Software Engineering

Ask about this topic

Overview

Software engineering studies how people design, build, test, deploy, and maintain software, with the goal of making systems reliable and useful as requirements change. Work spans requirements and architecture, code quality, testing and debugging, security, software evolution, and team practices, using approaches such as static analysis, model-based engineering, search-based testing, and empirical studies. Large language models and agents are increasingly used for coding, repair, testing, documentation, and repository understanding, with evaluations moving from isolated tasks toward repository-level and long-term maintenance benchmarks such as SWE-bench and continuous-integration tasks. A central challenge is turning success on bounded tasks into dependable software over time: integration, maintainability, security, and changing requirements remain difficult, making specifications, executable tests, human review, and transparent evaluation important.

Latest papers

CardsList

274 papers25 papers in the last four weeks, up 19% on the four weeks before. 0.1% of all new papers.

Aug 20, 2026

From Agent Behaviour to Agent-Friendly Documentation: An Empirical Study of How Coding Agents Discover, Read, and Write Technical Documentation

Technical documentation is written for human developers, but an increasing share of software changes is now authored by autonomous coding agents. Which documents they consult, when, and what follows remain unknown. We conduct a behaviour-grounded study of agent-documentation interaction across two public datasets: 557 agentic coding sessions from SWE-chat, yielding 94,813 development events including 3,033 documentation interactions; and 33,097 agentic pull requests from AIDev, with 690,260 classified file-level change records. Four findings challenge current documentation practice. First, agents' documentation work is dominated by agent-facing artefacts: instruction files and working notes account for 60.5% of all documentation interactions, versus 10.6% for classical technical documentation and 1.3% for API references. Second, the link between consultation and code editing is unresolved: the adjacent transition probability is 0.002 and the unadjusted three-event lift 1.05, whereas a stage-adjusted model places it above unity (OR 1.33 [1.09, 1.62]); documentation creation is elevated unadjusted (lift 1.67) but its adjusted interval includes unity. Third, no explicit documentation-based validation sequence was observed, and consultation is associated with less immediate testing (lift 0.23, cluster CI 0.08-0.45; adjusted OR 0.39 [0.25, 0.60]). Fourth, consultation is self-initiated (70.2%) far more often than failure-driven (7.5%), and documentation trails code: among multi-commit pull requests changing both, code is touched first 4.7x more often. From these traces we derive a descriptive model of agent-documentation interaction as a two-lobed cycle rather than a linear journey, and show that two widely assumed properties of "agent-friendly" documentation - actionability and verifiability - lack consistent behavioural support. We release our pipeline, coding scheme, and event-level data.

Zhijun Gao, Jing Chen

Peking University Beijing, China

Software EngineeringCoding Agents
AskPDF
Aug 20, 2026

Specification-delta-driven data governance: an empirical study of the «spec-delta» as the unit of change in lakehouse data platforms

Spec Driven Development SDD has consolidated the idea that the specification rather than the code should be the primary artefact governing AI assisted work. Tools such as GitHub Spec Kit, and proposals such as Constitutional SDD, have formalised this principle in the software domain, while the executable data-contracts literature has extended it to schema and quality enforcement at run time. Nevertheless, the treatment of the specification delta OpenSpec's core idea that every change should produce a reviewable increment of requirements as the unit of change in data platforms remains empirically unexplored, even though many data-platform changes are contractual (new datasets, service-level agreements, metric semantics, access policies) rather than purely code changes. This work formalises the spec-delta concept, proposes a taxonomy of data platform changes according to their suitability for incremental specification, and defines a controlled experiment comparing a spec-delta-driven workflow against a conventional code pull-request workflow without a delta. The response variables are discovery to deployment time, the density of defects reaching the Silver and Gold lakehouse layers, cross-tool metric divergence, and reviewer cognitive load measured with NASA TLX. The paper explicitly reserves a demonstration-and-laboratory section for instantiation on a real lakehouse environment. The contribution is not a tool but reproducible evidence and an applicability guide that helps to avoid the up front over specification antipattern.

Pablo Ramirez Amador

PhD Candidate in Computer Science — Universidad Abierta Interamericana (UAI) Zaragoza, Spain · PhD in Computer Science — Universidad Abierta Interamericana (UAI), Argentina. Zaragoza, Spain.

Software Engineering
AskPDF
Aug 20, 2026

SWE-bench Science: Can Coding Agents Resolve Engineering Tasks in Science?

Software increasingly functions as part of the scientific instrument itself, making failures in scientific code capable of compromising not only program behavior but also the evidence underlying scientific conclusions. Yet existing evaluations of coding agents largely emphasize aggregate task success, providing limited insight into why agents fail when repairing scientific software. We introduce SWE-bench Science, a repository-level benchmark for scientific software engineering comprising 119 tasks from 98 GitHub repositories across 20 scientific domains. Each task is organized into one of three paradigms: Issue-driven, Expert-exploratory, and Engineering-integration. Even the best-performing agent, Claude Code with Opus-5 (max), achieves a pass@1 below 50%, highlighting the substantial challenges posed by scientific software engineering. We identify four recurring failure mechanisms: deficits in scientific knowledge or abstraction, misguided exploration or surface-level repair, incomplete repair coverage or system integration, and failures to generalize scientific knowledge beyond observed cases in our analysis. We further conduct a paired ablation that removes explicit scientific guidance while preserving the repository and executable engineering context. The results show that scientific knowledge is not uniformly beneficial: well-grounded information can constrain repair and improve average performance and token efficiency, whereas poorly aligned guidance can induce anchoring and does not necessarily improve exact repair success. Together, SWE-bench Science provides a broad testbed for studying both the capabilities and failure mechanisms of coding agents in scientific software engineering.

