Mobile-Agent-E: Self-Evolving Mobile Assistant for Complex Tasks Article Swipe

PDF

Zhenhailong Wang , Haiyang Xu , Junyang Wang , Xi Zhang , Ming Yan , Ji Zhang , Fei Huang , Heng Ji ·

YOU? · · 2025 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2501.11733

Smartphones have become indispensable in modern life, yet navigating complex tasks on mobile devices often remains frustrating. Recent advancements in large multimodal model (LMM)-based mobile agents have demonstrated the ability to perceive and act in mobile environments. However, current approaches face significant limitations: they fall short in addressing real-world human needs, struggle with reasoning-intensive and long-horizon tasks, and lack mechanisms to learn and improve from prior experiences. To overcome these challenges, we introduce Mobile-Agent-E, a hierarchical multi-agent framework capable of self-evolution through past experience. By hierarchical, we mean an explicit separation of high-level planning and low-level action execution. The framework comprises a Manager, responsible for devising overall plans by breaking down complex tasks into subgoals, and four subordinate agents--Perceptor, Operator, Action Reflector, and Notetaker--which handle fine-grained visual perception, immediate action execution, error verification, and information aggregation, respectively. Mobile-Agent-E also features a novel self-evolution module which maintains a persistent long-term memory comprising Tips and Shortcuts. Tips are general guidance and lessons learned from prior tasks on how to effectively interact with the environment. Shortcuts are reusable, executable sequences of atomic operations tailored for specific subroutines. The inclusion of Tips and Shortcuts facilitates continuous refinement in performance and efficiency. Alongside this framework, we introduce Mobile-Eval-E, a new benchmark featuring complex mobile tasks requiring long-horizon, multi-app interactions. Empirical results show that Mobile-Agent-E achieves a 22% absolute improvement over previous state-of-the-art approaches across three foundation model backbones. Project page: https://x-plug.github.io/MobileAgent.

Related Topics

Computer Science

Human–Computer Interaction

Concepts

Computer science Human–computer interaction Mobile agent Distributed computing

Metadata

Type: preprint
Language: en
Landing Page: http://arxiv.org/abs/2501.11733
PDF: https://arxiv.org/pdf/2501.11733
OA Status: green
Cited By: 1
Related Works: 10
OpenAlex ID: https://openalex.org/W4406733262

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4406733262

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.48550/arxiv.2501.11733

Digital Object Identifier
Title: Mobile-Agent-E: Self-Evolving Mobile Assistant for Complex Tasks

Work title
Type: preprint

OpenAlex work type
Language: en

Primary language
Publication year: 2025

Year of publication
Publication date: 2025-01-20

Full publication date if available
Authors: Zhenhailong Wang, Haiyang Xu, Junyang Wang, Xi Zhang, Ming Yan, Ji Zhang, Fei Huang, Heng Ji

List of authors in order
Landing page: https://arxiv.org/abs/2501.11733

Publisher landing page
PDF URL: https://arxiv.org/pdf/2501.11733

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/2501.11733

Direct OA link when available
Concepts: Computer science, Human–computer interaction, Mobile agent, Distributed computing

