An LLM-based multi-agent framework for agile effort estimation Article Swipe

PDF

YOU? · · 2025 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2509.14483

Effort estimation is a crucial activity in agile software development, where teams collaboratively review, discuss, and estimate the effort required to complete user stories in a product backlog. Current practices in agile effort estimation heavily rely on subjective assessments, leading to inaccuracies and inconsistencies in the estimates. While recent machine learning-based methods show promising accuracy, they cannot explain or justify their estimates and lack the capability to interact with human team members. Our paper fills this significant gap by leveraging the powerful capabilities of Large Language Models (LLMs). We propose a novel LLM-based multi-agent framework for agile estimation that not only can produce estimates, but also can coordinate, communicate and discuss with human developers and other agents to reach a consensus. Evaluation results on a real-life dataset show that our approach outperforms state-of-the-art techniques across all evaluation metrics in the majority of the cases. Our human study with software development practitioners also demonstrates an overwhelmingly positive experience in collaborating with our agents in agile effort estimation.

Related Topics

National Institutional Ranking Framework

The Myth Of The Framework

Cynefin Framework

Django (Web Framework)

Iran Nuclear Deal Framework

United Nations Framework Convention On Climate Change

Bootstrap (Front-End Framework)

Electron (Software Framework)

Flask (Web Framework)

Multi-Agent System

Metal–Organic Framework

The Open Group Architecture Framework

Concepts

No concepts available.

Metadata

Type: preprint
Language: en
Landing Page: http://arxiv.org/abs/2509.14483
PDF: https://arxiv.org/pdf/2509.14483
OA Status: green
OpenAlex ID: https://openalex.org/W4417081343

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4417081343

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.48550/arxiv.2509.14483

Digital Object Identifier
Title: An LLM-based multi-agent framework for agile effort estimation

