14 articles tagged #software-engineering
arXiv:2607.18970v1 Announce Type: cross Abstract: Agent Skills have become persistent behavioral artifacts across independent AI agent systems. They combine natural-language task specifications with metadata and optional references, scripts, assets, hooks, package manifests, tests, and companion int
arXiv:2607.08124v1 Announce Type: cross Abstract: The behavior of an LLM agent is determined not only by the underlying model, but also by its harness: the executable program that constructs context, invokes tools, verifies intermediate results, and recovers from failures. Existing approaches optimi
arXiv:2503.08936v3 Announce Type: replace-cross Abstract: Scenario-based testing with driving simulators is extensively used to identify failing conditions of automated driving assistance systems (ADAS). However, existing studies have shown that repeated test execution in the same as well as in dist
arXiv:2606.20324v1 Announce Type: cross Abstract: Virtual training environments are software-intensive systems in which reinforcement learning (RL) agents learn, adapt, and demonstrate meaningful behavior. Virtual training environments offer a safe and cost-efficient alternative to training agents i
arXiv:2606.18733v1 Announce Type: cross Abstract: Realistic coding-agent benchmarks often replay public GitHub issues and pull requests, making them vulnerable to overlap with model pretraining, fine-tuning, synthetic-data generation, or benchmark-driven model selection. Fully synthetic tasks avoid
arXiv:2606.17507v1 Announce Type: new Abstract: Generative AI and large language models (LLMs) are increasingly applied to question generation and automated assessment. However, deploying LLMs in preparation for high-stakes exams requires more than prompt engineering; it demands software pipelines t
arXiv:2603.13384v2 Announce Type: replace-cross Abstract: Software vulnerabilities often depend on cross-file data flow, build options, framework conventions, and runtime guards, so isolated function classifiers produce fragile and poorly calibrated warnings. Repository-level LLM agents can gather r
arXiv:2601.20255v2 Announce Type: replace-cross Abstract: SWE-bench has emerged as the premier benchmark for evaluating Large Language Models on complex software engineering tasks. While these capabilities are fundamentally acquired during the mid-training phase and subsequently elicited during Supe
arXiv:2605.06136v1 Announce Type: cross Abstract: Most coding-agent benchmarks ask whether generated code behaves correctly. That remains essential, but repository-level engineering is increasingly agent-managed: one agent writes a repository, and later agents inspect, audit, or extend it as working
arXiv:2605.03800v1 Announce Type: cross Abstract: This paper analyzes the strategic education process aimed at transitioning traditional software development squads into hybrid structures centered on collaborative work between humans and Artificial Intelligence (AI). In a context where human-AI coll
arXiv:2605.01392v1 Announce Type: cross Abstract: Recent advancements in Large Language Models (LLMs) have demonstrated significant potential across a wide range of software engineering tasks, including software design, an area traditionally regarded as highly dependent on human expertise and judgme
arXiv:2604.19750v1 Announce Type: cross Abstract: Recent advances in Large Language Model (LLM)-based agents have shown remarkable progress in code generation. However, current agent methods mainly rely on text-output-based feedback (e.g. command-line outputs) for multi-round debugging and struggle
arXiv:2604.13100v1 Announce Type: cross Abstract: The shift toward intent-driven software engineering (often termed "Vibe Coding") exposes a critical Context-Fidelity Trade-off: vague user intents overwhelm linear reasoning chains, leading to architectural collapse in complex repo-level generation.
arXiv:2604.07494v1 Announce Type: cross Abstract: Context: AI coding agents route every task to a single frontier large language model (LLM), paying premium inference cost even when many tasks are routine. Objectives: We propose Triage, a framework that uses code health metrics -- indicators of soft