences.

cs.SE↗

Equal Access, Unequal Gains? GitHub Copilot and Productivity Among Developers with Disabilities

Generative AI tools are increasingly used in software development and have been associated with benefits such as faster task completion and improved perceived productivity. However, whether these benefits extend across different developer populations remains unclear. This is especially relevant for developers with disabilities, whose work can already be impacted by accessibility barriers. Yet, evidence remains limited across a broader range of disability groups. This study investigates whether the wider availability of GitHub Copilot is associated with changes in productivity among GitHub users who self-identify as having a disability. Using publicly available profile and repository data, we curated a dataset of 199 developers across multiple disability groups and compared their activity before and after GitHub Copilot became freely available. We found that most disability groups showed a descriptive pattern of fewer commits but more code modified. In several disability groups, the distribution of developers across commit activity levels shifted toward both lower and higher level, leaving fewer developers at moderate level. However, we found no evidence that changes in commits or net lines modified differed across disability groups. These findings suggest that the wider availability of GitHub Copilot cannot be associated with a broad increase or decrease in observable development activity, while patterns of change varied across developers and disability groups.

cs.SE↗

Hybrid LLM-Deterministic Pipelines for Enterprise-Scale Code Migration at Bloomberg

Large organizations carry a long tail of infrastructure migrations that are worth doing but rarely urgent enough to compete with feature work, because each one costs significant engineering time per repository. This paper reports on our industrial experience from Automated Uplift, a multi-month initiative applying LLM-assisted migration pipelines across thousands of Bloomberg repositories. We examine two distinct production campaigns: a heterogeneous Python packaging migration (approx. 1,900 candidate repositories) and a uniform C++ build system migration (approx. 6,700 candidate repositories). Together, these campaigns generated 2,333 pull requests, resulting in 729 successful migrations. We detail our hybrid architectural solution which maximizes deterministic processing, confines the LLM to bounded file transformations within a pre-computed context, and incorporates runtime production telemetry (such as execution logs and usage traces). Our findings show that generating migrations turned out to be the easier part; the bottleneck was the cost, for owning teams, of reviewing, testing, and deploying them. These costs were lowered when changes could be verified directly in the pipeline before opening a PR (as with C++ compilation and test validation), and when the population was uniform enough for fixes to carry over from one repository to the next. We conclude by distilling our experience and findings into actionable, transferable patterns for architecting hybrid LLM-deterministic pipelines and scaling code migrations across the enterprise

cs.SE↗

In the Driver's Seat: A Multi-Company Study on the Reality of Autonomous Driving System Testing

Autonomous driving systems (ADS) are increasingly deployed in complex real-world environments, creating strong demands for rigorous testing to establish their functionality and safety. However, ADS testing remains difficult because practitioners must determine not only what and how to test, but also whether the resulting evidence is sufficient to support progression and release decisions. To understand how this is handled in practice, we conducted semi-structured interviews with experts involved in ADS development and testing across nine companies in six countries. Through thematic analysis, we examined how practitioners organize ADS testing to produce and assess evidence, and what limits confidence in that evidence. Our findings show that industrial ADS testing can be understood as an evidence-building process involving three recurring activities: planning what evidence is needed, producing and evaluating evidence across complementary testing environments, and deciding when testing is sufficient. We further identified recurring limitations concerning scenario adequacy, simulation and deployment fidelity, test execution and observability, and assurance and decision sufficiency. Practitioners reported several approaches for addressing these limitations, although important gaps remain. Based on these findings, we propose an evidence-centered closed-loop testing framework that connects testing intent, scenario selection, evidence production, acceptance decisions, and operational feedback. The study provides an industry-grounded account of how ADS testing is organized, where confidence in current testing breaks down, and how testing processes can be structured more systematically.

cs.SE↗

From Research to Practice: An Interactive Rapid Review of Autonomous Driving System Testing in Industry

