Searcharxiv⌕ Search

subject

cs.SE

cs.SE: explore 370 source-linked works published from 2025 to 2026, with original documents and citations.

This collection is a preview while coverage and quality are evaluated.

Search within this collection

Coverage and selection

Includes records with this source-supplied label or an explicit phrase match in their metadata. Matches indicate a mention, not proof that a paper uses a method or tests a material. Source versions are consolidated by DOI.

Sources: arxiv. Collection updated 2026-09-16. Counts describe this index, not the complete source archives.

arXiv2026

Who Maintains Agent Skills? A Longitudinal Study of Human-Governed, AI-Assisted Skill Maintenance

Lifelong LLM agents increasingly rely on external skill artifacts as one element for preserving and reusing capabilities over time. These skills (usually portable Markdown files such as SKILL.md) describe when and how to apply a capability and must be corrected, expanded, and consolidated as tools and usage patterns shift over deployment. Recent work seeks to automate skill curation, but it largely evaluates against automated baselines and treats human maintenance as an unmeasured bottleneck. We study that missing process directly. We mine the full commit histories of five public AI-skill repositories, a purposive sample of AI-tooling organizations, covering 873 commits, 143 skill files, and 254 substantive post-creation edits from October 2025 to June 2026. We code each edit with pre-registered governance, operation, and trigger-evidence codebooks. Three findings emerge. First, every substantive edit is authored or merged through a named human account, while 62% carry an AI co-author trailer, with large repository-level variation. Second, these edits are genuine curation: an audited sample shows that most change skill content, and the coded operations are dominated by additions and corrections. Third, a pre-registered rule-likeness axis fails its reliability gate; reliably coding rule-likeness from commit artifacts remains an open measurement problem. We release the corpus, codebooks, mining scripts, and a replay protocol for automated skill curators. For self-evolving agents, public skill maintenance currently looks less like an autonomous pipeline than a human-governed, AI-assisted loop that future curators must measure against and operate within.

cs.CL↗
arXiv2026

Regret Dominates Surprise: Design-Time Requirements Engineering for Agentic-AI Safety

Requirements engineers for agentic-AI domains face challenges in evaluating, specifying, and operationalizing safe autonomy. Mainstream frameworks, such as Goal-Oriented Requirements Engineering (GORE), lack mechanisms to systematically address these challenges under epistemic uncertainty. We contribute an approach that builds on GORE to model and simulate safe autonomy in agentic-AI systems. We introduce a novel Regret-Dominance Mechanism (MS-RGR) to operationalize safe autonomy. MS-RGR uses two signals: epistemic surprise (novelty detection) and cognitive regret (evaluative risk) to address the trilemma problem: should the agent operate in routine autonomy, undergo reflective reasoning, or escalate to human? We instantiate MS-RGR in elderly care monitoring and autonomous driving. A 100-seed stochastic simulation shows MS-RGR reduces silent failures to near-zero and detects risk approximately 17.5 times faster than a sensor-only baseline, remaining formally traceable via LTL safety properties. A retrospective proxy instantiation applying the DRI gate post-hoc over execution traces from 208 AGENTHARM scenarios across seven LLMs shows the gate improves harmful-task refusal only for models with strong baseline safety (over 80% pre-gate refusal, e.g., 84.1% to 90.9%), indicating MS-RGR amplifies rather than substitutes for model-level safety training. We discuss threats to validity, positioning MS-RGR as initial feasibility evidence for design-time safety constraints in agentic-AI requirements engineering.

