AgileCoder: Dynamic Collaborative Agents for Software Development based on Agile Methodology

Software agents have emerged as promising tools for addressing complex software engineering tasks. Existing works, on the other hand, frequently oversimplify software development workflows, despite the fact that such workflows are typically more complex in the real world. Thus, we propose AgileCoder...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Nguyen, Minh Huynh, Chau, Thang Phan, Nguyen, Phong X, Bui, Nghi D. Q
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Nguyen, Minh Huynh
Chau, Thang Phan
Nguyen, Phong X
Bui, Nghi D. Q
description Software agents have emerged as promising tools for addressing complex software engineering tasks. Existing works, on the other hand, frequently oversimplify software development workflows, despite the fact that such workflows are typically more complex in the real world. Thus, we propose AgileCoder, a multi agent system that integrates Agile Methodology (AM) into the framework. This system assigns specific AM roles - such as Product Manager, Developer, and Tester to different agents, who then collaboratively develop software based on user inputs. AgileCoder enhances development efficiency by organizing work into sprints, focusing on incrementally developing software through sprints. Additionally, we introduce Dynamic Code Graph Generator, a module that creates a Code Dependency Graph dynamically as updates are made to the codebase. This allows agents to better comprehend the codebase, leading to more precise code generation and modifications throughout the software development process. AgileCoder surpasses existing benchmarks, like ChatDev and MetaGPT, establishing a new standard and showcasing the capabilities of multi agent systems in advanced software engineering environments.
doi_str_mv 10.48550/arxiv.2406.11912
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2406_11912</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2406_11912</sourcerecordid><originalsourceid>FETCH-LOGICAL-a672-9f8dae8b91011f6e3d94c5459b98a02eb882f0e242bc0ef7c38ed19f87f9b7c3</originalsourceid><addsrcrecordid>eNotj8tKxDAYhbNxIaMP4Mq8QGuS3hJ3peMNRlzMLAfKn-ZPLaTNkJZq395aXR0Oh_PBR8gdZ3Eqs4w9QPju5likLI85V1xck3PZdg4rbzA80v0yQN81tPLOgfYBpm5GWrY4TCO1PtCjt9MXBKR7nNH5S78uVMOIhvqBbij6jtOnN975drkhVxbciLf_uSPH56dT9RodPl7eqvIQQV6ISFlpAKVWnHFuc0yMSpsszZRWEphALaWwDEUqdMPQFk0i0fD1VVil17Yj93_Uza6-hK6HsNS_lvVmmfwAM4tONw</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>AgileCoder: Dynamic Collaborative Agents for Software Development based on Agile Methodology</title><source>arXiv.org</source><creator>Nguyen, Minh Huynh ; Chau, Thang Phan ; Nguyen, Phong X ; Bui, Nghi D. Q</creator><creatorcontrib>Nguyen, Minh Huynh ; Chau, Thang Phan ; Nguyen, Phong X ; Bui, Nghi D. Q</creatorcontrib><description>Software agents have emerged as promising tools for addressing complex software engineering tasks. Existing works, on the other hand, frequently oversimplify software development workflows, despite the fact that such workflows are typically more complex in the real world. Thus, we propose AgileCoder, a multi agent system that integrates Agile Methodology (AM) into the framework. This system assigns specific AM roles - such as Product Manager, Developer, and Tester to different agents, who then collaboratively develop software based on user inputs. AgileCoder enhances development efficiency by organizing work into sprints, focusing on incrementally developing software through sprints. Additionally, we introduce Dynamic Code Graph Generator, a module that creates a Code Dependency Graph dynamically as updates are made to the codebase. This allows agents to better comprehend the codebase, leading to more precise code generation and modifications throughout the software development process. AgileCoder surpasses existing benchmarks, like ChatDev and MetaGPT, establishing a new standard and showcasing the capabilities of multi agent systems in advanced software engineering environments.</description><identifier>DOI: 10.48550/arxiv.2406.11912</identifier><language>eng</language><subject>Computer Science - Artificial Intelligence ; Computer Science - Software Engineering</subject><creationdate>2024-06</creationdate><rights>http://creativecommons.org/publicdomain/zero/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,776,881</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2406.11912$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2406.11912$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Nguyen, Minh Huynh</creatorcontrib><creatorcontrib>Chau, Thang Phan</creatorcontrib><creatorcontrib>Nguyen, Phong X</creatorcontrib><creatorcontrib>Bui, Nghi D. Q</creatorcontrib><title>AgileCoder: Dynamic Collaborative Agents for Software Development based on Agile Methodology</title><description>Software agents have emerged as promising tools for