Top concepts (fields/topics) attached by OpenAlex
Cited by: 1

Total citation count in OpenAlex
Citations by year (recent): 2025: 1

Per-year citation counts (last 5 years)
Related works (count): 10

Other works algorithmically related by OpenAlex

Full payload

id	https://openalex.org/W4406733262
doi	https://doi.org/10.48550/arxiv.2501.11733
ids.doi	https://doi.org/10.48550/arxiv.2501.11733
ids.openalex	https://openalex.org/W4406733262
fwci
type	preprint
title	Mobile-Agent-E: Self-Evolving Mobile Assistant for Complex Tasks
biblio.issue
biblio.volume
biblio.last_page
biblio.first_page
topics[0].id	https://openalex.org/T12203
topics[0].field.id	https://openalex.org/fields/17
topics[0].field.display_name	Computer Science
topics[0].score	0.9871000051498413
topics[0].domain.id	https://openalex.org/domains/3
topics[0].domain.display_name	Physical Sciences
topics[0].subfield.id	https://openalex.org/subfields/1705
topics[0].subfield.display_name	Computer Networks and Communications
topics[0].display_name	Mobile Agent-Based Network Management
topics[1].id	https://openalex.org/T10456
topics[1].field.id	https://openalex.org/fields/17
topics[1].field.display_name	Computer Science
topics[1].score	0.9735000133514404
topics[1].domain.id	https://openalex.org/domains/3
topics[1].domain.display_name	Physical Sciences
topics[1].subfield.id	https://openalex.org/subfields/1702
topics[1].subfield.display_name	Artificial Intelligence
topics[1].display_name	Multi-Agent Systems and Negotiation
topics[2].id	https://openalex.org/T11942
topics[2].field.id	https://openalex.org/fields/22
topics[2].field.display_name	Engineering
topics[2].score	0.9653000235557556
topics[2].domain.id	https://openalex.org/domains/3
topics[2].domain.display_name	Physical Sciences
topics[2].subfield.id	https://openalex.org/subfields/2203
topics[2].subfield.display_name	Automotive Engineering
topics[2].display_name	Transportation and Mobility Innovations
is_xpac	False
apc_list
apc_paid
concepts[0].id	https://openalex.org/C41008148
concepts[0].level	0
concepts[0].score	0.542187511920929
concepts[0].wikidata	https://www.wikidata.org/wiki/Q21198
concepts[0].display_name	Computer science
concepts[1].id	https://openalex.org/C107457646
concepts[1].level	1
concepts[1].score	0.4427891969680786
concepts[1].wikidata	https://www.wikidata.org/wiki/Q207434
concepts[1].display_name	Human–computer interaction
concepts[2].id	https://openalex.org/C84875433
concepts[2].level	2
concepts[2].score	0.43813055753707886
concepts[2].wikidata	https://www.wikidata.org/wiki/Q3277848
concepts[2].display_name	Mobile agent
concepts[3].id	https://openalex.org/C120314980
concepts[3].level	1
concepts[3].score	0.21454337239265442
concepts[3].wikidata	https://www.wikidata.org/wiki/Q180634
concepts[3].display_name	Distributed computing
keywords[0].id	https://openalex.org/keywords/computer-science
keywords[0].score	0.542187511920929
keywords[0].display_name	Computer science
keywords[1].id	https://openalex.org/keywords/human–computer-interaction
keywords[1].score	0.4427891969680786
keywords[1].display_name	Human–computer interaction
keywords[2].id	https://openalex.org/keywords/mobile-agent
keywords[2].score	0.43813055753707886
keywords[2].display_name	Mobile agent
keywords[3].id	https://openalex.org/keywords/distributed-computing
keywords[3].score	0.21454337239265442
keywords[3].display_name	Distributed computing
language	en
locations[0].id	pmh:oai:arXiv.org:2501.11733
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/2501.11733
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/2501.11733
locations[1].id	doi:10.48550/arxiv.2501.11733
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
locations[1].pdf_url
locations[1].version
locations[1].raw_type	article
locations[1].license_id
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.2501.11733
indexed_in	arxiv, datacite
authorships[0].author.id	https://openalex.org/A5045684460
authorships[0].author.orcid	https://orcid.org/0000-0002-4704-5455
authorships[0].author.display_name	Zhenhailong Wang
authorships[0].author_position	first
authorships[0].raw_author_name	Wang, Zhenhailong
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5038379561
authorships[1].author.orcid	https://orcid.org/0000-0003-4486-0590
authorships[1].author.display_name	Haiyang Xu
authorships[1].author_position	middle
authorships[1].raw_author_name	Xu, Haiyang
authorships[1].is_corresponding	False
authorships[2].author.id	https://openalex.org/A5018357502
authorships[2].author.orcid	https://orcid.org/0000-0002-3204-6607
authorships[2].author.display_name	Junyang Wang
authorships[2].author_position	middle
authorships[2].raw_author_name	Wang, Junyang
authorships[2].is_corresponding	False
authorships[3].author.id	https://openalex.org/A5100430858
authorships[3].author.orcid	https://orcid.org/0000-0002-8994-8185
authorships[3].author.display_name	Xi Zhang
authorships[3].author_position	middle
authorships[3].raw_author_name	Zhang, Xi