cs.SE↗
arXiv2026

Evaluating Uncertainty and Quality of Vision-Language-Action-enabled Robots

Vision-Language-Action (VLA)-enabled robots integrate visual perception, natural language understanding, and action planning to interpret their environment, comprehend instructions, and perform embodied tasks autonomously. Such robots are typically evaluated through task success rates, i.e., whether a robot performs its intended task, which are commonly used as test oracles for evaluating such robots. Such an evaluation fails to capture the quality of task execution and the robot's confidence in its decisions. In this paper, we adapt eight uncertainty metrics and five quality metrics specifically designed for VLA-enabled robotic manipulation tasks. We assess their effectiveness through a large-scale empirical study involving 908 successful task executions from three state-of-the-art VLA models across four representative robotic manipulation tasks and two robot embodiments. Human domain experts manually labeled task quality, enabling us to analyze the correlation between our proposed metrics and expert judgments, serving as a human oracle for testing such robots. The results reveal that several metrics show moderate to strong correlation with human assessments, highlighting their utility for evaluating task quality and model confidence. Furthermore, we found that some metrics can discriminate between high-, medium-, and low-quality executions from unsuccessful tasks, which is useful when test oracles are absent. Our findings challenge the adequacy of current evaluation practices that rely solely on binary success rates and pave the way for improved real-time monitoring and adaptive enhancement of VLA-enabled robots.

cs.SE↗
arXiv2026

GraphMend: Code Transformations for Fixing Graph Breaks in PyTorch 2

This paper presents GraphMend, a compiler technique that automatically fixes FX graph breaks in PyTorch 2 programs. Although PyTorch 2 introduced TorchDynamo and TorchInductor to enable just-in-time graph compilation, certain code patterns still cause graph breaks that force execution to fall back to Python eager mode, introducing costly CPU-GPU synchronization and reducing optimization opportunities. Our investigation of 195 Hugging Face models reveals that 13.8% of models exhibit graph breaks. GraphMend automatically eliminates fixable breaks through source-level program analysis and transformations. It analyzes AST-level program structure to identify graph-break patterns and applies transformations only when their semantic preservation can be statically established. These transformations enable PyTorch to capture larger, uninterrupted FX graphs without manual refactoring by developers. We evaluate GraphMend on all 27 models found to exhibit graph breaks in our investigation. GraphMend eliminates 107 of 147 graph breaks (73%), fully fixing all breaks in 21 models. In our experiments on NVIDIA GPUs, GraphMend achieves up to 26x cold-start speedup, 5x on average, and up to 1.39x steady-state forward pass speedup. These results demonstrate that semantics-aware source-level analysis and transformation are effective complements to PyTorch's dynamic JIT compilation pipeline, substantially improving both usability and performance.

cs.PL↗
arXiv2026

Extending Fill-In-the-Middle with Instructions for Steerable Code Completion

Code completion models often fail when the developer's intent is under-specified in the code context. To mitigate this, developers frequently use natural language comments to clarify objectives. However, current code completion models fail to prioritize these directives effectively since they are merely pre-trained using the Fill-In-the-Middle (FIM) objective. On the one hand, the natural language instructions, mixed with the noisy code comments, are just treated as part of the background context within the prefix. On the other hand, the pre-training datasets for the FIM objective are mostly sourced from open-source repositories, which results in a scarcity of high-intent instruction-to-code pairings that reflect the developers' workflow in code completion. To bridge this gap, we propose Instruction-aware Fill-In-the-Middle (IFIM), a fine-tuning method that extends the FIM structure with a dedicated, structurally separated instruction section. Our evaluation shows that IFIM substantially improves adherence to developer intent, while leaving infilling performance unchanged when no instruction is given. The gains hold on an in-the-wild benchmark of 100 instructions written by real developers and across model scales from 1.5B to 7B. IFIM thus offers a backward-compatible upgrade path for existing FIM-based code completion systems at a modest training cost.

cs.SE↗
arXiv2026

LLM-Driven Cost-Effective Requirements Change Impact Analysis

Requirements are inherently subject to change throughout the software development lifecycle. Within the limited budget available to requirements engineers, manually identifying the impact of such changes on other requirements is error-prone and effort-intensive, especially in regulated domains. This can lead to overlooked impacted requirements, which, if not properly managed, can cause serious issues in downstream tasks. Inspired by the growing potential of large language models (LLMs) across diverse domains, we propose ProReFiCIA, an LLM-driven approach to automatically identify impacted requirements when changes occur. We conduct an extensive evaluation of ProReFiCIA using several LLMs and prompt variants tailored to this task. Using the best LLM-prompt combination, ProReFiCIA achieves 85.7% recall on an unseen industrial dataset, demonstrating its effectiveness in identifying impacted requirements. Further, the cost of applying ProReFiCIA remains small, as the engineer only needs to review the predicted impacted requirements, which represent 3.0% of the entire set of requirements. Lastly, incorporating domain knowledge via RAG increases recall to 95.8% while slightly raising the cost to 3.4%.

