arxivJun 3bullish
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
arxivMay 14bullish
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
arxivMay 8
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
arxivMay 7bullish
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
arxivMay 6
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
arxivApr 23bullish
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
arxivApr 17bullish
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.
arxivApr 10bullish
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