English
Related papers

Related papers: SAFEdit: Does Multi-Agent Decomposition Resolve th…

200 papers

Code readability is fundamental to software quality and maintainability. Poor readability extends development time, increases bug-inducing risks, and contributes to technical debt. With the rapid advancement of Large Language Models, AI…

Software Engineering · Computer Science 2026-03-17 Kyogo Horikawa , Kosei Horikawa , Yutaro Kashiwa , Hidetake Uwano , Hajimu Iida

The rapid progress in Automated Program Repair (APR) has been driven by advances in AI, particularly large language models (LLMs) and agent-based systems. SWE-Bench is a recent benchmark designed to evaluate LLM-based repair systems using…

Software Engineering · Computer Science 2026-02-06 Matias Martinez , Xavier Franch

Even the largest neural networks make errors, and once-correct predictions can become invalid as the world changes. Model editors make local updates to the behavior of base (pre-trained) models to inject updated knowledge or correct…

Artificial Intelligence · Computer Science 2022-06-15 Eric Mitchell , Charles Lin , Antoine Bosselut , Christopher D. Manning , Chelsea Finn

Code refactoring is a fundamental software engineering practice aimed at improving code quality and maintainability. Despite its importance, developers often neglect refactoring due to the significant time, effort, and resources it…

AI agents are increasingly being deployed to automate tasks, often based on underspecified user instructions. Making unwarranted assumptions to compensate for the missing information and failing to ask clarifying questions can lead to…

Artificial Intelligence · Computer Science 2026-02-24 Sanidhya Vijayvargiya , Xuhui Zhou , Akhila Yerukola , Maarten Sap , Graham Neubig

Large language models have demonstrated strong capabilities in individual software engineering tasks, yet most autonomous systems still treat issue resolution as a monolithic or pipeline-based process. In contrast, real-world software…

Artificial Intelligence · Computer Science 2026-02-10 Nikita Benkovich , Vitalii Valkov

We present Minitap, a multi-agent system that achieves 100% success on the AndroidWorld benchmark, the first to fully solve all 116 tasks and surpassing human performance (80%). We first analyze why single-agent architectures fail: context…

Large Language Models (LLMs) have revolutionized software engineering (SE), showcasing remarkable proficiency in various coding tasks. Despite recent advancements that have enabled the creation of autonomous software agents utilizing LLMs…

Software Engineering · Computer Science 2025-09-08 Huy Nhat Phan , Tien N. Nguyen , Phong X. Nguyen , Nghi D. Q. Bui

Numerous software analysis tools exist today, yet applying them to diverse open-source projects remains challenging due to environment setup, dependency resolution, and tool configuration. LLM-based agents offer a potential solution, yet no…

Software Engineering · Computer Science 2026-04-20 Islem Bouzenia , Cristian Cadar , Michael Pradel

Humans solve problems by executing targeted plans, yet large language models (LLMs) remain unreliable for structured workflow execution. We propose RunAgent, a multi-agent plan execution platform that interprets natural-language plans while…

Machine Learning · Computer Science 2026-05-04 Arunabh Srivastava , Mohammad A. , Khojastepour , Srimat Chakradhar , Sennur Ulukus

Large Language Models (LLMs) have achieved remarkable progress in code-related tasks. Despite their advancement, empirical evidence reveals that they still struggle with \emph{deductive code reasoning}, the ability to reason about the…

Programming Languages · Computer Science 2025-11-04 Jun Gao , Yun Peng , Xiaoxue Ren

Extracting structured, machine-readable compliance criteria from regulatory documents remains an open challenge. Single-pass language models hallucinate structural elements, lose hierarchical relationships, and fail to resolve…

Multiagent Systems · Computer Science 2026-04-15 Mohammed Ali , Abdelrahman Abdallah , Adam Jatowt

Large language model (LLM) agents typically rely on reactive decision-making paradigms such as ReAct, selecting actions conditioned on growing execution histories. While effective for short tasks, these approaches often lead to redundant…

Artificial Intelligence · Computer Science 2026-03-02 Yihan , Wen , Xin Chen

We introduce SWE Atlas, a benchmark suite for coding agents spanning three professional software engineering workflows: Codebase Q&A (124 tasks), Test Writing (90 tasks), and Refactoring (70 tasks). SWE Atlas differs from prior SWE…

Modern software development pipelines face growing challenges in securing large codebases with extensive dependencies. Static analysis tools like Bandit are effective at vulnerability detection but suffer from high false positives and lack…

Cryptography and Security · Computer Science 2025-09-23 Jugal Gajjar , Kamalasankari Subramaniakuppusamy , Relsy Puthal , Kaustik Ranaware

Architectural code smells erode software maintainability and are costly to repair manually, yet unlike localized bugs, they require cross-module reasoning about design intent that challenges both developers and automated tools. While large…

Software Engineering · Computer Science 2026-05-13 Ion George Dinu , Marian Cristian Mihăescu , Traian Rebedea

Automated Program Repair (APR) has advanced rapidly with Large Language Models (LLMs), but most existing methods remain computationally expensive, and focused on a small set of languages. Ruby, despite its widespread use in web development…

Software Engineering · Computer Science 2025-11-07 Nikta Akbarpour , Mahdieh Sadat Benis , Fatemeh Hendijani Fard , Ali Ouni , Mohamed Aymen Saied

Coding agents can generate web applications from natural-language descriptions, yet a recent benchmark study shows that generated applications fail to meet functional requirements in over 70% of cases. The core difficulty is that web…

Software Engineering · Computer Science 2026-05-19 Yuxuan Wan , Tingshuo Liang , Jiakai Xu , Jingyu Xiao , Yintong Huo , Michael R Lyu

Algorithmic problem solving serves as a rigorous testbed for evaluating structured reasoning in AI coding systems, as it directly reflects a model's ability to perform structured reasoning in complex scenarios. Existing approaches…

Artificial Intelligence · Computer Science 2026-05-11 Yuliang Xu , Xiang Xu , Yao Wan , Hu Wei , Tong Jia

As software systems evolve, developers increasingly work across multiple programming languages and often face the need to migrate code from one language to another. While automatic code translation offers a promising solution, it has long…

Software Engineering · Computer Science 2025-12-09 Fazle Rabbi , Soumit Kanti Saha , Tri Minh Triet Pham , Song Wang , Jinqiu Yang