Zhipeng Xu, Jiahao Lu, Yining Zheng +2

Shanghai Innovation Institute · Fudan University

Software EngineeringAutomated Program RepairCoding AgentsSoftware Engineering BenchmarksLLM Agent Reliability
AskPDF
Aug 20, 2026

Loreley: Repository-Scale Program Evolution with Quality-Diversity Search

Sequential agent search accumulates changes from its current champion but discards alternative branches; independent proposals preserve breadth but restart from the root. Loreley instead retains complete repository states in a Quality-Diversity (QD) archive and samples them as parents or supplies them as context for later edits. Candidates are Git commits produced in isolated worktrees and judged by a project-supplied evaluator. We compare configured Loreley QD, sequential champion editing, and independent root proposals in a matched Zstandard experiment: seven paired blocks and 48 physical candidate jobs per policy and block (1,008 total), with root-only initialization and each policy's native concurrency. Validation selected a winner at each budget checkpoint; an agent-hidden holdout measured the fixed candidate. At 48 jobs, QD was 0.135% below Sequential Champion (95% BCa interval for the paired effect: -0.556% to +0.161%) and 0.320% above Independent Root (-0.082% to +0.686%). Neither contrast established a QD advantage; Sequential had the highest observed 48-job mean and median. Archive retention and later sampling did occur. Four of seven final QD winners had a non-incumbent state in their primary-parent ancestry under a retrospective one-incumbent rule applied only to the observed QD stream. Including inspiration edges raised the count to six, without showing that supplied context caused an edit. Three earlier capability campaigns produced generation-4, multi-file improvements in two Python libraries and a separate Zstandard revision. Loreley engaged the intended stepping-stone mechanism, but the controlled experiment did not show an endpoint benefit at 48 jobs.

Mohan Chen

Code OptimizationSoftware EngineeringLLM Agent Workflow OptimizationQuality-Diversity Optimization
AskPDF
Aug 20, 2026

Escaping the Quicksand: A Call to Arms

Computing has been an astonishing success - but the accumulated technical debt exposes us all to huge costs in business and societal risk. For 75 years, we've built systems to prose specifications with test-and-debug development. That works well enough for industry to thrive, but it's an expensive and ineffective feedback loop, and leaves everyone relying on shaky foundations. Now, AI-enabled engineering is amplifying the success by reducing coding costs, but also amplifies the risks, by rapidly increasing technical debt, and by automating detection of the vulnerabilities therein. How can we do better? Research has long pursued mathematical proof of correctness, which, unlike testing, can cover all cases. This too has advanced massively, but it remains hard to apply, both technically and because of a deep-seated cultural disconnect. Instead, we argue for a pragmatic approach to flexible combinations of testing, specification, and proof, that provides more effective feedback loops for both AI and human development. Most simply, one can incrementally co-develop executable-as-test-oracle partial specifications alongside conventional prose descriptions, code, and tests. This clarifies design and makes testing much more discriminating. Developers can and should do it today. Or, even better, one can use specifications that support the full gamut of testing, property-based testing, symbolic execution, and proof. This enables a range of intertwined feedback loops, again both for AI and humans, from cheap testing to more expensive proof. However, making it really practical needs semantics infrastructure: specifications and tooling for the main programming languages and other abstractions, which we now more-or-less know how to build, but which is not yet in place. We call the community to arms to create and deploy it - to enable a future built on firmer ground.

Peter Sewell, Jean Pichon-Pharabod

University of Cambridge, UK · Aarhus University, Denmark

Property-Based TestingSoftware EngineeringFormal VerificationAutomated Software Testing
AskPDF
Aug 19, 2026

Building real-time digital twin instances with Function+Data Flow: user evaluation and extension for iterative pipelines

Digital twins (DTs) increasingly leverage artificial intelligence (AI) and machine learning (ML) pipelines, both to build real-time DTs from high-fidelity simulations and to instantiate them with historical data. However, engineering these pipelines remains largely ad-hoc: pipelines are hard to specify, validate, and reuse, with scarce dedicated tooling. Function+Data Flow (FDF) addresses this by defining a visual domain-specific language (DSL) that represents functions (ML models) explicitly, enabling their composition and reuse. We implemented FDF in DesCartes Builder, an integrated modeling environment supporting FDF-based DT synthesis and validation. In this paper, we report on an empirical user study evaluating whether FDF and DesCartes Builder can make AI-based DT development more accessible and reliable. Participants implemented a representative real-time DT prototype within DesCartes Builder, and we measured perceived usability and feature adequacy through quantitative and qualitative measures. Our results indicate that DesCartes Builder and FDF achieve a good level of usability across a broad range of potential users, and particularly for the intended audience of domain experts. The study additionally surfaces concrete strengths and areas for improvement of both the tool and the underlying FDF framework. Informed by these findings, we propose H-FDF, a Hierarchical extension of FDF supporting iterative and modular pipelines, enabling the formal specification of more complex DT pipelines such as dual training. Our findings suggest that integrated, model-driven platforms are a promising direction to transform AI-based DT engineering into a disciplined modeling practice.

Eduardo de Conto, Blaise Genest, Arvind Easwaran +2

College of Computing and Data Science, Nanyang Technological University, 50 Nanyang Avenue, Singapore, 639798, Singapore. · CNRS, IPAL Lab, France.

Model-Driven EngineeringDigital TwinsSoftware Engineering
AskPDF
Aug 18, 2026

What Makes Software Issue Resolution Tasks Difficult for Agents?

Background. Advances in agentic systems are simultaneously, and rapidly, saturating benchmarks. Despite this often discussed phenomena, benchmark scores remain difficult to interpret due to the lack of control and characterization of task difficulty. More specifically, we currently have little understanding of what makes one task harder than another, and to what extent task difficulty is predictable from static task properties. Aims. We propose a measurement framework to investigate and systematically quantify what structural properties of software tasks correspond to agent success rates for issue resolution tasks. Method. We conducted a large scale empirical study on CoderForge-Preview, the largest open dataset of coding agent trajectories to date, by extracting features across task patch, repository and prompt. We evaluated the predictive power of each feature against task outcomes using ensemble methods, SHAP attribution, and effect size analysis. Results We found that task difficulty is substantially predictable from static features (AU C = 0.863) and is largely driven by patch fragmentation and repository scale. Prompt linguistic features become visible among top contributors for tasks in the mid-band, revealing a layered structure of difficulty. Conclusion. The difficulty of an issue resolution task is encoded in its structure. This enables static, pre-hoc difficulty estimation and lays the groundwork for difficulty-controlled benchmark construction for evaluation of agents.