cs.SE↗
arXiv2026

Evolving Excellence: Automated Optimization of LLM-based Agents

Agentic AI systems built on large language models (LLMs) offer significant potential for automating complex workflows, from software development to customer support. However, LLM agents often underperform due to suboptimal configurations; poorly tuned prompts, tool descriptions, and parameters that typically require weeks of manual refinement. Existing optimization methods either are too complex for general use or treat components in isolation, missing critical interdependencies. We present ARTEMIS, a no-code evolutionary optimization platform that jointly optimizes agent configurations through semantically-aware genetic operators. Given only a benchmark script and natural language goals, ARTEMIS automatically discovers configurable components, extracts performance signals from execution logs, and evolves configurations without requiring architectural modifications. We evaluate ARTEMIS on four representative agent systems: the \emph{ALE Agent} for competitive programming on AtCoder Heuristic Contest, achieving a \textbf{$13.6\%$ improvement} in acceptance rate; the \emph{Mini-SWE Agent} for code optimization on SWE-Perf, with a statistically significant \textbf{10.1\% performance gain}; and the \emph{CrewAI Agent} for cost and mathematical reasoning on Math Odyssey, achieving a statistically significant \textbf{$36.9\%$ reduction} in the number of tokens required for evaluation. We also evaluate the \emph{MathTales-Teacher Agent} powered by a smaller open-source model (Qwen2.5-7B) on GSM8K primary-level mathematics problems, achieving a \textbf{22\% accuracy improvement} and demonstrating that ARTEMIS can optimize agents based on both commercial and local models.

cs.SE↗
arXiv2026

Security in the Age of AI Teammates: An Empirical Study of Agentic Pull Requests on GitHub

Autonomous coding agents are increasingly deployed as AI teammates in modern software engineering, independently authoring pull requests (PRs) that modify production code at scale. This study aims to systematically characterize how autonomous coding agents contribute to software security in practice, how these security-related contributions are reviewed and accepted, and which observable signals are associated with PR rejection. We conduct a large-scale empirical analysis of agent-authored PRs using the AIDev dataset, comprising of over 33,000 curated PRs from popular GitHub repositories. Security-relevant PRs are identified using a keyword filtering strategy, followed by manual validation, resulting in 1,293 confirmed security-related agentic-PRs. We then analyze prevalence, acceptance outcomes, and review latency across autonomous agents, programming ecosystems, and types of code changes. Moreover, we apply qualitative open coding to identify recurring security-related actions and underlying intents, and examine review metadata to identify early signals associated with PR rejection. Security-related Agentic-PRs constitute a meaningful share of agent activity (approximately 4\%). Rather than focusing solely on narrow vulnerability fixes, agents most frequently perform supportive security hardening activities, including testing, documentation, configuration, and improved error handling. Compared to non-security PRs, security-related Agentic-PRs exhibit lower merge rates and longer review latency, reflecting heightened human scrutiny, with variation across agents and programming ecosystems. PR rejection is more strongly associated with PR complexity and verbosity than with explicit security topics.

cs.CR↗
arXiv2026

EmoPyLab: A Tensor-Native, Hardware-Accelerated Laboratory for High-Throughput Benchmarking and Decision-Making in Multi/Many-Objective Optimization

