Results 281 to 290 of about 1,260,399 (325)
Some of the next articles are maybe not open access.
MERA: meta language for software engineering
Proceedings Fourth International Conference on Software Engineering and Knowledge Engineering, 2003MERA (Meta Entity-Relation-Attribute) is a versatile graphical language which can be used for modeling and analysis of the user requirements, for building a prototype, for representing designer's knowledge for controlling design process, etc. The current version of MERA has capacity for animation, view operation, user adaptability, and some semantic ...
K. Takeda, D.N. Chin, I. Miyamoto
openaire +1 more source
Do advanced language models eliminate the need for prompt engineering in software engineering?
ACM Transactions on Software Engineering and MethodologyLarge Language Models (LLMs) have significantly advanced software engineering (SE) tasks, with prompt engineering techniques enhancing their performance in code-related areas.
Guoqing Wang +7 more
semanticscholar +1 more source
SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering
Neural Information Processing SystemsLanguage model (LM) agents are increasingly being used to automate complicated tasks in digital environments. Just as humans benefit from powerful software applications, such as integrated development environments, for complex tasks like software ...
John Yang +6 more
semanticscholar +1 more source
Agentless: Demystifying LLM-based Software Engineering Agents
arXiv.orgRecent advancements in large language models (LLMs) have significantly advanced the automation of software development tasks, including code synthesis, program repair, and test generation.
Chun Xia +3 more
semanticscholar +1 more source
Design languages for cleanroom software engineering
Proceedings of the Twenty-Fifth Hawaii International Conference on System Sciences, 1992Choosing a good design language is essential for success in using the cleanroom software engineering techniques. The design language should be tailored to support the important aspects of cleanroom, most importantly, functional decomposition of intended functions and functional verification.
openaire +1 more source
SWE-smith: Scaling Data for Software Engineering Agents
arXiv.orgDespite recent progress in Language Models (LMs) for software engineering, collecting training data remains a significant pain point. Existing datasets are small, with at most 1,000s of training instances from 11 or fewer GitHub repositories.
John Yang +9 more
semanticscholar +1 more source
Demystifying LLM-Based Software Engineering Agents
Proc. ACM Softw. Eng.Recent advancements in large language models (LLMs) have significantly advanced the automation of software development tasks, including code synthesis, program repair, and test generation.
Chun Xia +3 more
semanticscholar +1 more source
Integrating Natural Language Processing and Software Engineering
International Journal of Software Engineering and Its Applications, 2015This paper tries to put various ways in which Natural Language Processing (NLP) and Software Engineering (SE) can be seen as inter-disciplinary research areas. We survey the current literature, with the aim of assessing use of Software Engineering and Natural Language Processing tools in the researches undertaken. An assessment of how various phases of
Nakul Sharma, Prasanth Yalla
openaire +1 more source
Software language engineering in the large: towards composing and deriving languages
Computer languages, systems & structures, 2018Katrin Hölldobler +2 more
semanticscholar +1 more source
Training Software Engineering Agents and Verifiers with SWE-Gym
International Conference on Machine LearningWe present SWE-Gym, the first environment for training real-world software engineering (SWE) agents. SWE-Gym contains 2,438 real-world Python task instances, each comprising a codebase with an executable runtime environment, unit tests, and a task ...
Jiayi Pan +6 more
semanticscholar +1 more source