Ebtesam Al-Haque, Brittany Johnson

Department of Computer Science, George Mason University, Fairfax, VA

Item Difficulty EstimationSoftware EngineeringLLM Agent EvaluationSoftware Engineering Benchmarks
AskPDF
Aug 17, 2026

Software Engineering for AI-driven Building Operation

Building operations are energy-inefficient. Artificial Intelligence (AI)-driven control systems promise benefits through optimization and predictive control, but deploying them in real buildings reveals a significant software engineering (SE) challenge. SE for AI practices assume digital environments where failures mean poor user experience. Buildings are different. A bad control decision wastes energy irreversibly, violates occupant comfort, or accelerates equipment wear. Although actual safety-critical failures are rare, as real building automation systems are inherently fault-tolerant, the physical and lasting nature of even minor failures fundamentally changes SE4AI requirements. Rooted in two interdisciplinary research projects in civil engineering and computer science that target the AI-driven optimization of building operations, we identify the missing perspectives in SE4AI that currently stymie the successful deployment of AI-based systems for building operations. We further share lessons learned and best practices, and discuss broader implications for engineering AI-driven building operations and cyber-physical systems more generally. Our work proposes a foundation for SE4AI in systems where failure has physical consequences - one the research agenda below will need to validate.

Philipp Zech, Sascha Hammes, Johannes Weninger +2

University of Innsbruck, Tyrol, Austria · Bartenbach - The Lighting Innovators, Wattens, Austria · University of Applied Sciences Burgenland, Austria

Software EngineeringAI ControlCyber-Physical SystemsSafety-Critical ControlBuilding Energy Management
AskPDF
Aug 15, 2026

The Quality of Claude AI-authored Python Tests Is Not Weaker Than Human-authored Tests

We evaluate the quality of Claude AI-written Python tests against human-written Python tests from two established open-source projects Django and Pandas. Hundreds of tests per corpus are scored under one identical protocol. Using one-sided non-inferiority bounds, we find that the tests written by recent Claude models (Sonnet/Opus 4.6 and later) are no weaker than the two human-written corpora. In this study: (i) the AI-written corpus is tests from real tools, not synthetic tests generated in isolation against a fixed target, the setup used by every other AI-test-generation study we are aware of; (ii) every test is individually scored under three independent fault-injection protocols plus a seven-axis qualitative design rubric, allowing methods to cross-validate each other; (iii) tests are scored individually, rather than suite-level, identifying exactly which specific tests need attention.

Douglas J. Leith

Trinity College Dublin Dublin, Ireland

Software EngineeringCode Generation EvaluationAutomated Test Generation
AskPDF
Aug 14, 2026

Engineering Signals of Human-AI Collaboration in the Agentic Coding Era: A Longitudinal Analysis of 33,228 Pull Requests from vLLM and SGLang with Implications for Biomedical AI Agents and Bioinformatics Pipeline Developmen

The rapid adoption of AI coding assistants and autonomous agentic development systems has coincided with major changes in the pace and structure of open-source software engineering. Yet empirical longitudinal evidence of these changes at the team level remains limited. We present a descriptive longitudinal analysis of seven engineering metrics: pull request (PR) throughput, cycle time, contributor diversity, PR comment density, merge rate, new-author participation, and PR size. Metrics were computed from all merged PRs in two high-velocity AI infrastructure repositories, vLLM (February 2023-June 2026; 18,290 PRs) and SGLang (January 2024-June 2026; 14,938 PRs). We segment development into four eras aligned with major changes in AI-assisted software development and examine human- and bot-authored activities. Both projects show substantial increases in development velocity and AI-developer collaboration signals. PR throughput increased 21x in vLLM and 17.9x in SGLang, while bot-authored PRs accounted for less than 0.2% of this growth, indicating that the increase was overwhelmingly human-driven. In the latest era, median cycle time was 1.04 days for vLLM and 0.62 days for SGLang, while P90 cycle times reached 16.8 and 14.3 days, respectively. Monthly unique authors increased steadily in both projects, suggesting broader contributor participation. PR comment density increased 4.2x in vLLM and 3.8x in SGLang, with bot comments contributing an estimated 15-20% of the increase. In contrast, PR size remained relatively stable across eras. Overall, AI-assisted development is associated with higher throughput, broader contributor participation, and increased AI-developer collaboration signals in high-velocity open-source software development.

Jiada Li, Xuesong Ye, Olamide Olowoniyi

Georgia Institute of Technology, Atlanta, GA, 30332 · Independent Researcher, Albany, NY, 12210

Open-Source Software DevelopmentHuman-AI CollaborationAI-Assisted Software DevelopmentSoftware Engineering
AskPDF
Aug 13, 2026

PandasCorpus: A Resource of Real-World Pandas Workflows and Usage Patterns

Pandas has emerged as the de facto library for data processing and machine learning, widely used for tasks, such as data loading, transformation, and analysis. Despite its ubiquity, there has been limited systematic investigation into how Pandas is used in real-world projects and how typical workflows are composed in practice. To address this gap, we introduce PandasCorpus, a dataset curated from GitHub repositories that captures real-world Pandas workflows at scale. In this work, a workflow refers to Pandas-based code contained in Jupyter notebooks, a prevalent medium for writing, executing, and sharing data analysis code. The dataset comprises 139k notebooks from approximately 100k repositories and captures more than 4M Pandas API calls spanning 136 distinct operations. Beyond dataset construction, we characterize workflows using structural and Pandas-specific features and analyze notebook evolution between 2015 and 2025. Our study examines code executability, notebook size, and recurring sequences of Pandas operations, providing empirical insights into how Pandas is used in practice. The resulting corpus offers a reusable resource for studying data analysis workflows, Pandas usage patterns, and library-aware code composition. Both the dataset and the extraction pipeline are publicly available via GitHub and Zenodo.