This paper presents \textit{EmoPyLab}, an open-source, tensor-native Python framework for high-throughput benchmarking, analysis, and multi-criteria decision-making in multi- and many-objective optimization ($M \ge 2$). Traditional evolutionary toolchains rely on object-oriented Array-of-Structures (AoS) models that incur memory fragmentation and interpreter overhead during large campaigns, while emerging tensor engines focus primarily on single-objective neuroevolution, lacking high-dimensional analytics and post-Pareto decision support. EmoPyLab resolves this dichotomy via a contiguous Structure-of-Arrays (SoA) columnar data model executed across a 5-tier backend dispatch engine (NVIDIA CUDA, Apple MLX, JAX, CuPy, and CPU SIMD) with zero-copy persistence. The platform incorporates deductive Efficient Non-dominated Sorting ($O(M N \sqrt{N})$) and a low-discrepancy quasi-Monte Carlo Hypervolume estimator (Fast-MC HV) with Sobol sequence pruning, enabling real-time analytical evaluation in up to 15-objective spaces. Alongside 298+ metaheuristics and 916 benchmark instances, EmoPyLab embeds an in-situ Multi-Criteria Decision Making (MCDM) layer (TOPSIS, PROMETHEE II, and Compromise Programming) with decision-space back-mapping, automated non-parametric statistics (Wilcoxon, Friedman with Kendall's $W$, Vargha-Delaney $A_{12}$, Holm-Bonferroni correction), and cryptographic SHA-256 reproducibility manifests. The ecosystem provides both a memory-safe reactive graphical workspace ($< 150\text{ MB}$ RAM) and a headless CLI for distributed supercomputers. Empirical validation across 5,970 runs on the Santos Dumont Bull Sequana supercomputer confirms linear multi-core scaling and robust thread-oversubscription suppression, establishing a unified, reproducible, hardware-accelerated laboratory under the MIT license.

cs.SE↗
arXiv2026

A Longitudinal Study of Dependency Reclassifications in JavaScript Projects

Modern software projects depend on third-party dependencies, whose declarations must be maintained as projects evolve. Prior work has focused on dependency version updates, while much less is known about how developers assign dependencies to different roles over time. In this paper, we investigate how developers of JavaScript projects reclassify their dependencies, including removal and role reassignment. By analyzing commit-level modifications to package.json files, we reconstruct dependency role histories and identify recurring reclassification practices. Our analysis of 33,087 JavaScript projects with active dependency maintenance reveals that dependency reclassification is a prevalent maintenance activity, occurring in 79.1% of the studied projects, and accounting for 19.4% of all dependency-maintenance commits. Of these projects, nearly all (97.2%) remove dependencies at some point, while 38.0% undergo role reassignments across Core (runtime), Dev (development-only), and Peer (consumer-provided) roles. These changes are not always final, as 33.1% of projects later reintroduce removed dependencies and 11.2% exhibit repeated role switching. Reclassification practices also tend to unfold over long periods, with a median duration of 408 days. Illustrative cases further show recurring motivations: batch removals as accumulated cleanup or toolchain retirement; reassignments from Core to Dev, which revise production install scope for auditing or builds; and Peer reassignments that simplify consumer installation or move packages that consumers need not provide into Dev. These findings broaden the study of dependency maintenance beyond version updates, and contribute implications for project maintainers, dependency tools, package managers, and research to support correct dependency role declarations.

cs.SE↗
arXiv2026

LLM4Log: A Systematic Review of Large Language Model-based Log Analysis

Software systems generate massive, evolving, semi-structured logs that are central to reliability engineering and AIOps, yet difficult to analyze at scale under drift and limited labels. Recent advances in pretrained Transformer models and instruction-tuned large language models (LLMs) have reshaped log analysis by enabling semantic generalization and cross-source evidence integration, but also introducing deployment risks such as context limits, latency and cost, privacy constraints, and hallucinations. This paper presents LLM4Log, a systematic review of LLM-based log analysis across the end-to-end pipeline, from upstream logging-statement generation and maintenance to log parsing/structuring and downstream tasks including anomaly detection, failure prediction, root cause analysis, and log summarization. Following a structured search and manual screening protocol, we completed literature collection in November 2025 and identified 145 unique papers across seven logging tasks. We organize the research area through a unified, task-driven taxonomy, summarize common design patterns (prompting/ICL, retrieval grounding, fine-tuning, tool/agent augmentation, and verification), and analyze evaluation practices, datasets, metrics, and reproducibility. Based on these cross-paper analyses, we summarize key lessons and open challenges for reliable real-world adoption. We emphasize robustness under drift and long-tail events, grounding and faithfulness for operator-facing outputs, and deployment-oriented designs with verifiable behavior.