addressing complex software engineering tasks. Existing works, on the other hand, frequently oversimplify software development workflows, despite the fact that such workflows are typically more complex in the real world. Thus, we propose AgileCoder, a multi agent system that integrates Agile Methodology (AM) into the framework. This system assigns specific AM roles - such as Product Manager, Developer, and Tester to different agents, who then collaboratively develop software based on user inputs. AgileCoder enhances development efficiency by organizing work into sprints, focusing on incrementally developing software through sprints. Additionally, we introduce Dynamic Code Graph Generator, a module that creates a Code Dependency Graph dynamically as updates are made to the codebase. This allows agents to better comprehend the codebase, leading to more precise code generation and modifications throughout the software development process. AgileCoder surpasses existing benchmarks, like ChatDev and MetaGPT, establishing a new standard and showcasing the capabilities of multi agent systems in advanced software engineering environments.</description><subject>Computer Science - Artificial Intelligence</subject><subject>Computer Science - Software Engineering</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj8tKxDAYhbNxIaMP4Mq8QGuS3hJ3peMNRlzMLAfKn-ZPLaTNkJZq395aXR0Oh_PBR8gdZ3Eqs4w9QPju5likLI85V1xck3PZdg4rbzA80v0yQN81tPLOgfYBpm5GWrY4TCO1PtCjt9MXBKR7nNH5S78uVMOIhvqBbij6jtOnN975drkhVxbciLf_uSPH56dT9RodPl7eqvIQQV6ISFlpAKVWnHFuc0yMSpsszZRWEphALaWwDEUqdMPQFk0i0fD1VVil17Yj93_Uza6-hK6HsNS_lvVmmfwAM4tONw</recordid><startdate>20240616</startdate><enddate>20240616</enddate><creator>Nguyen, Minh Huynh</creator><creator>Chau, Thang Phan</creator><creator>Nguyen, Phong X</creator><creator>Bui, Nghi D. Q</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20240616</creationdate><title>AgileCoder: Dynamic Collaborative Agents for Software Development based on Agile Methodology</title><author>Nguyen, Minh Huynh ; Chau, Thang Phan ; Nguyen, Phong X ; Bui, Nghi D. Q</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a672-9f8dae8b91011f6e3d94c5459b98a02eb882f0e242bc0ef7c38ed19f87f9b7c3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Computer Science - Artificial Intelligence</topic><topic>Computer Science - Software Engineering</topic><toplevel>online_resources</toplevel><creatorcontrib>Nguyen, Minh Huynh</creatorcontrib><creatorcontrib>Chau, Thang Phan</creatorcontrib><creatorcontrib>Nguyen, Phong X</creatorcontrib><creatorcontrib>Bui, Nghi D. Q</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Nguyen, Minh Huynh</au><au>Chau, Thang Phan</au><au>Nguyen, Phong X</au><au>Bui, Nghi D. Q</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>AgileCoder: Dynamic Collaborative Agents for Software Development based on Agile Methodology</atitle><date>2024-06-16</date><risdate>2024</risdate><abstract>Software agents have emerged as promising tools for addressing complex software engineering tasks. Existing works, on the other hand, frequently oversimplify software development workflows, despite the fact that such workflows are typically more complex in the real world. Thus, we propose AgileCoder, a multi agent system that integrates Agile Methodology (AM) into the framework. This system assigns specific AM roles - such as Product Manager, Developer, and Tester to different agents, who then collaboratively develop software based on user inputs. AgileCoder enhances development efficiency by organizing work into sprints, focusing on incrementally developing software through sprints. Additionally, we introduce Dynamic Code Graph Generator, a module that creates a Code Dependency Graph dynamically as updates are made to the codebase. This allows agents to better comprehend the codebase, leading to more precise code generation and modifications throughout the software development process. AgileCoder surpasses existing benchmarks, like ChatDev and MetaGPT, establishing a new standard and showcasing the capabilities of multi agent systems in advanced software engineering environments.</abstract><doi>10.48550/arxiv.2406.11912</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2406.11912
ispartof
issn
language eng
recordid cdi_arxiv_primary_2406_11912
source arXiv.org
subjects Computer Science - Artificial Intelligence
Computer Science - Software Engineering
title AgileCoder: Dynamic Collaborative Agents for Software Development based on Agile Methodology
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-23T15%3A15%3A05IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=AgileCoder:%20Dynamic%20Collaborative%20Agents%20for%20Software%20Development%20based%20on%20Agile%20Methodology&rft.au=Nguyen,%20Minh%20Huynh&rft.date=2024-06-16&rft_id=info:doi/10.48550/arxiv.2406.11912&rft_dat=%3Carxiv_GOX%3E2406_11912%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true