Syrym Abdikhan, Mazhar Hameed

Gisma University of Applied Sciences Potsdam, Germany

Software Engineering
AskPDF
Aug 13, 2026

Does ISO-Grounded NFR Specification Improve LLM Code Generation? A Comparison of Rich and Structured Interventions against a Natural-Language Baseline

In LLM-based code generation, Non-Functional Requirements (NFRs) are often specified as terse one-line phrases. We ask whether grounding those specifications in ISO/IEC 25010 Quality Model, either as rich natural-language prose (NL-rich) or as structured JSON (Structured), improves code generated on HumanEval/HumanEval-ET compared to a RobuNFR-style one-line baseline (NL-simple). We evaluate four NFRs (performance, error handling, code smell, readability) with ten prompt variations per condition under a fixed model snapshot and paired non-parametric analysis. Primary finding: ISO-grounded enrichment improves static quality proxies (unreadability density falls across all four NFRs (e.g., Performance 0.88 -> 0.69 for NL-rich)) and reduces sensitivity to prompt wording, but does not reliably improve functional correctness; for error handling, extended-test pass rate decreases, suggesting tension between defensive coding patterns and exact-output benchmarks. Secondary finding: when ISO content is held constant, NL-rich and Structured differ negligibly in correctness (|delta| <= 0.023), indicating that semantic content matters more than JSON-vs-prose format. Practitioners should invest in standard-grounded NFR content rather than serialization form. A fully traceable replication package is provided.

Joào Pedro Monteiro Pereira, Vinicius Cardoso Garcia

Centro de Informática, Universidade Federal de Pernambuco Recife, PE, Brazil

LLM Code GenerationCode GenerationSoftware EngineeringCode Generation Evaluation
AskPDF
Aug 12, 2026

Specification-first convergence with an AI coding agent: a case study of dismantling a core architectural invariant across 189 files in a 717k-line codebase with no test oracle and no human code review

This paper reports a single, fully instrumented case study of a large-scale architectural refactoring by an AI coding agent under a specification-first protocol, with no human review of the generated code and no pre-existing oracle to validate the target behaviour. The task, dismantling a central invariant across a large interdependent codebase, was assessed by the author as effectively infeasible through incremental refactoring, the kind of change that conventionally calls for a rewrite instead. Under the protocol described here, the agent completed it successfully. The system is a 717,725-line production TypeScript application across 3,648 files. The task required dismantling a core lifetime invariant: the guarantee that a UI panel remains open for the duration of an AI request. The target behaviour was that a streaming generation survives the closing of its panel and can be reattached, on reopening, to the same live stream with no loss or duplication. The protocol: formal specification by the agent, 14 refinement cycles auditing that specification against the source code, atomic implementation, a compile/test feedback loop, then 17 verification cycles auditing the code against the frozen specification. Across 31 audit passes, 201 defects were corrected before any human executed the program. The convergence criterion was empirical: two consecutive verification passes returning zero findings. The change touched 189 files (31 new); with the extraction phase, the two commits total 288 files, 34,770 insertions, 16,422 deletions. Across the first and roughly thirty later sessions, the software behaved as specified, no bug observed. Elapsed: three days; cost: USD 2,430. The full specification and raw session logs, 1,500+ pages in French, are published as evidence, allowing inspection of the process and submission to a language model for consistency checking.

Joel Abenhaim

AI Sovereign Labs, Paris, France

Software EngineeringAI Agent ReliabilityAI Coding AgentsAutomated Software EngineeringAutomated Code Refactoring
AskPDF
Aug 12, 2026

Instruction Alignment for Binary Code Representation Learning

Binary code representation learning is a fundamental problem in software security and reverse engineering. Existing methods mainly learn function-level embeddings that capture coarse-grained semantic relationships between binary functions, but they largely ignore fine-grained instruction-level correspondences. This limitation misses valuable supervision signals available from compiler debug information, which can support the learning of more accurate and interpretable binary code representations. We propose to leverage instruction alignment knowledge to further improve binary code representation learning. Our preliminary study reveals that models finetuned for function-level binary code similarity exhibit substantially better instruction alignment than their pre-trained model, suggesting a strong correlation between instruction alignment and function-level embedding quality. Motivated by this observation, we design a training approach that explicitly incorporates instruction alignment as an auxiliary training objective. Our experiments show that instruction alignment training improves retrieval accuracy and provides more discriminative signal for the model's similarity judgments.

Huaijin Wang, Shuai Wang

Shandong University · Hong Kong University of Science and Technology

Software EngineeringRepresentation LearningSoftware Reverse Engineering
AskPDF
Aug 11, 2026

GitSkills: A Dataset of Agent Skills on GitHub

An agent skill is a folder containing a SKILL.md file with instructions for a language-model agent, optionally accompanied by scripts and reference files. The agent loads the skill when it judges that a task matches the skill description. Anthropic introduced the format in October 2025 as an open specification. Nine months later, public GitHub repositories hold millions of skill files. Skills are unlike the artifacts that software engineering researchers usually mine: they are written mainly in natural language, a model selects them probabilistically at run time, and no compiler or type checker verifies the selection. Skills also have no central registry or package manager; developers reuse them by copying folders between repositories. How developers write, reuse, and maintain skills is therefore an empirical question, and no existing dataset records this population. We present GitSkills, a dataset of 3,797,117 SKILL.md files collected from 282,200 public repositories in July 2026. The dataset retains every file occurrence with its repository, path, and content hash. We group identical files into 1,877,981 distinct contents and enrich one representative per group with the full text, parsed front matter, folder contents, repository metadata, and, for a subset, the commit history of the file. A single self-contained SQLite file supports research on the adoption, reuse, structure, authorship, maintenance, and security of agent skills.

