在自动化软件工程任务,如代码合成、程序修复和测试生成等领域,是否真有必要采用复杂的自主软件代理(agent-based approaches)?随着大型语言模型(LLMs)在这些领域的应用日益广泛,研究人员和行业实践者开发了各种自主的LLM代理来执行端到端的软件开发任务。然而,这些基于代理的方法的复杂性,加上当前LLMs的有限能力,引发了...
Qian, C., Cong, X., Yang, C., Chen, W., Su, Y., Xu, J., ... & Sun, M. (2023). Communicative agents for software development. arXiv preprint arXiv:2307.07924. LLMs惊人的语言运用和编码能力,必深刻变革软件工程。畅想未来,软件开发团队由一系列LLMs智能体构成,而人类主要负责提出需求。...
From LLMs to LLM-based Agents for Software Engineering: A Survey of Current, Challenges and FutureO网页链接随着大型语言模型(LLM)的兴起,研究人员越来越探索其在各种垂直领域中的应用,如软件工程。LLM在代码生成和漏洞检测等领域取得了显著成功。然而,它也存在许多局限性和不足之处。LLM基础的智能体是一种具...
Repository for the paper "Large Language Model-Based Agents for Software Engineering: A Survey". agent artificial-intelligence software-engineering large-language-models llms llm-based-agents Updated Sep 25, 2024 Improve this page Add a description, image, and links to the llm-based-agents to...
Exploring LLM-based Agents for Root Cause Analysis Devjeet Roy, Xuchao Zhang, Rashi Bhave, Chetan Bansal, Pedro Las-Casas, Rodrigo Fonseca, Saravan Rajmohan FSE '24: 32nd ACM International Conference on the Foundations of Software Engineering|July 2024 ...
[2024/05/06] Large Language Models (LLMs) as Agents for Augmented Democracy | [paper] | [code] [2024/05/06] SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering | [paper] | [code] [2024/05/02] GAIA: A General AI Assistant for Intelligent Accelerator Operations |...
and feedback-necessitates the collaboration of four agents: a manager, a secretary, regular employees, and consultants. This method has historically been predominant in prior works. For example, Generative Agent [28], immersed in the context of a software company, utilizes authored natural language...
LLM-based agents for automating the enhancement of user story quality: An early reportIn agile software development, maintaining high-quality user stories is crucial, but also challenging. This study explores the use of large language models to automatically improve the user story quality in Austrian...
Exploring LLM-based Agents for Root Cause Analysis 7 Mar 2024·Devjeet Roy,Xuchao Zhang,Rashi Bhave,Chetan Bansal,Pedro Las-Casas,Rodrigo Fonseca,Saravan Rajmohan· The growing complexity of cloud based software systems has resulted in incident management becoming an integral part of the software ...
Motivated by the empirical findings, we propose a novel LLM-based Multi-Agent framework for GitHub Issue reSolution, MAGIS, consisting of four agents customized for software evolution: Manager, Repository Custodian, Developer, and Quality Assurance Engineer agents. This framework leverages the ...