arXiv subjects

Federica Sarro

Publications and source records attributed to Federica Sarro.

At least 37 records · Page 2Linked to original sources

arXiv2026

ContextBench: A Benchmark for Context Retrieval in Coding Agents

LLM-based coding agents have shown strong performance on automated issue resolution benchmarks, yet existing evaluations largely focus on final task success, providing limited insight into how agents retrieve and use code context during problem solving. We introduce ContextBench, a process-oriented evaluation of context retrieval in coding agents. ContextBench consists of 1,136 issue-resolution tasks from 66 repositories across eight programming languages, each augmented with human-annotated gold contexts. We further implement an automated evaluation framework that tracks agent trajectories and measures context recall, precision, and efficiency throughout issue resolution. Using ContextBench, we evaluate four frontier LLMs and five coding agents. Our results show that sophisticated agent scaffolding yields only marginal gains in context retrieval ("The Bitter Lesson" of coding agents), LLMs consistently favor recall over precision, and substantial gaps exist between explored and utilized context. ContextBench augments existing end-to-end benchmarks with intermediate gold-context metrics that unbox the issue-resolution process. These contexts offer valuable intermediate signals for guiding LLM reasoning in software tasks.

cs.LG↗

arXiv2026

Prometheus: Towards Long-Horizon Codebase Navigation for Repository-Level Problem Solving

Large Language Models (LLMs) have shown remarkable capabilities in automating software engineering tasks, spurring the emergence of coding agents that scaffold LLMs with external tools to resolve repository-level problems. However, existing agents still struggle to navigate large-scale codebases, as the Needle-in-a-Haystack problem persists even with million-token context windows, where relevant evidence is often overwhelmed by large volumes of irrelevant code and documentation. Prior codebase navigation approaches, including embedding-based retrieval, file-system exploration, and graph-based retrieval, address parts of this challenge but fail to capture the temporal continuity of agent reasoning, rendering agents stateless and causing repeated repository traversals that hinder scalable planning and reasoning. To address these limitations, we present Prometheus, a memory-centric coding agent framework for long-horizon codebase navigation. Prometheus represents the repository as a unified knowledge graph to encode semantic dependencies and employs a context engine augmented with working memory that retains and reuses previously explored contexts to ensure continuity across reasoning steps. Built upon this engine, Prometheus integrates memory-enhanced navigation into a multi-agent system for automated issue resolution, encompassing issue classification, bug reproduction, patch generation, and verification. Comprehensive experiments are conducted on two widely used issue resolution benchmarks, i.e., SWE-bench Verified and SWE-PolyBench Verified. Powered by GPT-5, Prometheus achieves state-of-the-art performance with 74.4% and 33.8% resolution rates on the two benchmarks, ranking Top-6 and Top-1 among open-source agent systems, respectively. Our data and code are available at https://github.com/EuniAI/Prometheus.

cs.SE↗

arXiv2026

Empirical and Sustainability Aspects of Software Engineering Research in the Era of Large Language Models: A Reflection

Software Engineering (SE) research involving the use of Large Language Models (LLMs) has introduced several new challenges related to rigour in benchmarking, contamination, replicability, and sustainability. In this paper, we invite the research community to reflect on how these challenges are addressed in SE. Our results provide a structured overview of current LLM-based SE research at ICSE, highlighting both encouraging practices and persistent shortcomings. We conclude with recommendations to strengthen benchmarking rigour, improve replicability, and address the financial and environmental costs of LLM-based SE.

cs.SE↗

arXiv2026

FairRF: Multi-Objective Search for Single and Intersectional Software Fairness

Background: The wide adoption of AI- and ML-based systems in sensitive domains raises severe concerns about their fairness. Many methods have been proposed in the literature to enhance software fairness. However, the majority behave as a black-box, not allowing stakeholders to prioritise fairness or effectiveness (i.e., prediction correctness) based on their needs. Aims: In this paper, we introduce FairRF, a novel approach based on multi-objective evolutionary search to optimise fairness and effectiveness in classification tasks. FairRF uses a Random Forest (RF) model as a base classifier and searches for the best hyperparameter configurations and data mutation to maximise fairness and effectiveness. Eventually, it returns a set of Pareto optimal solutions, allowing the final stakeholders to choose the best one based on their needs. Method: We conduct an extensive empirical evaluation of FairRF against 26 different baselines in 11 different scenarios using five effectiveness and three fairness metrics. Additionally, we also include two variations of the fairness metrics for intersectional bias for a total of six definitions analysed. Result: Our results show that FairRF can significantly improve the fairness of base classifiers, while maintaining consistent prediction effectiveness. Additionally, FairRF provides a more consistent optimisation under all fairness definitions compared to state-of-the-art bias mitigation methods and overcomes the existing state-of-the-art approach for intersectional bias mitigation. Conclusions: FairRF is an effective approach for bias mitigation also allowing stakeholders to adapt the development of fair software systems based on their specific needs.