Autonomous driving systems (ADS) are increasingly deployed in real traffic, yet testing remains fundamentally challenging due to open environments, complex scenarios, and the lack of established processes and acceptance criteria. Despite extensive research, a gap persists between academic advances and their applicability in industrial practice. To address this, we conduct an interactive rapid review in collaboration with 21 practitioners from a leading automotive company. Practitioners identified 12 key challenges in ADS testing, and prioritised two as the most critical issues, namely approaches to and completeness of testing for End-to-End (E2E) ADS. We analyzed 17 research studies relevant to these two challenges, most of which focus on generating critical testing scenarios, and subsequently assessed their relevance and applicability in practice. Our study provides the first practitioner-driven review and evaluation of current ADS testing research, reveals practical challenges in ADS testing, offers rapid insights for practitioners, and highlights the need for more context-aware, industry-relevant solutions to bridge the gap between research and practice.

cs.SE↗

When Code Becomes an LLM Call: An Empirical Study of Call-Site Contracts in Agentic Systems

Software quality has long rested on specifications that state what code must do, and on testing and verification that check that the code does it. Agentic systems change this foundation: they replace parts of their logic, such as choosing the next tool, judging whether an action is allowed, or writing code to run, with calls to a large language model (LLM). The program still relies on what this logic must guarantee, but the model's behavior is not fixed by code, varies across runs, and can be steered by its input. The guarantee must therefore come from the program around each LLM call site, as a contract of pre-conditions, prompt constraints, and post-conditions. We present an empirical study of these contracts in 496 LLM call sites of 40 popular open-source agentic systems (13.4 MLOC, four languages). Using a multi-agent pipeline validated by 17,428 human judgments, we trace where every model output flows, derive an expected contract for each call site without access to its code, and compare it with the contract that the code implements. We find that 48% of LLM outputs reach control flow or execution, and 73% of these never reach a person. Programs enforce 78% of their constraints in code, but in the prompt, 67% of the constraints are only requested from the model. Although 82% of call sites are checked before and after the call, 63% of the expected constraints are unmet and only 5.3% of call sites satisfy their whole contract; ten recurring patterns explain 99% of the gaps. 38 mechanisms behind these gaps trigger at runtime, and a small code fix that enforces the expected constraint stops all 38. Our results show that the presence of checks says little about their adequacy, and we derive implications for agent developers, framework maintainers, and researchers.

cs.SE↗

OpenRUA: Robot-Use Agents Are Zero-Shot Visuomotor Policies

Coding agents are extending their reach into the physical world by writing and executing robot control programs. One might expect the agents to use the existing mature software stack that engineers have developed over decades to access sensors and control motion. Yet prior work primarily engineers complex custom harnesses to orchestrate agents for robot use, particularly by prescribing specialized workflows and providing bespoke interfaces. This raises the question: "Is such additional harness engineering necessary?" We introduce OpenRUA, a zero-abstraction harness that bypasses bespoke abstraction layers by providing off-the-shelf coding agents with only terminal access to the robot's native software interface ROS 2. OpenRUA employs a minimalist workspace-as-harness design, only offering ROS 2 documentation and basic tools while leaving the coding agent to organize its own work without orchestrating any agentic workflow. Within this workspace, OpenRUA recasts perception as file I/O and manipulation as coding. With Claude Code powered by Claude Opus 5, OpenRUA achieves success rates of 99.0% on CaP-Bench and 87.0% on LIBERO-PRO, demonstrating that an off-the-shelf coding agent can serve as a zero-shot visuomotor policy through the robot's native interface, without bespoke primitives or task-specific training. Under this minimalist design, further analysis reveals striking emergent behaviors of coding agents: (1) For perception, the agent spontaneously writes programs that process raw sensory inputs and derive metric measurements in 96.80% of episodes. (2) For manipulation, the agent spontaneously builds motion-control clients (e.g., gripper control) in 95.87% of episodes and closed-loop control programs (e.g., adjusting motion based on sensor feedback) in 50.13% of episodes. Our code is available at https://github.com/terminalworld/OpenRUA.

cs.RO↗

Reusing Battle-tested Code: A Systematic Literature Review of Automated Software Transplantation