Work title
Type: preprint

OpenAlex work type
Language: en

Primary language
Publication year: 2025

Year of publication
Publication date: 2025-09-17

Full publication date if available
Authors: Hoa Khanh Dam, Rashina Hoda

List of authors in order
Landing page: https://arxiv.org/abs/2509.14483

Publisher landing page
PDF URL: https://arxiv.org/pdf/2509.14483

Direct link to full text PDF
Open access: Yes

Whether a free full text is available
OA status: green

Open access status per OpenAlex
OA URL: https://arxiv.org/pdf/2509.14483

Direct OA link when available
Cited by: 0

Total citation count in OpenAlex

Full payload

id	https://openalex.org/W4417081343
doi	https://doi.org/10.48550/arxiv.2509.14483
ids.doi	https://doi.org/10.48550/arxiv.2509.14483
ids.openalex	https://openalex.org/W4417081343
fwci
type	preprint
title	An LLM-based multi-agent framework for agile effort estimation
biblio.issue
biblio.volume
biblio.last_page
biblio.first_page
is_xpac	False
apc_list
apc_paid
language	en
locations[0].id	pmh:oai:arXiv.org:2509.14483
locations[0].is_oa	True
locations[0].source.id	https://openalex.org/S4306400194
locations[0].source.issn
locations[0].source.type	repository
locations[0].source.is_oa	True
locations[0].source.issn_l
locations[0].source.is_core	False
locations[0].source.is_in_doaj	False
locations[0].source.display_name	arXiv (Cornell University)
locations[0].source.host_organization	https://openalex.org/I205783295
locations[0].source.host_organization_name	Cornell University
locations[0].source.host_organization_lineage	https://openalex.org/I205783295
locations[0].license
locations[0].pdf_url	https://arxiv.org/pdf/2509.14483
locations[0].version	submittedVersion
locations[0].raw_type	text
locations[0].license_id
locations[0].is_accepted	False
locations[0].is_published	False
locations[0].raw_source_name
locations[0].landing_page_url	http://arxiv.org/abs/2509.14483
locations[1].id	doi:10.48550/arxiv.2509.14483
locations[1].is_oa	True
locations[1].source.id	https://openalex.org/S4306400194
locations[1].source.issn
locations[1].source.type	repository
locations[1].source.is_oa	True
locations[1].source.issn_l
locations[1].source.is_core	False
locations[1].source.is_in_doaj	False
locations[1].source.display_name	arXiv (Cornell University)
locations[1].source.host_organization	https://openalex.org/I205783295
locations[1].source.host_organization_name	Cornell University
locations[1].source.host_organization_lineage	https://openalex.org/I205783295
locations[1].license	cc-by
locations[1].pdf_url
locations[1].version
locations[1].raw_type	article
locations[1].license_id	https://openalex.org/licenses/cc-by
locations[1].is_accepted	False
locations[1].is_published
locations[1].raw_source_name
locations[1].landing_page_url	https://doi.org/10.48550/arxiv.2509.14483
indexed_in	arxiv, datacite
authorships[0].author.id	https://openalex.org/A5017181940
authorships[0].author.orcid	https://orcid.org/0000-0003-4246-0526
authorships[0].author.display_name	Hoa Khanh Dam
authorships[0].author_position	last
authorships[0].raw_author_name	Dam, Hoa Khanh
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5036986396
authorships[1].author.orcid	https://orcid.org/0000-0001-5147-8096
authorships[1].author.display_name	Rashina Hoda
authorships[1].author_position	middle
authorships[1].raw_author_name	Hoda, Rashina
authorships[1].is_corresponding	False
has_content.pdf	False
has_content.grobid_xml	False
is_paratext	False
open_access.is_oa	True
open_access.oa_url	https://arxiv.org/pdf/2509.14483
open_access.oa_status	green
open_access.any_repository_has_fulltext	False
created_date	2025-10-10T00:00:00
display_name	An LLM-based multi-agent framework for agile effort estimation
has_fulltext	False
is_retracted	False
updated_date	2025-12-06T18:07:19.224398
primary_topic
cited_by_count	0
locations_count	2
best_oa_location.id	pmh:oai:arXiv.org:2509.14483
best_oa_location.is_oa	True
best_oa_location.source.id	https://openalex.org/S4306400194
best_oa_location.source.issn
best_oa_location.source.type	repository
best_oa_location.source.is_oa	True
best_oa_location.source.issn_l
best_oa_location.source.is_core	False
best_oa_location.source.is_in_doaj	False
best_oa_location.source.display_name	arXiv (Cornell University)
best_oa_location.source.host_organization	https://openalex.org/I205783295
best_oa_location.source.host_organization_name	Cornell University
best_oa_location.source.host_organization_lineage	https://openalex.org/I205783295
best_oa_location.license
best_oa_location.pdf_url	https://arxiv.org/pdf/2509.14483
best_oa_location.version	submittedVersion
best_oa_location.raw_type	text
best_oa_location.license_id
best_oa_location.is_accepted	False
best_oa_location.is_published	False
best_oa_location.raw_source_name
best_oa_location.landing_page_url	http://arxiv.org/abs/2509.14483
primary_location.id	pmh:oai:arXiv.org:2509.14483
primary_location.is_oa	True
primary_location.source.id	https://openalex.org/S4306400194
primary_location.source.issn
primary_location.source.type	repository
primary_location.source.is_oa	True
primary_location.source.issn_l
primary_location.source.is_core	False
primary_location.source.is_in_doaj	False
primary_location.source.display_name	arXiv (Cornell University)