authorships[3].is_corresponding	False
authorships[4].author.id	https://openalex.org/A5000844861
authorships[4].author.orcid	https://orcid.org/0000-0002-4388-6708
authorships[4].author.display_name	Ming Yan
authorships[4].author_position	middle
authorships[4].raw_author_name	Yan, Ming
authorships[4].is_corresponding	False
authorships[5].author.id	https://openalex.org/A5100329266
authorships[5].author.orcid	https://orcid.org/0000-0002-3835-7975
authorships[5].author.display_name	Ji Zhang
authorships[5].author_position	middle
authorships[5].raw_author_name	Zhang, Ji
authorships[5].is_corresponding	False
authorships[6].author.id	https://openalex.org/A5101488344
authorships[6].author.orcid	https://orcid.org/0000-0002-3709-5053
authorships[6].author.display_name	Fei Huang
authorships[6].author_position	middle
authorships[6].raw_author_name	Huang, Fei
authorships[6].is_corresponding	False
authorships[7].author.id	https://openalex.org/A5075033889
authorships[7].author.orcid	https://orcid.org/0000-0002-0464-7966
authorships[7].author.display_name	Heng Ji
authorships[7].author_position	last
authorships[7].raw_author_name	Ji, Heng
authorships[7].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/2501.11733
open_access.oa_status	green
open_access.any_repository_has_fulltext	False
created_date	2025-10-10T00:00:00
display_name	Mobile-Agent-E: Self-Evolving Mobile Assistant for Complex Tasks
has_fulltext	False
is_retracted	False
updated_date	2025-11-06T06:51:31.235846
primary_topic.id	https://openalex.org/T12203
primary_topic.field.id	https://openalex.org/fields/17
primary_topic.field.display_name	Computer Science
primary_topic.score	0.9871000051498413
primary_topic.domain.id	https://openalex.org/domains/3
primary_topic.domain.display_name	Physical Sciences
primary_topic.subfield.id	https://openalex.org/subfields/1705
primary_topic.subfield.display_name	Computer Networks and Communications
primary_topic.display_name	Mobile Agent-Based Network Management
related_works	https://openalex.org/W4391375266, https://openalex.org/W2899084033, https://openalex.org/W2748952813, https://openalex.org/W2390279801, https://openalex.org/W4391913857, https://openalex.org/W2358668433, https://openalex.org/W4396701345, https://openalex.org/W2376932109, https://openalex.org/W2001405890, https://openalex.org/W4396696052
cited_by_count	1
counts_by_year[0].year	2025
counts_by_year[0].cited_by_count	1
locations_count	2
best_oa_location.id	pmh:oai:arXiv.org:2501.11733
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/2501.11733
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/2501.11733
primary_location.id	pmh:oai:arXiv.org:2501.11733
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/2501.11733
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/2501.11733
publication_date	2025-01-20
publication_year	2025
referenced_works_count	0
abstract_inverted_index.a	74, 101, 140, 146, 203, 220
abstract_inverted_index.By	84
abstract_inverted_index.To	67
abstract_inverted_index.an	88
abstract_inverted_index.by	108
abstract_inverted_index.in	4, 19, 34, 46, 193
abstract_inverted_index.of	79, 91, 177, 186
abstract_inverted_index.on	11, 164
abstract_inverted_index.to	30, 60, 166
abstract_inverted_index.we	71, 86, 200
abstract_inverted_index.22%	221
abstract_inverted_index.The	98, 184
abstract_inverted_index.act	33
abstract_inverted_index.and	32, 54, 57, 62, 94, 115, 122, 133, 152, 158, 188, 195
abstract_inverted_index.are	155, 173
abstract_inverted_index.for	104, 181
abstract_inverted_index.how	165
abstract_inverted_index.new	204
abstract_inverted_index.the	28, 170
abstract_inverted_index.yet	7
abstract_inverted_index.Tips	151, 154, 187
abstract_inverted_index.also	138
abstract_inverted_index.down	110
abstract_inverted_index.face	40
abstract_inverted_index.fall	44
abstract_inverted_index.four	116
abstract_inverted_index.from	64, 161
abstract_inverted_index.have	1, 26
abstract_inverted_index.into	113
abstract_inverted_index.lack	58
abstract_inverted_index.mean	87
abstract_inverted_index.over	224
abstract_inverted_index.past	82
abstract_inverted_index.show	216
abstract_inverted_index.that	217
abstract_inverted_index.they	43
abstract_inverted_index.this	198
abstract_inverted_index.with	52, 169
abstract_inverted_index.error	131
abstract_inverted_index.human	49
abstract_inverted_index.large	20
abstract_inverted_index.learn	61
abstract_inverted_index.life,	6
abstract_inverted_index.model	22, 231
abstract_inverted_index.novel	141
abstract_inverted_index.often	14
abstract_inverted_index.page:	234
abstract_inverted_index.plans	107
abstract_inverted_index.prior	65, 162
abstract_inverted_index.short	45
abstract_inverted_index.tasks	10, 112, 163, 209
abstract_inverted_index.these	69
abstract_inverted_index.three	229
abstract_inverted_index.which	144
abstract_inverted_index.Action	120
abstract_inverted_index.Recent	17
abstract_inverted_index.across	228
abstract_inverted_index.action	96, 129