Software reuse remains a fundamental challenge in software engineering, often caught between the security risks of external libraries and the reliability concerns of generative AI. Automated software transplantation offers a compelling alternative by enabling the direct extraction and integration, into new host systems, of battle-tested logic (code that has already survived the rigors of production, possibly over many years of extensive in-production use). This paper presents a systematic literature review to evaluate the current state-of-the-art and identify the remaining barriers preventing this technology from becoming a mainstream engineering practice. We identified 27 distinct automated software transplantation approaches. Our analysis reveals that while the adaptation of code is highly automated, significant bottlenecks remain in the manual prerequisite steps of organ location and test suite augmentation. We conclude with a research roadmap that suggests how these manual obstacles might be overcome, including the strategic use of Large Language Models to assist in identifying and verifying high-value, production-hardened logic for transplantation.

cs.SE↗

Characterizing the Landscape of Open-Source Satellite Software

Satellites have become fundamental components of modern technological systems, supporting critical infrastructure in communication, navigation, Earth observation, and scientific research. As space exploration advances and demand for satellite-enabled services grows, reliance on complex, heterogeneous satellite software continues to increase. A systematic understanding of the satellite software landscape is therefore increasingly important, yet existing studies still lack a comprehensive empirical examination. To address this gap, we present the first characterization study of open-source satellite software, examining its ecosystem and development practices. We mine and analyze 22,286 satellite-related GitHub projects through three research questions on popularity trends (RQ1), software goals (RQ2), and development practices (RQ3). First, we characterize the temporal evolution of projects and active developers, revealing increasing popularity. Second, through manual inspection of 646 projects, we construct a taxonomy of 43 software-goal categories spanning conceptual design, datasets, system implementation, simulation, testing, and tools. Third, we conduct an in-depth analysis of projects with source code, revealing a highly heterogeneous and task-specialized ecosystem with 66 programming languages and diverse implementation strategies. Finally, we summarize key findings and derive actionable implications for satellite developers and researchers.

cs.SE↗

The Green Software Landscape: A Systematic Mapping Study on Evolution, Applications, Software Lifecycle, and Best Practices

Energy consumption and climate change have made sustainability critical in Software Engineering (SE), driving the emergence of Green SE. Over the past 15 years, numerous solutions for sustainable software systems have been published by the SE community, offering a rich resource for analyzing the field's evolution. To explore this, we conducted a systematic mapping study of Green SE research published between 2010 and 2024. We collected 390 publications, categorizing them by application domain (e.g., mobile, cloud, AI) and research type (e.g., optimisation study, benchmarking, literature review Additionally, we analyzed a representative subset of 79 papers to classify the key elements-such as hardware, measurement, stability, and replicability-considered during energy measurement experiments. Our findings indicate that SE conferences host the majority of energy-related literature. Notably, Green SE studies surged in popularity starting in 2023, largely driven by AI-related publications. Optimization and benchmarking emerged as the most prevalent research types. Ultimately, we aim to inform the SE community about current approaches to energy concerns, highlight critical experimental practices, and advocate for continued action toward more sustainable software engineering.

cs.SE↗

Pomona: Continuous Code Quality Improvement via Small, Agentic Pull Requests at Bloomberg

In this industrial experience paper, we present Pomona, a lightweight agentic tool that utilises agent skills for continuous code quality improvement. Inspired by the Kaizen (TM) philosophy, Pomona automates a cycle of discovery and incremental repair: a Scanning skill identifies tasks and prioritises them in a backlog, while a Repair skill generates small, easily reviewable pull requests (PRs). This design enables frequent, low-risk improvements while maintaining engineer trust and reducing technical debt. We evaluated Pomona at Bloomberg through a three-month team deployment and a questionnaire distributed to senior engineers. The results are promising: 32/39 PRs (82.1%) were merged with a median time-to-close of just over two hours. Moreover, 10/12 surveyed engineers expressed a desire to adopt Pomona, praising its small diff sizes and focus on code quality. Since our evaluation, another team has adopted Pomona. We conclude with actionable insights for deploying agents in industry.