Giuseppe Destefanis, Daniel Graziotin, Matteo Vaccargiu +1

University College London, United Kingdom · University of Hohenheim, Stuttgart, Germany · University of Cagliari, Italy

Software EngineeringMining Software Repositories
AskPDF
Aug 10, 2026

Detecting Soft Skills in ML Engineering Roles CVs

Soft skills shape collaboration among ML engineers, data scientists, and software engineers building ML-enabled systems, yet what we know about them comes almost entirely from the demand side. Job advertisements, surveys, and hiring manager interviews capture what employers ask for. How candidates themselves articulate these competencies has not been studied, and existing CV-mining work is both keyword-based, so it cannot see skills conveyed through narrative, and descriptive, reporting frequency rankings without testing whether group differences exceed sampling variation. We close both gaps. Using a balanced corpus of 300 curated CVs spanning the three roles, we extract explicitly listed and implicitly narrated soft skills with an LLM-based pipeline validated against a human-annotated ground truth, a distinction that existing extractors were not designed to make. We then convert the demand-side literature's claims into 13 falsifiable hypotheses about role signatures, seniority progression, and disclosure style, and test them with effect sizes under family-wise error control, so that candidate-side data can corroborate or contradict the demand-side account rather than merely illustrate it. Eleven hypotheses are supported, one partially, and one refuted. Candidates disclose soft skills through narrative rather than keyword lists by roughly three to one, and most so for the competencies employers value most: leadership, coordination, and mentoring (88-96% narrative). Seniority nearly triples the odds of articulating leadership. That competency, assumed universal in prior work, is articulated by software engineers at half the rate of their peers. Technical candidates do articulate soft skills, but a keyword-based screening systematically misses them.

Aidin Azamnouri, Nouran Ayad, Justus Bogner +1

Chair of Software Engineering, TUM School of Computation, Information and Technology, Technical University of Munich, Heilbronn, Germany · Software and Sustainability (S2) Group, Vrije Universiteit Amsterdam, Amsterdam, The Netherlands

Software Engineering
AskPDF
Aug 7, 2026

Coupling Planning with Episodic Memory in LLM Agents for Software Issue Resolution

Resolving a real software issue with a large language model (LLM) agent is a long repair episode, often tens to hundreds of steps spanning exploration, hypothesis, implementation, and verification. Success depends on both the base model's local reasoning and the agent's ability to maintain an evolving plan and remember observations across phases. Existing repository-level agents typically strengthen planning or memory in isolation, leaving long trajectories vulnerable to stale evidence, repeated failed edits, and verification inferred from the agent's own claims instead of execution evidence. We present PMCoder, an issue-resolution agent that couples a hierarchical phase planner with episodic memory. The coupling is bidirectional: the current plan phase conditions memory retrieval, while memory-derived trajectory statistics inform stuck detection and replanning. When available, issue-reproduction verdicts ground verification progress in execution evidence rather than self-reported completion. On SWE-bench Verified, PMCoder resolves an average of 2525 more cases (+5.0+5.0pp) than a harness-matched baseline, with gains persisting even where the reproduction gate never fires. Further Verified-500 evaluations show the same positive direction across Claude Haiku 4.5, DeepSeek-V4-Flash, and an OpenHands port, with at least 1414 additional resolved cases (+2.8+2.8pp). Separately, evaluation on TerminalWorld's official sample suggests that the plan-memory substrate transfers beyond issue reports. Ablation and trajectory analyses show where the gains come from: coupling planning and memory outperforms either component alone and reduces repeated failed actions, empty-patch exits, and context-window exhaustion.

Jiahao Zhang, Yifan Zhang, Yu Huang

Vanderbilt University

Software EngineeringSoftware Engineering AgentsLLM Agent MemoryLong-Horizon LLM AgentsLLM Agent Planning
AskPDF
Aug 6, 2026

JTA: Joint Testability Architecture for Scenario-Based Validation of Safety-Critical Software

Validation adequacy in safety-critical software depends on more than the system under test. Critical scenarios must be constructed under controlled conditions, execution evidence must be aligned into verdict-ready form, and abnormal outcomes must be attributable to actionable causes. Existing testability research remains largely artifact-centric and offers little architectural support for reasoning about the combined capability of the scenario, the test system, and the system under test. Joint Testability Architecture (JTA) addresses this gap by treating those three elements as a single object of analysis and design. It characterizes validation capability along three dimensions--controllability, observability, and isolability--and organizes them through three domains, three bridges, and an analysis-design-evaluation-refinement loop. JTA also introduces scenario contracts, joint capability assessment, validation blind-spot identification, and bridge-oriented design actions that map capability gaps to concrete improvements in control points, evidence organization, and attribution boundaries. An illustrative analysis of ArduPilot failsafe validation shows that link-loss scenarios are comparatively mature, whereas state-estimation anomaly scenarios remain harder to validate because evidence alignment and attribution semantics are weaker. JTA is not a replacement for existing testing or safety-analysis techniques; it provides an architectural basis for modeling, designing, and assessing scenario-based validation in safety-critical software.

Wenyao Xue, Jiandi Wang, Yichen Wang

Beihang University, Beijing, China

Software EngineeringAutomated Software TestingScenario-Based Testing
AskPDF
Aug 5, 2026

OctoLong: Mid-Training On Cross-Repository Code Contexts Enhances Long-Context Modeling

Context lengths of language models (LMs) have dramatically increased, driven by the demands for in-context learning, self-improvement, and long-horizon agentic workflows. However, existing long-context corpora are dominated by books, academic articles, and code repositories, which are finite and often lack long-distance dependencies. In this work, we introduce OctoLong, a context-engineering pipeline that instruments an AST parser, a language server backend, and a package manager to recursively retrieve code references, enabling the curation of dependency-rich code contexts up to millions of tokens long. We then train OctoLong-Instruct, a suite of capable long-context open LMs, derived from base models ranging in size from 600M to 14B parameters, via context-extension mid-training on a approx 50B-token mixture containing approx 6.2B tokens of OctoLong code contexts, followed by approx 10B tokens of instruction tuning. Our ablations and experimental evaluations against 18 strong long-context open-weight LMs show that supplanting just 12% of conventional context-extension corpora with OctoLong data yields substantial gains in long-range retrieval, long-term state tracking, repository-level code understanding, and downstream agentic tasks, while also enhancing API usage in regular coding scenarios.