cs.SE↗

arXiv2025

A Comprehensive Study of Bugs in Modern Distributed Deep Learning Systems

In today's data-driven era, deep learning is vital for processing massive datasets, yet single-device training is constrained by computational and memory limits. Distributed deep learning overcomes these challenges by leveraging multiple GPUs or machines in parallel. While general-purpose frameworks (e.g., TensorFlow and PyTorch) provide distributed capabilities, these are often add-on features that demand significant manual effort for advanced parallelism, underscoring the need for specialized frameworks. This study conducts the first large-scale empirical analysis of practitioner challenges in dedicated distributed frameworks. We examine 849 real-world issues from DeepSpeed, Megatron-LM, and Colossal-AI and construct a taxonomy of 34 bug symptoms, 28 root causes, and 6 fix patterns. Crucially, we establish explicit mappings between symptoms, causes, and fixes across distributed training stages, enabling a systematic understanding of how issues emerge and are resolved. Our results show that 45.1\% of bug symptoms are unique to distributed frameworks, with setup failures, memory issues, and performance anomalies being the most prevalent. Moreover, 95\% of issues in the communication setup stage occur exclusively in distributed contexts. We also find over 60\% of cases can be resolved through version and dependency management, and distributed feature, API, and communication tuning. Based on these findings, we provide actionable implications.

cs.SE↗

arXiv2025

SustainDiffusion: Optimising the Social and Environmental Sustainability of Stable Diffusion Models

Background: Text-to-image generation models are widely used across numerous domains. Among these models, Stable Diffusion (SD) - an open-source text-to-image generation model - has become the most popular, producing over 12 billion images annually. However, the widespread use of these models raises concerns regarding their social and environmental sustainability. Aims: To reduce the harm that SD models may have on society and the environment, we introduce SustainDiffusion, a search-based approach designed to enhance the social and environmental sustainability of SD models. Method: SustainDiffusion searches the optimal combination of hyperparameters and prompt structures that can reduce gender and ethnic bias in generated images while also lowering the energy consumption required for image generation. Importantly, SustainDiffusion maintains image quality comparable to that of the original SD model. Results: We conduct a comprehensive empirical evaluation of SustainDiffusion, testing it against six different baselines using 56 different prompts. Our results demonstrate that SustainDiffusion can reduce gender bias in SD3 by 68%, ethnic bias by 59%, and energy consumption (calculated as the sum of CPU and GPU energy) by 48%. Additionally, the outcomes produced by SustainDiffusion are consistent across multiple runs and can be generalised to various prompts. Conclusions: With SustainDiffusion, we demonstrate how enhancing the social and environmental sustainability of text-to-image generation models is possible without fine-tuning or changing the model's architecture.

cs.SE↗

arXiv2025

Understanding Code Agent Behaviour: An Empirical Study of Success and Failure Trajectories

The increasing deployment of Large Language Model (LLM) agents for complex software engineering tasks has created a need to understand their problem-solving behaviours beyond simple success metrics. While these agents demonstrate impressive capabilities in automated issue resolution, their decision-making processes remain largely opaque. This paper presents an empirical study of agent trajectories, namely the execution traces capturing the steps agents take when attempting to resolve software issues. We analyse trajectories from three state-of-the-art code agents (OpenHands, SWE-agent, and Prometheus) on the SWE-Bench benchmark, examining both successful and failed attempts. Our investigation reveals several key insights into agent behaviour. First, we identify how distinct problem-solving strategies, such as defensive programming and context gathering, enable success in different scenarios. Second, we find that failed trajectories are consistently longer and exhibit higher variance than successful ones, with failure patterns differing significantly between agents. Third, our fault localisation analysis shows that while most trajectories correctly identify problematic files (72-81\% even in failures), success depends more on achieving approximate rather than exact code modifications. These and other findings unveiled by our study, provide a foundation for understanding agent behaviour through trajectory analysis, contributing to the development of more robust and interpretable autonomous software engineering systems.

