English
Related papers

Related papers: APEX-SWE

200 papers

Serverless computing is a popular cloud computing paradigm that has found widespread adoption across various online workloads. It allows software engineers to develop cloud applications as a set of functions (called serverless functions).…

Software Engineering · Computer Science 2025-02-13 Jinfeng Wen , Zhenpeng Chen , Jianshu Zhao , Federica Sarro , Haodi Ping , Ying Zhang , Shangguang Wang , Xuanzhe Liu

In this technical report, we present SWE-Master, an open-source and fully reproducible post-training framework for building effective software engineering agents. SWE-Master systematically explores the complete agent development pipeline,…

Computer-use agents (CUAs) hold the promise of performing a wide variety of general tasks, but current evaluations have primarily focused on simple scenarios. It therefore remains unclear whether such generalist agents can automate more…

Software Engineering · Computer Science 2025-10-06 Pranjal Aggarwal , Sean Welleck

Context: Software startups are an essential source of innovation and software-intensive products. The need to understand product development in startups and to provide relevant support are highlighted in software research. While…

Software Engineering · Computer Science 2021-03-16 Anh Nguyen-Duc , Kai-Kristian Kemell , Pekka Abrahamsson

Learning-based techniques, especially advanced pre-trained models for code have demonstrated capabilities in code understanding and generation, solving diverse software engineering (SE) tasks. Despite the promising results, current training…

Software Engineering · Computer Science 2025-02-07 Kyi Shin Khant , Hong Yi Lin , Patanamon Thongtanunam

LLM-based agents struggle to execute complex, multi-step Standard Operating Procedures (SOPs) that are fundamental to industrial automation. Existing benchmarks fail to capture the procedural complexity and tool orchestration demands of…

LLMs have achieved strong results on both function-level code synthesis and repository-level code modification, yet a capability that falls between these two extremes -- compositional code creation, i.e., building a complete, internally…

Software Engineering · Computer Science 2026-04-30 Yeheng Chen , Chaoxiang Xie , Yuling Shi , Wenhao Zeng , Yongpan Wang , Hongyu Zhang , Xiaodong Gu

Language models (LMs) perform well on standardized coding benchmarks but struggle with real-world software engineering tasks such as resolving GitHub issues in SWE-Bench, especially when model parameters are less than 100B. While smaller…

Computation and Language · Computer Science 2025-05-30 Guangtao Zeng , Maohao Shen , Delin Chen , Zhenting Qi , Subhro Das , Dan Gutfreund , David Cox , Gregory Wornell , Wei Lu , Zhang-Wei Hong , Chuang Gan

The goal of automated feature generation is to liberate machine learning experts from the laborious task of manual feature generation, which is crucial for improving the learning performance of tabular data. The major challenge in automated…

Machine Learning · Computer Science 2023-06-06 Tianping Zhang , Zheyu Zhang , Zhiyuan Fan , Haoyan Luo , Fengyuan Liu , Qian Liu , Wei Cao , Jian Li

If AI models can detect when they are being evaluated, the effectiveness of evaluations might be compromised. For example, models could have systematically different behavior during evaluations, leading to less reliable benchmarks for…

Computation and Language · Computer Science 2025-07-17 Joe Needham , Giles Edkins , Govind Pimpale , Henning Bartsch , Marius Hobbhahn

Large language models are increasingly deployed as autonomous agents for multi-step workflows in real-world software environments. However, existing agent benchmarks are limited by trajectory-opaque grading, underspecified safety and…

Artificial Intelligence · Computer Science 2026-05-08 Bowen Ye , Rang Li , Qibin Yang , Yuanxin Liu , Linli Yao , Hanglong Lv , Zhihui Xie , Chenxin An , Lei Li , Lingpeng Kong , Qi Liu , Zhifang Sui , Tong Yang

Software effort estimation (SEE) models are typically developed based on an underlying assumption that all data points are equally relevant to the prediction of effort for future projects. The dynamic nature of several aspects of the…

Software Engineering · Computer Science 2020-12-17 Michael Franklin Bosu , Stephen G. MacDonell , Peter Whigham

Forecasting when AI systems will become capable of meaningfully accelerating AI research is a central challenge for AI safety. Existing benchmarks measure broad capability growth, but may not provide ample early warning signals for…

Multiagent Systems · Computer Science 2026-04-30 Joshua Sherwood , Ben Aybar , Benjamin Kaplan

Purpose: The rapid integration of artificial intelligence (AI) systems like ChatGPT, Claude AI, etc., has a deep impact on how work is done. Predicting how AI will reshape work requires understanding not just its capabilities, but how it is…

General Economics · Economics 2025-10-30 Peeyush Agarwal , Harsh Agarwal , Akshat Rana

While recent work has benchmarked large language models on Swiss legal translation (Niklaus et al., 2025) and academic legal reasoning from university exams (Fan et al., 2025), no existing benchmark evaluates frontier model performance on…

Computation and Language · Computer Science 2026-03-26 Fatih Uenal

Automating real-world software engineering tasks remains challenging for large language model (LLM)-based agents due to the need for long-horizon reasoning over large, evolving codebases and making consistent decisions across interdependent…

Software Engineering · Computer Science 2026-04-14 Mahir Labib Dihan , Md Ashrafur Rahman Khan

For software development companies, one of the most important objectives is to identify and acquire talented software engineers in order to maintain a skilled team that can produce competitive products. Traditional approaches for finding…

Software Engineering · Computer Science 2014-11-25 Jun Lin , Han Yu , Zhiqi Shen

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

Systems Engineering (SE) is the set of processes and documentation required for successfully realising large-scale engineering projects, but the classical approach is not a good fit for software-intensive projects, especially when the needs…

Instrumentation and Methods for Astrophysics · Physics 2017-12-05 Juande Santander-Vela

Domain-specific software and hardware co-design is encouraging as it is much easier to achieve efficiency for fewer tasks. Agile domain-specific benchmarking speeds up the process as it provides not only relevant design inputs but also…

‹ Prev 1 4 5 6 7 8 10 Next ›