Curiosity-Driven Testing for Sequential Decision-Making Process Article Swipe

PDF

Jieke Shi , Chengran Yang , Kisub Kim , David Lo ·

YOU? · · 2025 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2509.02025

Sequential decision-making processes (SDPs) are fundamental for complex real-world challenges, such as autonomous driving, robotic control, and traffic management. While recent advances in Deep Learning (DL) have led to mature solutions for solving these complex problems, SDMs remain vulnerable to learning unsafe behaviors, posing significant risks in safety-critical applications. However, developing a testing framework for SDMs that can identify a diverse set of crash-triggering scenarios remains an open challenge. To address this, we propose CureFuzz, a novel curiosity-driven black-box fuzz testing approach for SDMs. CureFuzz proposes a curiosity mechanism that allows a fuzzer to effectively explore novel and diverse scenarios, leading to improved detection of crashtriggering scenarios. Additionally, we introduce a multi-objective seed selection technique to balance the exploration of novel scenarios and the generation of crash-triggering scenarios, thereby optimizing the fuzzing process. We evaluate CureFuzz on various SDMs and experimental results demonstrate that CureFuzz outperforms the state-of-the-art method by a substantial margin in the total number of faults and distinct types of crash-triggering scenarios. We also demonstrate that the crash-triggering scenarios found by CureFuzz can repair SDMs, highlighting CureFuzz as a valuable tool for testing SDMs and optimizing their performance.

Related Topics

Sequential Art

The Testing Of Luther Albright

Comics And Sequential Art

Nuclear Weapons Testing

Nuclear Testing At Bikini Atoll

A/B Testing

Software Testing

White-Box Testing

Cannabis Drug Testing

Regression Testing

Sequential Hermaphroditism

Underground Nuclear Weapons Testing

Concepts

No concepts available.

Metadata

Type: preprint
Language: en
Landing Page: http://arxiv.org/abs/2509.02025
PDF: https://arxiv.org/pdf/2509.02025
OA Status: green
OpenAlex ID: https://openalex.org/W4416703656

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4416703656

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.48550/arxiv.2509.02025

Digital Object Identifier
Title: Curiosity-Driven Testing for Sequential Decision-Making Process

Work title
Type: preprint

OpenAlex work type
Language: en

Primary language
Publication year: 2025

Year of publication
Publication date: 2025-09-02

Full publication date if available
Authors: Jieke Shi, Chengran Yang, Kisub Kim, David Lo