cs.SE↗

SkillMOO: Multi-Objective Optimization of Agent Skills for Software Engineering

Agent skills are increasingly used to configure coding agents for software engineering (SE) tasks, yet current practice treats them as static, hand-crafted assets, or evolved on pass rate alone. This is insufficient: a skill can improve task success while substantially raising token cost, or introducing misleading guidance. We argue that SE agent skill bundles can be treated as multi-objective search objects and present SkillMOO, a framework that evolves skill bundles through LLM-proposed edits and NSGA-II Pareto selection on pass rate and inference cost. Evaluated across all 16 SkillsBench SE tasks, SkillMOO achieves the top pass rate rank on 11 of 12 non-zero-pass tasks while achieving cost reductions of up to 31.7% over static bundles, with pass rate gains up to 21 percentage points. Analysis of 38 skill edits shows that pruning and substitution dominate successful operations, offering actionable principles for skill bundle design. Thereby, the current practice of deploying skills without cost-aware validation leaves better skill configurations unexplored, motivating a new class of cost-aware, search-based skill engineering.

cs.SE↗

How Do Practitioners Build SE Agents? Insights from a Mixed-Methods Study

The rise of Software Engineering (SE) agents, i.e., LLM-based agents that can understand large codebases and carry out engineering tasks with limited human intervention, has been marked by rapid advances and adoption, but little is known about how developers build these systems in practice: existing studies mine repositories or examine deployment, but few investigate how SE agents are constructed. Through semi-structured interviews with 20 practitioners from 12 organizations and an online survey of 80 practitioners, this paper is the first to study how SE processes are changing in the development of SE agents and what challenges developers face. We find that as implementation becomes cheaper, bottlenecks shift rather than disappear: long-standing work in requirements, coordination, and deployment becomes more visible, while reviewing generated code and evaluating agent behavior become new and increasingly central forms of work. We characterize a seven-stage workflow and five process shifts, including a move toward evaluation-driven development, in which evaluation is increasingly defined early and steers iteration, and the emergence of specifications as first-class artifacts that teams test and version alongside code. We further identify six challenges that teams face, together with 12 corresponding practices they use or propose to address them, including unreliable evaluation signals, comprehension debt as code outpaces understanding, and behavioral changes introduced by provider-side model updates.

cs.SE↗

Failure as a Process: An Anatomy of CLI Coding Agent Trajectories

Large language model (LLM) coding agents are increasingly deployed to autonomously perform software engineering tasks in terminal-based environments, making their reliability a growing concern. Existing empirical studies investigate why coding agents fail, yet they largely treat failure as a final outcome rather than a temporal process, providing limited insight into how failures emerge, evolve, and become unrecoverable. We present the first large-scale empirical study of CLI coding-agent failure trajectories, introducing a process-oriented framework that analyzes failure through its onset, evolution, and recovery across execution trajectories. We first collect 3,843 execution trajectories generated by seven frontier models across three coding-agent scaffolds (OpenHands, MiniSWE, and Terminus2) on Terminal-Bench, then carefully filter them to obtain 1,794 complete and valid trajectories for manual annotation (over 63,000 execution steps), from which we derive 14 findings spanning failure occurrence, root causes, recovery, and cross-system consistency. Our findings show that coding-agent failures are predominantly driven by epistemic errors, typically begin within the first few execution steps, and often remain hidden until recovery is no longer possible, suggesting that improving coding-agent reliability requires earlier validation and intervention rather than relying solely on final-outcome evaluation.

cs.SE↗

SafeTune: Search-based Harmfulness Minimisation for Large Language Models

The widespread adoption of Large Language Models (LLMs) raises concerns about the potential harmfulness of their responses. In this paper, we first investigate the harmfulness of responses from four general-purpose LLMs. Next, we propose SafeTune, a multi-objective search-based approach to mitigate harmfulness while increasing response relevance through hyperparameter tuning and system prompt engineering. Our initial evaluation shows that SafeTune significantly reduces the rate of harmful responses generated by Qwen3.5 0.8B and increases prompt-response relevance (both with a large effect size). Among the parameters we explore, we also find that encouraging greater repetition in responses is most impactful in reducing harmfulness while increasing relevance.

cs.SE↗