cs.SE↗
arXiv2026

Two Truths and A Lie? Benchmarking Off-the-Shelf LLMs for Requirements Quality Assessment: Performance, False Alarms, and Misses

Requirements engineering (RE) governs the quality of everything downstream in systems engineering (SE); defective requirements that survive review cycles propagate into design rework, schedule delays, and cost overruns. Because requirements are often written in natural language, recent advances in generative AI have raised expectations that large language models (LLMs) can absorb requirement quality assessment, a task otherwise slow and human expertise-intensive. Yet empirical evidence on whether LLMs can be trusted to do so remains scarce. This study presents the first benchmarking analysis of off-the-shelf LLM performance for requirement quality evaluation. Against an expert-derived ground truth built on INCOSE quality criteria, we evaluate ten models spanning two families (OpenAI and Anthropic) and five generations each, across one hundred independent runs, two requirement sets, and five sampling temperatures. Four contributions follow. First, we quantify a strongly asymmetric error profile: across all models and runs, the best-performing Anthropic model detects a median of only 47% of expert-identified issues while false-flagging 11%. Second, performance degrades significantly where SE judgment is required, as necessity and correctness issues are almost always missed. Third, generational progress is non-monotonic, so newer models cannot be assumed better. Fourth, this error behavior shifts only modestly and non-monotonically across sampling temperatures, indicating characteristic model deficiencies rather than inherent stochasticity. Off-the-shelf LLMs are therefore not yet trustworthy autonomous evaluators. Findings also warrant caution for Agentic AI developers: orchestrating these LLM modules in specialized architectures risks compounding these deficiencies rather than correcting them. Their defensible near-term role is human-in-the-loop decision support.

cs.SE↗
arXiv2026

Refusing the Impossible: A Taxonomy and Benchmark for Code Hallucination in Large Language Models

Large language models (LLMs) often produce code that looks plausible but is not grounded in reality. The code may import packages that do not exist or claim to implement algorithms that violate proven theorems, while still compiling and running. We study \emph{code hallucination} as \emph{ungrounded generation} and separate it from ordinary \emph{code error} (bugs in otherwise grounded programs). We propose a taxonomy with three dimensions: \textbf{groundedness} (absolute violations of universal truths vs.\ relative fabrications of contingent or ecosystem-specific facts), \textbf{manifestation level} (syntactic, semantic, or factual), and \textbf{behavior} (from confident fabrication to degenerate output), organized into a severity ordering. We build an \textbf{adversarial} suite of deliberately unsatisfiable tasks where the correct response is to refuse and categorize the responses under our taxonomy. The suite contains \textbf{270 prompts} across six languages and 24 subcategories, paired with \textbf{91 matched solvable controls}, and responses are judged by a two-tier protocol validated against human labels (82\% agreement, $κ{=}0.73$). Across twelve open-weight code and reasoning models (4{,}332 judged responses), models produce ungrounded code on about 60\% of unsatisfiable prompts and refuse only 27\%, while wrongly refusing 0\% of the solvable controls.

cs.SE↗
arXiv2026

TIPCODER: Reinforcement Learning Boosted Test-time Instruction Proposer for Code Generation

Test-time scaling for code generation typically explores the solution space by sampling multiple programs from a fixed instruction. We study a complementary direction: instance-level instruction-space exploration. Our observation is that many coding failures stem from missing constraints, overlooked edge cases, or misleading reasoning paths induced by the original prompt. To address this, we propose TipCoder, a test-time instruction proposer that generates problem-specific auxiliary tips before code synthesis. TipCoder distills multi-turn debugging trajectories into proactive guidance and further optimizes the Proposer with reinforcement learning using a marginal-utility reward. At inference time, it generates both a base solution and a tip-guided solution, and applies a Reward Model for post-hoc selection. This exploration-selection design allows tips to expose additional candidate potential while reducing regressions from unnecessary guidance. Across the evaluated code-generation benchmarks and target Code LLMs, TipCoder provides a consistent instruction-level test-time scaling strategy, comparing favorably with stochastic sampling and generic prompt optimization baselines under a shared reward-model-based selection protocol.