Indraneil Paul, Falko Helm, Goran Glavaš +1

UKP Lab & Center for Applied Cybersecurity ATHENE, TU Darmstadt · CAIDAS, University of Würzburg

Software EngineeringLong-Context Language ModelingContinued PretrainingCode Language ModelsLLM Training
AskPDF
Aug 5, 2026

Scrouting: Cost-Aware Routing of Coding Agents by Scouting the Repository First

Frontier language models can resolve repository-level software issues, but each attempt is expensive, and existing routers select a model from the issue text alone. We present SuperScout, which routes after scouting the repository: a 7B searcher, SuperScout-7B, first explores the repository and produces a structured handoff whose reproduction claims are sandbox-verified, with false claims stripped before delivery. The searcher's hidden states, together with the task text, then feed a resume-based router that dispatches the task to one of four frontier fixers. Adding a new fixer requires no retraining. On the full Python slice of SWE-bench Pro (266 tasks) under the benchmark's official capped budget tier, SuperScout matches the best single model's solve rate (159 of 266 for SuperScout, 158 for the best model) at about a fifth of the total cost per solve, and the reported configuration sits above the random traffic-splitting baseline. A no-router ablation, always the cheapest fixer with the handoff, ties the routed system on this benchmark, so the handoff rather than the routing decision carries the result. A paired calibration study points to the mechanism: the handoff appears to redistribute rather than add solving ability, lifting the three cheaper fixers while slightly hurting the strongest, though at N=99N=99 the per-fixer effects are directional only; the searcher's hidden states improve cost routing on the calibration labels while the handoff's own text does not. The searcher's compute adds less than half a cent of GPU time per task.

Ishaan Bhola, Adithyan Krishnan, Mukunda NS

SuperAGI Research

Software EngineeringSoftware Engineering AgentsLLM Agent Routing
AskPDF
Aug 5, 2026

RepoProbe: Benchmarking Architecture-Aware Repository Comprehension with Checklists

The integration of Large Language Models (LLMs) into software engineering has shifted the focus from function-level generation to repository-scale assistance. However, existing benchmarks largely rely on bug reports from GitHub Issues, which often allow models to bypass genuine understanding via pattern matching on error logs. This misalignment under-measures Edit Bias, which refers to premature generation, where models prematurely propose code modifications instead of understanding the existing repository architecture. Furthermore, current LLM-as-a-Judge scalar scoring suffers from high variance and low interpretability. This work introduces RepoProbe, a novel benchmark for evaluating repository-level code understanding through open-ended Q&A using GitHub Discussions, which focuses on open-ended architectural inquiries rather than defect reporting. To ensure rigorous evaluation, we propose a Checklist-Based Verification Protocol that decomposes answers into atomic, verifiable facts, thereby replacing subjective ratings with objective verification. Our evaluation of state-of-the-art (SOTA) LLMs reveals a persistent gap between high clarity and evidencegrounded technical correctness. It also quantitatively confirms the prevalence of edit bias, in which models prioritize code generation instead of architectural analysis. Finally, we demonstrate that our verification protocol significantly improves evaluation reliability compared to traditional evaluations with scalar scoring.

Yuexi Yang, Alyssa Wu, Ji Luo +4

Zhejiang University · Hunyuan, Tencent · Ningbo Global Innovation Center, Zhejiang University

Software EngineeringLLM EvaluationLLM Answer VerificationSoftware Engineering Benchmarks
AskPDF
Aug 5, 2026

The Order Is the Guarantee: Verifier-Budgeted Code Deletion with Static-First Learned Proposals

Frontier coding models now match or exceed strong human reference points on programming benchmarks, yet benchmark success does not imply maintainable software. Prompt-driven "vibe coding" is additive: new branches, guards, and fallbacks accumulate faster than obsolete logic is removed. We study the inverse problem-how an Al system should remove code when execution-verification capacity is finite. We formulate redundant-code reduction as proposal scheduling: a ranker orders single-statement deletion candidates, an execution suite accepts the first candidate that passes, and a budget bounds how many candidates may be tested. Our central observation is that candidate order, not model confidence, is the control surface a deployment can reason about. DELSCOUT instantiates two schedules. Given representative target-domain validation, a five-slot budget spends three slots on deterministic shortest-first candidates and two on complementary learned candidates; across nine MBPP replications with 0.5B, 0.6B, and 8B rankers this raises verified-deletion coverage by 9.5% relative (+6.7 accepted tasks) while consuming slightly fewer verifier calls than the matched static baseline. Without such validation the same rankers can lose coverage under shift, so we instead evaluate the complete static prefix first and append learned candidates only afterwards; for a deterministic verifier this makes coverage and character reduction non-decreasing by construction, at a measured 4.8-62.5% increase in verifier calls. MBPP+ then erases the in-domain advantage, showing that scheduling governs search while the test suite alone governs what "preserving behavior" means. The result is an auditable division of labor: models widen the search for removable code, order bounds the damage a mis-ranked proposal can do, and execution retains authority over every committed deletion.

Ruitong Li, Binjie Guo, Aisheng Mo +4

University of Hong Kong · Zhejiang University · Dalian University of Technology +1

Software Engineering
AskPDF
Aug 4, 2026

From Social Coding to Agentic Coding: Productivity and Relational Reconfiguration in Open-Source Communities

Open-source software communities are a form of digital public infrastructure that not only produces code, but also generates public knowledge and interpersonal relationships through visible collaboration. Generative coding agents (CAs) are an advanced tool to improve development efficiency while shifting part of activities from public human interaction to private human-agent loops. We study this shift using an LLM-based multi-agent simulation initialized with real GitHub data from 1,084 active developers and their repository relationships. After a warm-up with historical commits, we branch the same community state into parallel No-CA and CA conditions for 4-week simulations. CA introduction increases planned and completed tasks by 34.0% and 39.0%, respectively, and reduces median completion time from 45 to 20 minutes. However, adoption reaches only 26.0%, and the gains concentrate among developers who are already more active and well connected. CAs also restructure task execution pathways. Direct human-human interaction declines from 32.4% to 11.6%, while CA-involved modes increase to 57.3%, including 40.3% completed through CA-assisted self-loops. Public knowledge generated under CA condition also provides less support for later tasks. On a standardized retrieval benchmark, the CA corpus achieves 22.3% knowledge coverage, far below the 81.1% achieved by the real-human corpus, and requires more retrieval steps with a lower success rate. These results reveal a productivity-public knowledge tension: coding agents increase technical production, but more work shifts to agent-mediated or private loops, leaving public records less useful to future contributors.

