中文
相关论文

相关论文: Needle in the Repo: A Benchmark for Maintainabilit…

200 篇论文

The integration of AI agents as coding assistants into software development has raised questions about the long-term viability of AI agent-generated code. A prevailing hypothesis within the software engineering community suggests this code…

软件工程 · 计算机科学 2026-01-26 Musfiqur Rahman , Emad Shihab

As generative AI models such as large language models (LLMs) become more pervasive, ensuring the safety, robustness, and overall trustworthiness of these systems is paramount. However, AI is currently facing a reproducibility crisis driven…

机器学习 · 计算机科学 2026-05-14 Deepak Pandita , Flip Korn , Chris Welty , Christopher M. Homan

AI coding agents are increasingly integrated into modern software engineering workflows, actively collaborating with human developers to create pull requests (PRs) in open-source repositories. Although coding agents improve developer…

软件工程 · 计算机科学 2026-03-31 K M Ferdous , Dipayan Banik , Kowshik Chowdhury , Shazibul Islam Shamim

Artificial intelligence systems based on large language models (LLMs) can now generate coherent text, music, and images, yet they operate without a persistent state: each inference reconstructs context from scratch. This paper introduces…

计算机与社会 · 计算机科学 2025-11-04 Stefano Natangelo

Computational reproducibility is fundamental to trustworthy science, yet remains difficult to achieve in practice across various research workflows, including Jupyter notebooks published alongside scholarly articles. Environment drift,…

软件工程 · 计算机科学 2026-04-02 Sheeba Samuel , Daniel Mietchen , Hemanta Lo , Martin Gaedke

Context: Retrieval-augmented code generation relies on cross-file repository context, but retrieved snippets may come from obsolete project states. Objectives: We study whether temporally stale repository snippets act as harmless noise or…

软件工程 · 计算机科学 2026-05-15 Haojun Weng , Qianqian Yang , Hao Fu , Haobin Pan , Xinwei Lv

Reproducing computational research is often assumed to be as simple as rerunning the original code with provided data. In practice, missing packages, fragile file paths, version conflicts, or incomplete logic frequently cause analyses to…

软件工程 · 计算机科学 2026-04-24 Syed Mehtab Hussain Shah , Frank Hopfgartner , Arnim Bleier

As the potential for neural networks to augment our daily lives grows, ensuring their quality through effective testing, debugging, and maintenance is essential. This is especially the case as we acknowledge the prospects of negative…

软件工程 · 计算机科学 2025-07-08 Fatema Tuz Zohra , Brittany Johnson

Alignment research focuses on making individual AI systems reliable. Human institutions achieve reliable collective behaviour differently: they mitigate the risk posed by misaligned individuals through organisational structure. Multi-agent…

人工智能 · 计算机科学 2026-02-17 William Waites

A large challenge in Artificial Intelligence (AI) is training control agents that can properly adapt to variable environments. Environments in which the conditions change can cause issues for agents trying to operate in them. Building…

神经与进化计算 · 计算机科学 2023-07-04 Destiny Bailey

AI coding assistants increasingly generate code alongside tests. How developers structure test code, whether inline with the implementation or in separate blocks, has traditionally been a matter of testing philosophy. We investigate whether…

软件工程 · 计算机科学 2026-04-23 Éric Jacopin

Practitioners have reported a directional pattern in AI-assisted code generation: AI-generated code tends to fail quietly, preserving the appearance of functionality while degrading or concealing guarantees. This paper introduces the…

软件工程 · 计算机科学 2026-04-21 William M. Parris

As AI coding agents evolve from autocomplete tools to autonomous "AI workforce" teammates, they introduce a critical new bottleneck: human maintainers must now manage complex interaction loops rather than just reviewing code. Analyzing…

Large language model (LLM)-based coding agents achieve impressive results on controlled benchmarks yet routinely produce pull requests that real maintainers reject. The root cause is not functional incorrectness but a lack of organicity:…

软件工程 · 计算机科学 2026-03-30 Mo Li , L. H. Xu , Qitai Tan , Ting Cao , Yunxin Liu

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…

软件工程 · 计算机科学 2026-05-08 Jhen-Ke Lin

While "Intent-oriented programming" (or "Vibe Coding") redefines software engineering, existing code agents remain tethered to static code snapshots. Consequently, they struggle to model the critical information embedded in the temporal…

机器学习 · 计算机科学 2026-03-17 Yi-Xuan Deng , Xiaoqin Liu , Yi Zhang , Guo-Wei Yang , Shuojin Yang

Automated Program Repair (APR) aims to automatically fix bugs in the source code. Recently, as advances in Deep Learning (DL) field, there is a rise of Neural Program Repair (NPR) studies, which formulate APR as a translation task from…

软件工程 · 计算机科学 2022-09-22 Wenkang Zhong , Chuanyi Li , Jidong Ge , Bin Luo

An important challenge for human-like AI is compositional semantics. Recent research has attempted to address this by using deep neural networks to learn vector space embeddings of sentences, which then serve as input to other tasks. We…

计算与语言 · 计算机科学 2018-05-21 Ishita Dasgupta , Demi Guo , Andreas Stuhlmüller , Samuel J. Gershman , Noah D. Goodman

Retrieval-augmented generation (RAG) enhances language models by integrating external knowledge, but its effectiveness is highly dependent on system configuration. Improper retrieval settings can degrade performance, making RAG less…

计算与语言 · 计算机科学 2025-07-17 Jennifer Hsia , Afreen Shaikh , Zhiruo Wang , Graham Neubig

AI coding agents are now submitting pull requests (PRs) to software projects, acting not just as assistants but as autonomous contributors. As these agentic contributions are rapidly increasing across real repositories, little is known…

‹ 上一页 1 2 3 10 下一页 ›