cs.SE↗

arXiv2025

HotBugs.jar: A Benchmark of Hot Fixes for Time-Critical Bugs

Hot fixes are urgent, unplanned changes deployed to production systems to address time-critical issues. Despite their importance, no existing evaluation benchmark focuses specifically on hot fixes. We present HotBugs$.$jar, the first dataset dedicated to real-world hot fixes. From an initial mining of 10 active Apache projects totaling over 190K commits and 150K issue reports, we identified 746 software patches that met our hot-fix criteria. After manual evaluation, 679 were confirmed as genuine hot fixes, of which 110 are reproducible using a test suite. Building upon the Bugs$.$jar framework, HotBugs$.$jar integrates these 110 reproducible cases and makes available all 679 manually validated hot fixes, each enriched with comprehensive metadata to support future research. Each hot fix was systematically identified using Jira issue data, validated by independent reviewers, and packaged in a reproducible format with buggy and fixed versions, test suites, and metadata. HotBugs$.$jar has already been adopted as the official challenge dataset for the Search-Based Software Engineering (SBSE) Conference Challenge Track, demonstrating its immediate impact. This benchmark enables the study and evaluation of tools for rapid debugging, automated repair, and production-grade resilience in modern software systems to drive research in this essential area forward.

cs.SE↗

arXiv2025

GA4GC: Greener Agent for Greener Code via Multi-Objective Configuration Optimization

Coding agents powered by LLMs face critical sustainability and scalability challenges in industrial deployment, with single runs consuming over 100k tokens and incurring environmental costs that may exceed optimization benefits. This paper introduces GA4GC, the first framework to systematically optimize coding agent runtime (greener agent) and code performance (greener code) trade-offs by discovering Pareto-optimal agent hyperparameters and prompt templates. Evaluation on the SWE-Perf benchmark demonstrates up to 135x hypervolume improvement, reducing agent runtime by 37.7% while improving correctness. Our findings establish temperature as the most critical hyperparameter, and provide actionable strategies to balance agent sustainability with code optimization effectiveness in industrial deployment.

cs.SE↗

arXiv2025

Automated Repair of Ambiguous Problem Descriptions for LLM-Based Code Generation

The growing use of large language models (LLMs) has increased the importance of natural language (NL) in software engineering. However, ambiguity of NL can harm software quality, as unclear problem descriptions may lead to incorrect program generation. Detecting and resolving such ambiguity is challenging, motivating our introduction of the automated repair of ambiguous NL descriptions, which we approach by reducing code generation uncertainty and better aligning NL with input-output examples. Ambiguity repair is difficult for LLMs because they must understand how their interpretation of a description changes when the text is altered. We find that directly prompting LLMs to clarify ambiguity often produces irrelevant or inconsistent edits. To address this, we decompose this task into two simpler steps: (1) analyzing and repairing the LLM's interpretation of the description - captured by the distribution of programs it induces - using traditional testing and program repair, and (2) refining the description based on distribution changes via a method we call contrastive specification inference. We implement this approach in a tool called SpecFix and evaluate it using four state-of-the-art LLMs (GPT-4o, GPT-4o-mini, DeepSeek-V3, and Qwen2.5-Coder-32B-Instruct) on three popular code generation benchmarks (HumanEval+, MBPP+ and LiveCodeBench). Without human intervention or external information, SpecFix modified 43.58% of descriptions, improving Pass@1 on the modified set by 30.9%. This yields a 4.09% absolute improvement across the entire benchmark. Repairs also transfer across models: descriptions repaired for one model improve other models' performance by 10.48%.

cs.SE↗

arXiv2025

Generative AI for Testing of Autonomous Driving Systems: A Survey

Autonomous driving systems (ADS) have been an active area of research, with the potential to deliver significant benefits to society. However, before large-scale deployment on public roads, extensive testing is necessary to validate their functionality and safety under diverse driving conditions. Therefore, different testing approaches are required, and achieving effective and efficient testing of ADS remains an open challenge. Recently, generative AI has emerged as a powerful tool across many domains, and it is increasingly being applied to ADS testing due to its ability to interpret context, reason about complex tasks, and generate diverse outputs. To gain a deeper understanding of its role in ADS testing, we systematically analyzed 91 relevant studies and synthesized their findings into six major application categories, primarily centered on scenario-based testing of ADS. We also reviewed their effectiveness and compiled a wide range of datasets, simulators, ADS, metrics, and benchmarks used for evaluation, while identifying 27 limitations. This survey provides an overview and practical insights into the use of generative AI for testing ADS, highlights existing challenges, and outlines directions for future research in this rapidly evolving field.