List of authors in order
Landing page: https://arxiv.org/abs/2509.02025

Publisher landing page
PDF URL: https://arxiv.org/pdf/2509.02025

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/2509.02025

Direct OA link when available
Cited by: 0

Total citation count in OpenAlex

Full payload

id	https://openalex.org/W4416703656
doi	https://doi.org/10.48550/arxiv.2509.02025
ids.doi	https://doi.org/10.48550/arxiv.2509.02025
ids.openalex	https://openalex.org/W4416703656
fwci
type	preprint
title	Curiosity-Driven Testing for Sequential Decision-Making Process
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:2509.02025
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/2509.02025
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/2509.02025
locations[1].id	doi:10.48550/arxiv.2509.02025
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.2509.02025
indexed_in	arxiv, datacite
authorships[0].author.id	https://openalex.org/A5002667771
authorships[0].author.orcid	https://orcid.org/0000-0002-0799-5018
authorships[0].author.display_name	Jieke Shi
authorships[0].author_position	middle
authorships[0].raw_author_name	Shi, Jieke
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5066446055
authorships[1].author.orcid	https://orcid.org/0000-0001-6100-8127
authorships[1].author.display_name	Chengran Yang
authorships[1].author_position	last
authorships[1].raw_author_name	Yang, Chengran
authorships[1].is_corresponding	False
authorships[2].author.id	https://openalex.org/A5074029092
authorships[2].author.orcid	https://orcid.org/0000-0002-4462-6916
authorships[2].author.display_name	Kisub Kim
authorships[2].author_position	middle
authorships[2].raw_author_name	Kim, Kisub
authorships[2].is_corresponding	False
authorships[3].author.id	https://openalex.org/A5081036622
authorships[3].author.orcid	https://orcid.org/0000-0002-4367-7201
authorships[3].author.display_name	David Lo
authorships[3].author_position	middle
authorships[3].raw_author_name	Lo, David
authorships[3].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/2509.02025
open_access.oa_status	green
open_access.any_repository_has_fulltext	False
created_date	2025-10-10T00:00:00
display_name	Curiosity-Driven Testing for Sequential Decision-Making Process
has_fulltext	False
is_retracted	False
updated_date	2025-11-28T21:05:06.107286
primary_topic
cited_by_count	0
locations_count	2
best_oa_location.id	pmh:oai:arXiv.org:2509.02025
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/2509.02025
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/2509.02025
primary_location.id	pmh:oai:arXiv.org:2509.02025
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/2509.02025
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/2509.02025
publication_date	2025-09-02
publication_year	2025
referenced_works_count	0
abstract_inverted_index.a	51, 59, 75, 86, 91, 110, 150, 181
abstract_inverted_index.To	69
abstract_inverted_index.We	133, 165
abstract_inverted_index.an	66
abstract_inverted_index.as	11, 180
abstract_inverted_index.by	149, 173
abstract_inverted_index.in	22, 46, 153
abstract_inverted_index.of	62, 104, 119, 125, 157, 162
abstract_inverted_index.on	136
abstract_inverted_index.to	28, 39, 93, 101, 115
abstract_inverted_index.we	72, 108
abstract_inverted_index.and	16, 97, 122, 139, 159, 187
abstract_inverted_index.are	4
abstract_inverted_index.can	57, 175
abstract_inverted_index.for	6, 31, 54, 82, 184
abstract_inverted_index.led	27
abstract_inverted_index.set	61
abstract_inverted_index.the	117, 123, 130, 146, 154, 169
abstract_inverted_index.(DL)	25
abstract_inverted_index.Deep	23
abstract_inverted_index.SDMs	36, 55, 138, 186
abstract_inverted_index.also	166
abstract_inverted_index.fuzz	79
abstract_inverted_index.have	26
abstract_inverted_index.open	67
abstract_inverted_index.seed	112
abstract_inverted_index.such	10
abstract_inverted_index.that	56, 89, 143, 168
abstract_inverted_index.tool	183
abstract_inverted_index.SDMs,	177
abstract_inverted_index.SDMs.	83
abstract_inverted_index.While	19
abstract_inverted_index.found	172
abstract_inverted_index.novel	76, 96, 120
abstract_inverted_index.risks	45
abstract_inverted_index.their	189
abstract_inverted_index.these	33
abstract_inverted_index.this,	71
abstract_inverted_index.total	155
abstract_inverted_index.types	161
abstract_inverted_index.(SDPs)	3
abstract_inverted_index.allows	90
abstract_inverted_index.faults	158
abstract_inverted_index.fuzzer	92
abstract_inverted_index.margin	152
abstract_inverted_index.mature	29
abstract_inverted_index.method	148
abstract_inverted_index.number	156
abstract_inverted_index.posing	43
abstract_inverted_index.recent	20
abstract_inverted_index.remain	37
abstract_inverted_index.repair	176
abstract_inverted_index.unsafe	41
abstract_inverted_index.address	70
abstract_inverted_index.balance	116
abstract_inverted_index.complex	7, 34
abstract_inverted_index.diverse	60, 98
abstract_inverted_index.explore	95
abstract_inverted_index.fuzzing	131
abstract_inverted_index.leading	100
abstract_inverted_index.propose	73
abstract_inverted_index.remains	65
abstract_inverted_index.results	141
abstract_inverted_index.robotic	14
abstract_inverted_index.solving	32
abstract_inverted_index.testing	52, 80, 185
abstract_inverted_index.thereby	128
abstract_inverted_index.traffic	17
abstract_inverted_index.various	137
abstract_inverted_index.CureFuzz	84, 135, 144, 174, 179
abstract_inverted_index.However,	49
abstract_inverted_index.Learning	24
abstract_inverted_index.advances	21
abstract_inverted_index.approach	81
abstract_inverted_index.control,	15
abstract_inverted_index.distinct	160
abstract_inverted_index.driving,	13
abstract_inverted_index.evaluate	134
abstract_inverted_index.identify	58
abstract_inverted_index.improved	102
abstract_inverted_index.learning	40
abstract_inverted_index.process.	132
abstract_inverted_index.proposes	85
abstract_inverted_index.valuable	182
abstract_inverted_index.CureFuzz,	74
abstract_inverted_index.black-box	78
abstract_inverted_index.curiosity	87
abstract_inverted_index.detection	103
abstract_inverted_index.framework	53
abstract_inverted_index.introduce	109
abstract_inverted_index.mechanism	88
abstract_inverted_index.problems,	35
abstract_inverted_index.processes	2
abstract_inverted_index.scenarios	64, 121, 171
abstract_inverted_index.selection	113
abstract_inverted_index.solutions	30
abstract_inverted_index.technique	114
abstract_inverted_index.Sequential	0
abstract_inverted_index.autonomous	12
abstract_inverted_index.behaviors,	42
abstract_inverted_index.challenge.	68
abstract_inverted_index.developing	50
abstract_inverted_index.generation	124
abstract_inverted_index.optimizing	129, 188
abstract_inverted_index.real-world	8
abstract_inverted_index.scenarios,	99, 127
abstract_inverted_index.scenarios.	106, 164
abstract_inverted_index.vulnerable	38
abstract_inverted_index.challenges,	9
abstract_inverted_index.demonstrate	142, 167
abstract_inverted_index.effectively	94
abstract_inverted_index.exploration	118
abstract_inverted_index.fundamental	5
abstract_inverted_index.management.	18
abstract_inverted_index.outperforms	145
abstract_inverted_index.significant	44
abstract_inverted_index.substantial	151
abstract_inverted_index.experimental	140
abstract_inverted_index.highlighting	178
abstract_inverted_index.performance.	190
abstract_inverted_index.Additionally,	107
abstract_inverted_index.applications.	48
abstract_inverted_index.crashtriggering	105
abstract_inverted_index.decision-making	1
abstract_inverted_index.multi-objective	111
abstract_inverted_index.safety-critical	47
abstract_inverted_index.crash-triggering	63, 126, 163, 170
abstract_inverted_index.curiosity-driven	77
abstract_inverted_index.state-of-the-art	147
cited_by_percentile_year
countries_distinct_count	0
institutions_distinct_count	4
citation_normalized_percentile