primary_location.source.host_organization	https://openalex.org/I205783295
primary_location.source.host_organization_name	Cornell University
primary_location.source.host_organization_lineage	https://openalex.org/I205783295
primary_location.license
primary_location.pdf_url	https://arxiv.org/pdf/2509.14483
primary_location.version	submittedVersion
primary_location.raw_type	text
primary_location.license_id
primary_location.is_accepted	False
primary_location.is_published	False
primary_location.raw_source_name
primary_location.landing_page_url	http://arxiv.org/abs/2509.14483
publication_date	2025-09-17
publication_year	2025
referenced_works_count	0
abstract_inverted_index.a	3, 25, 90, 119, 124
abstract_inverted_index.We	88
abstract_inverted_index.an	153
abstract_inverted_index.by	78
abstract_inverted_index.in	6, 24, 30, 44, 138, 157, 162
abstract_inverted_index.is	2
abstract_inverted_index.of	83, 141
abstract_inverted_index.on	36, 123
abstract_inverted_index.or	58
abstract_inverted_index.to	20, 40, 66, 117
abstract_inverted_index.Our	72, 144
abstract_inverted_index.all	135
abstract_inverted_index.and	15, 42, 62, 109, 114
abstract_inverted_index.but	104
abstract_inverted_index.can	101, 106
abstract_inverted_index.for	95
abstract_inverted_index.gap	77
abstract_inverted_index.not	99
abstract_inverted_index.our	129, 160
abstract_inverted_index.the	17, 45, 64, 80, 139, 142
abstract_inverted_index.also	105, 151
abstract_inverted_index.lack	63
abstract_inverted_index.only	100
abstract_inverted_index.rely	35
abstract_inverted_index.show	52, 127
abstract_inverted_index.team	70
abstract_inverted_index.that	98, 128
abstract_inverted_index.they	55
abstract_inverted_index.this	75
abstract_inverted_index.user	22
abstract_inverted_index.with	68, 111, 147, 159
abstract_inverted_index.Large	84
abstract_inverted_index.While	47
abstract_inverted_index.agile	7, 31, 96, 163
abstract_inverted_index.fills	74
abstract_inverted_index.human	69, 112, 145
abstract_inverted_index.novel	91
abstract_inverted_index.other	115
abstract_inverted_index.paper	73
abstract_inverted_index.reach	118
abstract_inverted_index.study	146
abstract_inverted_index.teams	11
abstract_inverted_index.their	60
abstract_inverted_index.where	10
abstract_inverted_index.Effort	0
abstract_inverted_index.Models	86
abstract_inverted_index.across	134
abstract_inverted_index.agents	116, 161
abstract_inverted_index.cannot	56
abstract_inverted_index.cases.	143
abstract_inverted_index.effort	18, 32, 164
abstract_inverted_index.recent	48
abstract_inverted_index.(LLMs).	87
abstract_inverted_index.Current	28
abstract_inverted_index.crucial	4
abstract_inverted_index.dataset	126
abstract_inverted_index.discuss	110
abstract_inverted_index.explain	57
abstract_inverted_index.heavily	34
abstract_inverted_index.justify	59
abstract_inverted_index.leading	39
abstract_inverted_index.machine	49
abstract_inverted_index.methods	51
abstract_inverted_index.metrics	137
abstract_inverted_index.produce	102
abstract_inverted_index.product	26
abstract_inverted_index.propose	89
abstract_inverted_index.results	122
abstract_inverted_index.review,	13
abstract_inverted_index.stories	23
abstract_inverted_index.Language	85
abstract_inverted_index.activity	5
abstract_inverted_index.approach	130
abstract_inverted_index.backlog.	27
abstract_inverted_index.complete	21
abstract_inverted_index.discuss,	14
abstract_inverted_index.estimate	16
abstract_inverted_index.interact	67
abstract_inverted_index.majority	140
abstract_inverted_index.members.	71
abstract_inverted_index.positive	155
abstract_inverted_index.powerful	81
abstract_inverted_index.required	19
abstract_inverted_index.software	8, 148
abstract_inverted_index.LLM-based	92
abstract_inverted_index.accuracy,	54
abstract_inverted_index.estimates	61
abstract_inverted_index.framework	94
abstract_inverted_index.practices	29
abstract_inverted_index.promising	53
abstract_inverted_index.real-life	125
abstract_inverted_index.Evaluation	121
abstract_inverted_index.capability	65
abstract_inverted_index.consensus.	120
abstract_inverted_index.developers	113
abstract_inverted_index.estimates,	103
abstract_inverted_index.estimates.	46
abstract_inverted_index.estimation	1, 33, 97
abstract_inverted_index.evaluation	136
abstract_inverted_index.experience	156
abstract_inverted_index.leveraging	79
abstract_inverted_index.subjective	37
abstract_inverted_index.techniques	133
abstract_inverted_index.communicate	108
abstract_inverted_index.coordinate,	107
abstract_inverted_index.development	149
abstract_inverted_index.estimation.	165
abstract_inverted_index.multi-agent	93
abstract_inverted_index.outperforms	131
abstract_inverted_index.significant	76
abstract_inverted_index.assessments,	38
abstract_inverted_index.capabilities	82
abstract_inverted_index.demonstrates	152
abstract_inverted_index.development,	9
abstract_inverted_index.inaccuracies	41
abstract_inverted_index.collaborating	158
abstract_inverted_index.practitioners	150
abstract_inverted_index.learning-based	50
abstract_inverted_index.overwhelmingly	154
abstract_inverted_index.collaboratively	12
abstract_inverted_index.inconsistencies	43
abstract_inverted_index.state-of-the-art	132
cited_by_percentile_year
countries_distinct_count	0
institutions_distinct_count	2
citation_normalized_percentile