cs.SE↗

arXiv2025

LLM-Guided Genetic Improvement: Envisioning Semantic Aware Automated Software Evolution

Genetic Improvement (GI) of software automatically creates alternative software versions that are improved according to certain properties of interests (e.g., running-time). Search-based GI excels at navigating large program spaces, but operates primarily at the syntactic level. In contrast, Large Language Models (LLMs) offer semantic-aware edits, yet lack goal-directed feedback and control (which is instead a strength of GI). As such, we propose the investigation of a new research line on AI-powered GI aimed at incorporating semantic aware search. We take a first step at it by augmenting GI with the use of automated clustering of LLM edits. We provide initial empirical evidence that our proposal, dubbed PatchCat, allows us to automatically and effectively categorize LLM-suggested patches. PatchCat identified 18 different types of software patches and categorized newly suggested patches with high accuracy. It also enabled detecting NoOp edits in advance and, prospectively, to skip test suite execution to save resources in many cases. These results, coupled with the fact that PatchCat works with small, local LLMs, are a promising step toward interpretable, efficient, and green GI. We outline a rich agenda of future work and call for the community to join our vision of building a principled understanding of LLM-driven mutations, guiding the GI search process with semantic signals.

cs.SE↗

arXiv2025

How Do Generative Models Draw a Software Engineer? A Case Study on Stable Diffusion Bias

Generative models are nowadays widely used to generate graphical content used for multiple purposes, e.g. web, art, advertisement. However, it has been shown that the images generated by these models could reinforce societal biases already existing in specific contexts. In this paper, we focus on understanding if this is the case when one generates images related to various software engineering tasks. In fact, the Software Engineering (SE) community is not immune from gender and ethnicity disparities, which could be amplified by the use of these models. Hence, if used without consciousness, artificially generated images could reinforce these biases in the SE domain. Specifically, we perform an extensive empirical evaluation of the gender and ethnicity bias exposed by three versions of the Stable Diffusion (SD) model (a very popular open-source text-to-image model) - SD 2, SD XL, and SD 3 - towards SE tasks. We obtain 6,720 images by feeding each model with two sets of prompts describing different software-related tasks: one set includes the Software Engineer keyword, and one set does not include any specification of the person performing the task. Next, we evaluate the gender and ethnicity disparities in the generated images. Results show how all models are significantly biased towards male figures when representing software engineers. On the contrary, while SD 2 and SD XL are strongly biased towards White figures, SD 3 is slightly more biased towards Asian figures. Nevertheless, all models significantly under-represent Black and Arab figures, regardless of the prompt style used. The results of our analysis highlight severe concerns about adopting those models to generate content for SE tasks and open the field for future research on bias mitigation in this context.

cs.SE↗

arXiv2025

When Prompts Go Wrong: Evaluating Code Model Robustness to Ambiguous, Contradictory, and Incomplete Task Descriptions

Large Language Models (LLMs) have demonstrated impressive performance in code generation tasks under idealized conditions, where task descriptions are clear and precise. However, in practice, task descriptions frequently exhibit ambiguity, incompleteness, or internal contradictions. In this paper, we present the first empirical study examining the robustness of state-of-the-art code generation models when faced with such unclear task descriptions. We extend the HumanEval and MBPP benchmarks by systematically introducing realistic task descriptions flaws through guided mutation strategies, producing a dataset that mirrors the messiness of informal developer instructions. We evaluate multiple LLMs of varying sizes and architectures, analyzing their functional correctness and failure modes across task descriptions categories. Our findings reveal that even minor imperfections in task description phrasing can cause significant performance degradation, with contradictory task descriptions resulting in numerous logical errors. Moreover, while larger models tend to be more resilient than smaller variants, they are not immune to the challenges posed by unclear requirements. We further analyze semantic error patterns and identify correlations between description clarity, model behavior, and error types. Our results underscore the critical need for developing LLMs that are not only powerful but also robust to the imperfections inherent in natural user tasks, highlighting important considerations for improving model training strategies, designing more realistic evaluation benchmarks, and ensuring reliable deployment in practical software development environments.