abstract_inverted_index.agents	25
abstract_inverted_index.atomic	178
abstract_inverted_index.become	2
abstract_inverted_index.handle	124
abstract_inverted_index.memory	149
abstract_inverted_index.mobile	12, 24, 35, 208
abstract_inverted_index.modern	5
abstract_inverted_index.module	143
abstract_inverted_index.needs,	50
abstract_inverted_index.tasks,	56
abstract_inverted_index.visual	126
abstract_inverted_index.Project	233
abstract_inverted_index.ability	29
abstract_inverted_index.capable	78
abstract_inverted_index.complex	9, 111, 207
abstract_inverted_index.current	38
abstract_inverted_index.devices	13
abstract_inverted_index.general	156
abstract_inverted_index.improve	63
abstract_inverted_index.learned	160
abstract_inverted_index.lessons	159
abstract_inverted_index.overall	106
abstract_inverted_index.remains	15
abstract_inverted_index.results	215
abstract_inverted_index.through	81
abstract_inverted_index.However,	37
abstract_inverted_index.Manager,	102
abstract_inverted_index.absolute	222
abstract_inverted_index.achieves	219
abstract_inverted_index.breaking	109
abstract_inverted_index.devising	105
abstract_inverted_index.explicit	89
abstract_inverted_index.features	139
abstract_inverted_index.guidance	157
abstract_inverted_index.interact	168
abstract_inverted_index.overcome	68
abstract_inverted_index.perceive	31
abstract_inverted_index.planning	93
abstract_inverted_index.previous	225
abstract_inverted_index.specific	182
abstract_inverted_index.struggle	51
abstract_inverted_index.tailored	180
abstract_inverted_index.Alongside	197
abstract_inverted_index.Empirical	214
abstract_inverted_index.Operator,	119
abstract_inverted_index.Shortcuts	172, 189
abstract_inverted_index.benchmark	205
abstract_inverted_index.comprises	100
abstract_inverted_index.featuring	206
abstract_inverted_index.framework	77, 99
abstract_inverted_index.immediate	128
abstract_inverted_index.inclusion	185
abstract_inverted_index.introduce	72, 201
abstract_inverted_index.long-term	148
abstract_inverted_index.low-level	95
abstract_inverted_index.maintains	145
abstract_inverted_index.multi-app	212
abstract_inverted_index.requiring	210
abstract_inverted_index.reusable,	174
abstract_inverted_index.sequences	176
abstract_inverted_index.subgoals,	114
abstract_inverted_index.Reflector,	121
abstract_inverted_index.Shortcuts.	153
abstract_inverted_index.addressing	47
abstract_inverted_index.approaches	39, 227
abstract_inverted_index.backbones.	232
abstract_inverted_index.comprising	150
abstract_inverted_index.continuous	191
abstract_inverted_index.executable	175
abstract_inverted_index.execution,	130
abstract_inverted_index.execution.	97
abstract_inverted_index.foundation	230
abstract_inverted_index.framework,	199
abstract_inverted_index.high-level	92
abstract_inverted_index.mechanisms	59
abstract_inverted_index.multimodal	21
abstract_inverted_index.navigating	8
abstract_inverted_index.operations	179
abstract_inverted_index.persistent	147
abstract_inverted_index.real-world	48
abstract_inverted_index.refinement	192
abstract_inverted_index.separation	90
abstract_inverted_index.(LMM)-based	23
abstract_inverted_index.Smartphones	0
abstract_inverted_index.challenges,	70
abstract_inverted_index.effectively	167
abstract_inverted_index.efficiency.	196
abstract_inverted_index.experience.	83
abstract_inverted_index.facilitates	190
abstract_inverted_index.improvement	223
abstract_inverted_index.information	134
abstract_inverted_index.multi-agent	76
abstract_inverted_index.perception,	127
abstract_inverted_index.performance	194
abstract_inverted_index.responsible	103
abstract_inverted_index.significant	41
abstract_inverted_index.subordinate	117
abstract_inverted_index.advancements	18
abstract_inverted_index.aggregation,	135
abstract_inverted_index.demonstrated	27
abstract_inverted_index.environment.	171
abstract_inverted_index.experiences.	66
abstract_inverted_index.fine-grained	125
abstract_inverted_index.frustrating.	16
abstract_inverted_index.hierarchical	75
abstract_inverted_index.limitations:	42
abstract_inverted_index.long-horizon	55
abstract_inverted_index.subroutines.	183
abstract_inverted_index.environments.	36
abstract_inverted_index.hierarchical,	85
abstract_inverted_index.indispensable	3
abstract_inverted_index.interactions.	213
abstract_inverted_index.long-horizon,	211
abstract_inverted_index.respectively.	136
abstract_inverted_index.verification,	132
abstract_inverted_index.Mobile-Agent-E	137, 218
abstract_inverted_index.Mobile-Eval-E,	202
abstract_inverted_index.self-evolution	80, 142
abstract_inverted_index.Mobile-Agent-E,	73
abstract_inverted_index.Notetaker--which	123
abstract_inverted_index.state-of-the-art	226
abstract_inverted_index.agents--Perceptor,	118
abstract_inverted_index.reasoning-intensive	53
abstract_inverted_index.https://x-plug.github.io/MobileAgent.	235
cited_by_percentile_year
countries_distinct_count	0
institutions_distinct_count	8
citation_normalized_percentile