Mengying Zhou, Yongjie Yin, Yang Chen

School of Computing and Artificial Intelligence, Shanghai University of Finance and Economics · College of Computer Science and Artificial Intelligence, Fudan University

Software EngineeringOpen-Source Software DevelopmentAI Coding AgentsHuman-AI Collaboration
AskPDF
Aug 4, 2026

HyperFL: Query-Adaptive Representation Learning for Software Fault Localization

Software fault localization identifies the code locations responsible for reported issues and is a fundamental step toward automated debugging and program repair. Recent retrieval-based approaches formulate fault localization as a dense retrieval task by learning a shared embedding space between issue reports and source code. However, these methods encode all issue reports using a fixed query representation, despite the substantial diversity of real-world issue reports in length, structure, and debugging information. To address this limitation, we propose HyperFL, a query-adaptive representation learning framework for software fault localization. HyperFL employs a lightweight hypernetwork to generate query-specific LoRA parameters for the query encoder, enabling dynamic query adaptation while keeping the code encoder fixed and reusable. Experiments on a real-world issue localization benchmark demonstrate that HyperFL consistently improves retrieval performance across multiple embedding backbones, achieving up to 13.3% relative improvement in function-level MRR@10 and 16.7% relative improvement in Hit@1 over the state-of-the-art method SweRank. Further analysis shows that HyperFL learns distinct adaptation patterns for different issue characteristics, highlighting the effectiveness of query-adaptive representations for software issue localization.

Shuai Shao, Yiming Zeng, Yu Zhao +1

University of Connecticut · University of Cincinnati

Software EngineeringRepresentation Learning
AskPDF
Aug 2, 2026

From AI Technical Debt to Agentic Technical Debt: A Systematic Mapping of Root Causes and Manifestations in Agentic AI Systems

The emergence of Agentic AI systems, characterized by autonomous reasoning, multi-agent collaboration, tool orchestration, adaptive decision-making, and persistent memory, represents a fundamental shift from traditional AI pipelines to dynamic software ecosystems. While AI Technical Debt (AITD) has been widely studied in machine learning and software engineering, existing models assume static, component-level architectures and fail to capture the dynamic and emergent behaviors of agentic environments. To address this gap, this paper introduces Agentic Technical Debt (AgTD), defined as technical debt that emerges, accumulates, propagates, and amplifies due to the autonomous and collaborative nature of Agentic AI systems. Building on our prior systematic scoping review of 31 AITDs across seven root-cause categories, we employ a theory-informed transformation methodology to reinterpret these debts in Agentic AI through direct transformation, contextual transformation, and manifestation expansion. We present the first systematic mapping of established AITDs to their agentic manifestations, showing how conventional debts evolve into system-level liabilities, including memory inconsistencies, orchestration fragility, cascading failures, and unsafe autonomous decision-making. Our findings show that technical debt extends beyond software artifacts to encompass agent behaviors, coordination mechanisms, and interactions among agents, tools, and execution environments. We further examine its implications for AI Trust, Risk, and Security Management (AI TRiSM), highlighting impacts on trustworthiness, governance, security, operational resilience, and Sustainability Technical Debt. Overall, this work establishes AgTD as a foundational software engineering construct and provides a transformation framework, taxonomy, and research agenda for managing technical debt in autonomous multi-agent AI systems.

Muhammad Tukur, Hayatullahi B. Adeyemo, Tao Chen +5

School of Computer Science, University of Birmingham, Edgbaston, UK · College of Science and Engineering, HBKU, Qatar · Computing and Informatics, Bournemouth University, Bournemouth, UK +2

Software EngineeringMulti-Agent SystemsAgentic AI
AskPDF
Jul 31, 2026

Studying, Identifying, and Fixing Hidden Technical Debt in AI-Intensive Cyber-Physical Systems

Artificial Intelligence (AI) components are increasingly pervasive in several software systems, including Cyber-Physical Systems (CPSs). AI-CPS are used in several domains, including autonomous vehicles, industry, home automation, robotics, and healthcare. Being composed of hardware, AI components, and conventional modules, AI-CPS can exhibit technical debt (TD) that is peculiar and potentially more challenging than that of conventional systems. This thesis aims to characterize AI-CPS TD and propose approaches for its identification and repair. In a first phase, we characterize AI-CPS TD by analyzing AI ecosystems and AI-CPS repositories, as well as interviewing developers. Based on the acquired knowledge, we define approaches to identify and mitigate such TD. Finally, we plan to develop and validate an automated tool that supports agentic AI solutions to monitor, govern, and repay AI-CPS TD.