cs.SE↗
arXiv2026

The Psychological Costs of Artificial Intelligence Adoption in Software Engineering

Artificial intelligence (AI) is increasingly used to augment software engineering (SE) workflows. While code generation remains the main use case, organizations are actively seeking AI integration in other practices such as test cases generation and code reviews. Organizational AI adoption strategies seem to focus on tangible outcomes such as productivity. However, AI is a disruptive force, introduced into settings where role identity, team norms, and the sources of job satisfaction were well established before the recent advances in generative AI. Historically, technological disruptions have caused psychological and social strains in workplaces, ranging from anxiety and eroded meaning to deskilling and disrupted professional identities. The assumption that AI for SE is cost-free may not be accurate. Therefore, in this study we sought to understand the psychological costs software professionals experience during organizational AI adoption. We carried out a case study in a large software development services company, one year after the company launched its AI adoption. We collected qualitative data through meetings and semi-structured interviews (N = 21). We found that software professionals experience accountability anxiety, craft identity disruption, meaning and satisfaction erosion, cognitive and workload intensification, and uncertainty distress. Practitioners manage these costs through practices that restore control, mitigate them through protective and identity-preserving adaptations, or absorb them, carrying what neither can resolve. We contribute to AI-human collaboration in SE by repositioning AI adoption as a human transition, not only a technological and organizational one.

cs.SE↗
arXiv2026

Code Transformation Rule Synthesis using LLMs: Potential and Limits

Due to their black-box nature, LLMs suffer from limited explain- ability and a lack of determinism. Their usage cost can also rise, particularly with repetitive tasks on large codebases. To mitigate this, we conduct a novel empirical study targeting three domain- specific languages for transformation rules, namely Comby, GritQL, and Ast-Grep. We evaluate three LLMs (GPT-5.4, GPT-oss-120B, and Llama3.1-8B) on six diverse datasets covering four software- evolution tasks: API misuse correction, program repair, API migra- tion, and language version migration. Our results provide evidence that transformation rule synthesis moves beyond proof-of-concept with strong frontier models. GPT-5.4 achieves consistently high rule applicability rates and produces transformations closest to the ground truth across most benchmarks. Smaller and open-weight GPT-oss-120B and Llama3.1-8B models remain effective for simpler, localized changes but struggle with complex migration scenarios. We also observe non-negligible generalizability through the usage of meta-variables and through a high reuse score in the first quartile of many datasets. Finally, when compared to the anti-unification algorithm, LLMs outperform it in correctness, but underperform in rule applicability. Overall, our results show great potential for LLMs to generate sound, correct, generalizable, and reusable rules.

cs.SE↗
arXiv2026

Can LLMs Extract Architectural Design Decisions from Source Code Commits? - A Preliminary Exploratory Study

Context: Architectural Design Decisions (ADDs) capture the rationale behind the structure and evolution of software systems but are rarely documented explicitly, and are often hidden inside source code commits. Recovering them is important for Architectural Knowledge Management (AKM). Problem: Extracting ADDs from commits is challenging due to their implicit and unstructured nature. Large Language Models (LLMs) have shown strong capabilities in understanding code and text, yet their effectiveness for this task remains underexplored. Study: We present a preliminary study using four LLMs (Gemini 3 Pro, DeepSeek R1, Kimi K2, Qwen3) with zeroshot and fewshot prompting on 30 developer-written ADDs from open-source projects. We score outputs with ROUGE-L, BLEU, METEOR, and BERTScore, and one author manually reviews the Gemini outputs. Results: All models reach a BERT-F1 above 0.81, and fewshot prompting improves alignment (Gemini BERT-F1: 0.828 to 0.847). However, the generated ADDs are often too long, implementation-focused, and miss the rationale behind the decision. This highlights opportunities for architecture-aware LLM systems and automated AKM.