cs.SE↗

arXiv2025

It is Giving Major Satisfaction: Why Fairness Matters for Software Practitioners

Software practitioners often encounter workplace unfairness, such as unequal recognition and gender bias. While the link between fairness and job satisfaction has been established in other fields, its relevance to software professionals remains underexplored. This study examines how fairness perceptions relate to job satisfaction among software practitioners, focusing on both general trends and demographic-specific differences. We conducted an online survey of 108 software practitioners, followed by ordinal logistic regression to analyze the relationship between fairness perceptions and job satisfaction in software engineering contexts, with moderation analysis examining how this relationship varies across demographic groups. Our findings indicate that all four fairness dimensions (namely distributive, procedural, interpersonal, and informational fairness) significantly affect overall job satisfaction and satisfaction with job security. Among these, interpersonal fairness has the biggest impact. The relationship between fairness and job satisfaction is stronger for female, ethnically underrepresented, less experienced practitioners, and those with work limitations. Fairness in authorship emerged as an important factor for job satisfaction collectively, while fairness in policy implementation, high-demand situations, and working hours impacted specific demographic groups. This study highlights the role of fairness among software practitioners, offering strategies for organizations to promote fair practices and targeted approaches for certain demographic groups.

cs.SE↗

arXiv2025

Greening AI-enabled Systems with Software Engineering: A Research Agenda for Environmentally Sustainable AI Practices

The environmental impact of Artificial Intelligence (AI)-enabled systems is increasing rapidly, and software engineering plays a critical role in developing sustainable solutions. The "Greening AI with Software Engineering" CECAM-Lorentz workshop (no. 1358, 2025) funded by the Centre Européen de Calcul Atomique et Moléculaire and the Lorentz Center, provided an interdisciplinary forum for 29 participants, from practitioners to academics, to share knowledge, ideas, practices, and current results dedicated to advancing green software and AI research. The workshop was held February 3-7, 2025, in Lausanne, Switzerland. Through keynotes, flash talks, and collaborative discussions, participants identified and prioritized key challenges for the field. These included energy assessment and standardization, benchmarking practices, sustainability-aware architectures, runtime adaptation, empirical methodologies, and education. This report presents a research agenda emerging from the workshop, outlining open research directions and practical recommendations to guide the development of environmentally sustainable AI-enabled systems rooted in software engineering principles.

cs.SE↗

arXiv2025

SCOPE: Performance Testing for Serverless Computing

Serverless computing is a popular cloud computing paradigm that has found widespread adoption across various online workloads. It allows software engineers to develop cloud applications as a set of functions (called serverless functions). However, accurately measuring the performance (i.e., end-to-end response latency) of serverless functions is challenging due to the highly dynamic nature of the environment in which they run. To tackle this problem, a potential solution is to apply checks of performance testing techniques to determine how many repetitions of a given serverless function across a range of inputs are needed to cater to the performance fluctuation. However, the available literature lacks performance testing approaches designed explicitly for serverless computing. In this paper, we propose SCOPE, the first serverless computing-oriented performance testing approach. SCOPE takes into account the unique performance characteristics of serverless functions, such as their short execution durations and on-demand triggering. As such, SCOPE is designed as a fine-grained analysis approach. SCOPE incorporates the accuracy check and the consistency check to obtain the accurate and reliable performance of serverless functions. The evaluation shows that SCOPE provides testing results with 97.25% accuracy, 33.83 percentage points higher than the best currently available technique. Moreover, the superiority of SCOPE over the state-of-the-art holds on all functions that we study.

cs.SE↗

arXiv2025

Unveiling Overlooked Performance Variance in Serverless Computing

Serverless computing is an emerging cloud computing paradigm for developing applications at the function level, known as serverless functions. Due to the highly dynamic execution environment, multiple identical runs of the same serverless function can yield different performance, specifically in terms of end-to-end response latency. However, surprisingly, our analysis of serverless computing-related papers published in top-tier conferences highlights that the research community lacks awareness of the performance variance problem, with only 38.38% of these papers employing multiple runs for quantifying it. To further investigate, we analyze the performance of 72 serverless functions collected from these papers. Our findings reveal that the performance of these serverless functions can differ by up to 338.76% (44.28% on average) across different runs. Moreover, 61.11% of these functions produce unreliable performance results, with a low number of repetitions commonly employed in the serverless computing literature. Our study highlights a lack of awareness in the serverless computing community regarding the well-known performance variance problem in software engineering. The empirical results illustrate the substantial magnitude of this variance, emphasizing that ignoring the variance can affect research reproducibility and result reliability.

cs.SE↗