English
Related papers

Related papers: BUILD-AND-FIND: An Effort-Aware Protocol for Evalu…

200 papers

User comments on online programming platforms such as Stack Overflow play a vital role in maintaining the correctness and relevance of shared code examples. However, the majority of comments express gratitude or clarification, while only a…

Software Engineering · Computer Science 2026-04-27 Mehedi Hasan Shanto , Muhammad Asaduzzaman , Alioune Ngom

Repository-level code agents have shown strong promise in real-world feature addition tasks, making reliable evaluation of their capabilities increasingly important. However, existing benchmarks primarily evaluate these agents as black…

Software Engineering · Computer Science 2026-03-30 Shuhan Liu , Zhiyi Zhao , Xing Hu , Kui Liu , Xiaohu Yang , Xin Xia

While significant progress has been made in automating various aspects of software development through coding agents, there is still significant room for improvement in their bug fixing capabilities. Debugging and investigation of runtime…

Software Engineering · Computer Science 2026-04-22 Spandan Garg , Yufan Huang

Automated code generation remains a persistent challenge in software engineering, as conventional multi-agent frameworks are often constrained by static planning, isolated execution, high computational overhead, and limited adaptability to…

Software Engineering · Computer Science 2026-04-21 Duy Tung Doan , Quang Huy Phung , Dzung Nguyen , Khac-Hoai Nam Bui

Code localization is a fundamental challenge in repository-level software engineering tasks such as bug fixing. While existing methods equip language agents with comprehensive tools/interfaces to fetch information from the repository, they…

Software Engineering · Computer Science 2026-02-10 Boshi Wang , Weijian Xu , Yunsheng Li , Mei Gao , Yujia Xie , Huan Sun , Dongdong Chen

Repository-level code completion automatically predicts the unfinished code based on the broader information from the repository. Recent strides in Code Large Language Models (code LLMs) have spurred the development of repository-level code…

Computation and Language · Computer Science 2025-09-22 Sheng Zhang , Yifan Ding , Shuquan Lian , Shun Song , Hui Li

Formal verification offers a path to provably correct software, but writing verified code remains expensive enough that the technique is rarely used in production. Recent large language models can accelerate this work, and recent benchmarks…

Logic in Computer Science · Computer Science 2026-05-28 Leo Yao

AI coding agents can now complete complex programming tasks, but existing evaluations largely emphasize behavioral correctness and often overlook maintainability risks such as weak modularity or testability. We present Needle in the Repo…

Software Engineering · Computer Science 2026-03-31 Haichao Zhu , Qian Zhang , Jiyuan Wang , Zhaorui Yang , Yuxin Qiu

While Large Language Models (LLMs) have achieved remarkable success in code generation, they often struggle with the deep, long-horizon reasoning required for complex software engineering. We attribute this limitation to the nature of…

Manually generating access control policies from an organization's high-level requirement specifications poses significant challenges. It requires laborious efforts to sift through multiple documents containing such specifications and…

Cryptography and Security · Computer Science 2024-09-16 Sakuna Harinda Jayasundara , Nalin Asanka Gamagedara Arachchilage , Giovanni Russello

The escalating complexity of modern codebases has intensified the need for retrieval systems capable of interpreting cross-component change intents, a capability fundamentally absent in conventional function-level search paradigms. While…

Software Engineering · Computer Science 2025-10-30 Aofan Liu , Shiyuan Song , Haoxuan Li , Cehao Yang , Yiyan Qi

Behaviour-Driven Development (BDD) has emerged in the last years as a powerful methodology to specify testable and executable user requirements through stories and scenarios. With the support of external testing frameworks, BDD stories can…

Software Engineering · Computer Science 2022-09-14 Thiago Rocha Silva , Marco Winckler

Repository-level code review requires reasoning over project structure, repository context, and file-level implementation details. Existing automated review workflows often collapse these tasks into a single pass, which can reduce…

Software Engineering · Computer Science 2026-03-18 Peng Zhang

Recent advances in code generation models have unlocked unprecedented opportunities for automating feature engineering, yet their adoption in real-world ML teams remains constrained by critical challenges: (i) the scarcity of datasets…

Machine Learning · Computer Science 2026-01-19 Himanshu Thakur , Anusha Kamath , Anurag Muthyala , Dhwani Sanmukhani , Smruthi Mukund , Jay Katukuri

Recent advances in coding agents suggest rapid progress toward autonomous software development, yet existing benchmarks fail to rigorously evaluate the long-horizon capabilities required to build complete software systems. Most prior…

Recently, Agentic AI has become an increasingly popular research field. However, we argue that current agent research practices lack standardization and scientific rigor, making it hard to conduct fair comparisons among methods. As a…

Agentic Retrieval-Augmented Generation (RAG) is a new paradigm where the reasoning model decides when to invoke a retriever (as a "tool") when answering a question. This paradigm, exemplified by recent research works such as Search-R1,…

Information Retrieval · Computer Science 2025-07-15 Fangzheng Tian , Jinyuan Fang , Debasis Ganguly , Zaiqiao Meng , Craig Macdonald

Code changes are an integral part of the software development process. Many code changes are meant to improve the code without changing its functional behavior, e.g., refactorings and performance improvements. Unfortunately, validating…

Software Engineering · Computer Science 2025-02-25 Lars Gröninger , Beatriz Souza , Michael Pradel

Repository-level coding agents must first localize the files and symbols relevant to a task; failures at this stage can cascade across downstream objectives ranging from patch generation to test writing and codebase question answering.…

Information Retrieval · Computer Science 2026-05-19 Yuntong Hu , Tongli Su , Liang Zhao , Bowen Zhu , Hasibul Haque

Code generation models based on large language models (LLMs) have gained wide adoption, but challenges remain in ensuring safety, accuracy, and controllability, especially for complex tasks. Existing methods often lack dynamic integration…

Software Engineering · Computer Science 2025-10-13 Aofan Liu , Haoxuan Li , Bin Wang , Ao Yang , Hui Li