cs.SE↗
arXiv2026

Virtual Testing of Automated Driving Systems through Credible Simulations

Simulation is increasingly used to support safety-related decision-making in road transport, particularly for the assessment and approval of automated driving systems (ADS). The complexity of ADS behavior and size of their operational design domains make exclusive reliance on physical testing impractical, leading to extensive use of virtual testing (VT) during the approval phase. This shift raises critical questions regarding the credibility of modelling and simulation (M&S) results used to support road safety decisions. Current VT accreditation approaches in the ADS domain typically rely on validation-only practices, which have been shown to scale poorly when applied to complex, multi-tool simulation environments. To address this limitation, this paper proposes a risk-based framework for assessing the credibility of simulation toolchains used in ADS safety evaluation, drawing inspiration from established practices in other safety-critical domains, notably NASA's STD-7009 for models and simulations. The framework extends traditional verification and validation (V&V) by explicitly linking credibility requirements to the intended use of simulation outputs and to the safety criticality of the decisions they support within the approval process. It provides a lifecycle-oriented assessment scheme integrating toolchain management, modelling assumptions and limitations, verification, validation, and sensitivity analysis. Credibility acceptance thresholds are defined proportionally, allowing differentiated requirements depending on whether simulation is used for exploratory safety analysis, partial decision support, or as a substitute for physical testing. While demonstrated for ADS, the proposed approach is directly applicable to road safety and simulation studies where VT plays a central role in safety assessment and regulatory decision-making.

cs.RO↗
Compare source metadata on this page
WorkPublishedSource identifierSource
Who Maintains Agent Skills? A Longitudinal Study of Human-Governed, AI-Assisted Skill Maintenance2026-09-042609.05677arxiv
Regret Dominates Surprise: Design-Time Requirements Engineering for Agentic-AI Safety2026-09-042609.05692arxiv
Evaluating Uncertainty and Quality of Vision-Language-Action-enabled Robots2026-09-032507.17049arxiv
GraphMend: Code Transformations for Fixing Graph Breaks in PyTorch 22026-09-032509.16248arxiv
Extending Fill-In-the-Middle with Instructions for Steerable Code Completion2026-09-032509.24637arxiv
LLM-Driven Cost-Effective Requirements Change Impact Analysis2026-09-032511.00262arxiv
Evolving Excellence: Automated Optimization of LLM-based Agents2026-09-032512.09108arxiv
Security in the Age of AI Teammates: An Empirical Study of Agentic Pull Requests on GitHub2026-09-032601.00477arxiv
EmoPyLab: A Tensor-Native, Hardware-Accelerated Laboratory for High-Throughput Benchmarking and Decision-Making in Multi/Many-Objective Optimization2026-09-032603.01345arxiv
A Longitudinal Study of Dependency Reclassifications in JavaScript Projects2026-09-032604.08747arxiv
LLM4Log: A Systematic Review of Large Language Model-based Log Analysis2026-09-032604.16359arxiv
Two Truths and A Lie? Benchmarking Off-the-Shelf LLMs for Requirements Quality Assessment: Performance, False Alarms, and Misses2026-09-032609.03230arxiv
Refusing the Impossible: A Taxonomy and Benchmark for Code Hallucination in Large Language Models2026-09-032609.03267arxiv
TIPCODER: Reinforcement Learning Boosted Test-time Instruction Proposer for Code Generation2026-09-032609.03309arxiv
The Psychological Costs of Artificial Intelligence Adoption in Software Engineering2026-09-032609.03456arxiv
Code Transformation Rule Synthesis using LLMs: Potential and Limits2026-09-032609.03592arxiv
Can LLMs Extract Architectural Design Decisions from Source Code Commits? - A Preliminary Exploratory Study2026-09-032609.03721arxiv
Virtual Testing of Automated Driving Systems through Credible Simulations2026-09-032609.03760arxiv

These are bibliographic comparisons, not experimental rankings. Follow the original document for methods and conditions.