Beena

University of Sannio Benevento, Italy

Software EngineeringCyber-Physical Systems
AskPDF
Jul 29, 2026

SWE-NFI: Studying and Benchmarking Coding Agents for Non-Functional Improvements

Although coding agents have achieved impressive performance on correctness-oriented benchmarks, their ability to make behavior-preserving non-functional improvements (NFIs) remains underexplored. In real-world software development, developers continuously improve software quality without changing observable behavior, yet existing benchmarks primarily evaluate functional correctness and provide limited support for assessing these non-functional improvements. In this paper, we present SWE-NFI, a benchmark for evaluating coding agents on NFIs beyond functional correctness. SWE-NFI contains 188 tasks constructed from real merged pull requests in open-source Python projects. We operationalize five developer-oriented NFI aspects into 92 executable rules and develop an evaluation suite that first applies task-specific functional preservation checks to assess whether key properties of the original code are preserved and then performs rule-based NFI evaluation. For outputs that pass these checks, we measure NFI improvement as the change in the normalized rule score for the task's target aspect relative to the original code. We evaluate eight commercial and open-source agent configurations and run each configuration five times on every task. At most 70.0% of valid agent outputs satisfy all task-specific functional preservation checks. Among outputs that pass these checks, NFI performance varies substantially across aspects. In particular, all evaluated configurations achieve mean Logic Patterns improvements between 0.0 and 1.3, below the Human Reference mean of 1.5. Our benchmark and findings provide a reproducible foundation for evaluating coding agents on non-functional improvements and identifying the NFI aspects where further advances are needed.

Pengyu Xue, He Yang Yuan, Xin Wang +6

York University Toronto, Ontario, Canada · The Hong Kong University of Science and Technology (Guangzhou) Guangzhou, Guangdong, China · Singapore Management University Singapore, Singapore +2

Software EngineeringCoding AgentsSoftware Engineering Benchmarks
AskPDF
Jul 28, 2026

ContractHIL-HLS: Contract-Aligned Multi-Agent Workflow with Hardware-in-the-Loop Feedback for HLS Design

This paper presents ContractHIL-HLS, a contract-aligned multi-agent workflow for practical high-level synthesis (HLS) engineering. The workflow makes three contributions. First, it introduces a structured contract as the semantic-alignment and task-execution artifact that translates natural language requirements into explicit interfaces, constraints, validation checks, and rollback rules. Second, it incorporates hardware information into the feedback loop by feeding HLS, Vivado, PYNQ runtime, power, and failure evidence back into generation, thereby extending LLM-assisted HLS from kernel code toward system- and board-level closure. Third, it decomposes agents by semantic lowering and execution tasks rather than by conversational roles: a Contract Agent lowers natural language into the contract, an HTML Agent renders the contract as persistent structured HTML, and a Hardware-in-the-Loop Agent implements and revises the design with measured evidence. We evaluate ContractHIL-HLS in two parts. On 94 locally executable HLS-Eval tasks, the structured contract provides the largest small design gain, improving the estimated single-sample testbench pass rate from 64.0% to 70.2%; the full flow reaches 70.4% pass@1 and 76.6% pass@5. Because HLS-Eval does not exercise board-level design, we also validate ContractHIL-HLS on a board tested ML-KEM/ML-DSA post-quantum cryptography (PQC) secure-message accelerator, where the retained dual-bitstream organization reduces six-message average text runtime from 207.3 ms to 52.4 ms with positive routed WNS on both images while preserving decrypted-message verification. We open-source our work at BJUT-CS316-LAB/ContractHIL-HLS (https://github.com/BJUT-CS316-LAB/ContractHIL-HLS).

Jingbo Zhang, Haoxiang Sun, Wenbo Wang +1

Beijing University of Technology

Software EngineeringMulti-Agent LLM SystemsElectronic Design AutomationLLM-Based Program Synthesis
AskPDF
Jul 25, 2026

On AI Safety and Security Technical Debt in Engineering AI-Enabled Systems

Artificial intelligence (AI) systems are increasingly deployed in high-stakes domains such as healthcare, autonomous driving, finance, and education. While these systems offer powerful data-driven and adaptive capabilities, their complexity, rapid evolution, and dependence on dynamic data pipelines introduce new forms of engineering liability collectively referred to as AI Technical Debts (AITDs). AITDs arise from root causes spanning data governance, model implementation, algorithm design, architectural decisions, operational processes, documentation practices, and testing adequacy. Unlike conventional technical debt, many AITDs are latent and propagate across tightly coupled AI pipelines, leading to maintenance challenges, reliability degradation, and heightened safety or security risks. Guided by the principles of AI Trust, Risk, and Security Management (AI TRiSM), this study reinterprets technical debt through the interconnected dimensions of trustworthiness, focusing on AI safety and security technical debts. We conduct a systematic review of 60 primary studies and identify 31 distinct types of AITD, which are organized into a root-cause-oriented taxonomy comprising seven classes. The analysis examines how these debts map to 18 trust-related concerns, including 6 safety hazards and 12 security vulnerabilities. To support mitigation, the review synthesizes 34 actionable guidelines (8 safety and 26 security) targeting the prevention, detection, and reduction of AITDs across the AI lifecycle. Building on these findings, we introduce AITD-MAP, an integrated framework that connects the AITD taxonomy, quality and risk impacts, and mitigation strategies into a unified structure for risk-aware AI engineering. The framework aims to assist AI software engineers in making AI safety and security technical debts visible, understanding their root causes, and mitigating their presence.

Muhammad Tukur, Hayatullahi B. Adeyemo, Tao Chen +5

Computer Science, University of Birmingham, Edgbaston, UK · CSE, HBKU, Qatar · Computing and Informatics, Bournemouth University, UK +3

Software EngineeringAI Risk ManagementAI Safety
AskPDF
Jul 24, 2026

AI4PLE: A Methodology for Integrating AI into Product Line Engineering

Reuse-based development has become increasingly important in the creation of complex systems, offering significant opportunities to reduce costs, improve quality, and accelerate time-to-market. Product Line Engineering (PLE) provides a systematic approach to realizing this potential by enabling the efficient creation, management, and customization of product families by reusing shared assets and capabilities. PLE involves addressing numerous complex decisions, including feature selection, variability management, and configuration optimization, which are critical to the success of a product line. Despite its promise, the systematic integration of Artificial Intelligence (AI) into PLE processes has not yet been comprehensively explored. In this paper, we propose a methodological framework to support the systematic integration of AI into PLE and evaluate its effectiveness through a multi-case study conducted in an industrial context.

Bedir Tekinerdogan

Information Technology, Wageningen University & Research Wageningen, The Netherlands

Software EngineeringAutomated Software EngineeringAI-Assisted Software Development
AskPDF