Human-In-the-Loop Software Development Agents

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Takerngsaksiri, Wannita, Pasuksmit, Jirat, Thongtanunam, Patanamon, Tantithamthavorn, Chakkrit, Zhang, Ruixiong, Jiang, Fan, Li, Jing, Cook, Evan, Chen, Kun, Wu, Ming
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917888812646400
author Takerngsaksiri, Wannita
Pasuksmit, Jirat
Thongtanunam, Patanamon
Tantithamthavorn, Chakkrit
Zhang, Ruixiong
Jiang, Fan
Li, Jing
Cook, Evan
Chen, Kun
Wu, Ming
author_facet Takerngsaksiri, Wannita
Pasuksmit, Jirat
Thongtanunam, Patanamon
Tantithamthavorn, Chakkrit
Zhang, Ruixiong
Jiang, Fan
Li, Jing
Cook, Evan
Chen, Kun
Wu, Ming
contents Recently, Large Language Models (LLMs)-based multi-agent paradigms for software engineering are introduced to automatically resolve software development tasks (e.g., from a given issue to source code). However, existing work is evaluated based on historical benchmark datasets, rarely considers human feedback at each stage of the automated software development process, and has not been deployed in practice. In this paper, we introduce a Human-in-the-loop LLM-based Agents framework (HULA) for software development that allows software engineers to refine and guide LLMs when generating coding plans and source code for a given task. We design, implement, and deploy the HULA framework into Atlassian JIRA for internal uses. Through a multi-stage evaluation of the HULA framework, Atlassian software engineers perceive that HULA can minimize the overall development time and effort, especially in initiating a coding plan and writing code for straightforward tasks. On the other hand, challenges around code quality remain a concern in some cases. We draw lessons learned and discuss opportunities for future work, which will pave the way for the advancement of LLM-based agents in software development.
format Preprint
id arxiv_https___arxiv_org_abs_2411_12924
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Human-In-the-Loop Software Development Agents
Takerngsaksiri, Wannita
Pasuksmit, Jirat
Thongtanunam, Patanamon
Tantithamthavorn, Chakkrit
Zhang, Ruixiong
Jiang, Fan
Li, Jing
Cook, Evan
Chen, Kun
Wu, Ming
Software Engineering
Artificial Intelligence
Human-Computer Interaction
Machine Learning
Recently, Large Language Models (LLMs)-based multi-agent paradigms for software engineering are introduced to automatically resolve software development tasks (e.g., from a given issue to source code). However, existing work is evaluated based on historical benchmark datasets, rarely considers human feedback at each stage of the automated software development process, and has not been deployed in practice. In this paper, we introduce a Human-in-the-loop LLM-based Agents framework (HULA) for software development that allows software engineers to refine and guide LLMs when generating coding plans and source code for a given task. We design, implement, and deploy the HULA framework into Atlassian JIRA for internal uses. Through a multi-stage evaluation of the HULA framework, Atlassian software engineers perceive that HULA can minimize the overall development time and effort, especially in initiating a coding plan and writing code for straightforward tasks. On the other hand, challenges around code quality remain a concern in some cases. We draw lessons learned and discuss opportunities for future work, which will pave the way for the advancement of LLM-based agents in software development.
title Human-In-the-Loop Software Development Agents
topic Software Engineering
Artificial Intelligence
Human-Computer Interaction
Machine Learning
url https://arxiv.org/abs/2411.12924