Planning, Creation, Usage: Benchmarking LLMs for Comprehensive Tool Utilization in Real-World Complex Scenarios Article Swipe

PDF

Shijue Huang , Wanjun Zhong , Jianqiao Lu , Qi Zhu , Jiahui Gao , Weiwen Liu , Yutai Hou , Xingshan Zeng , Yasheng Wang , Lifeng Shang , Xin Jiang , Ruifeng Xu , Qun Liu ·

YOU? · · 2024 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2401.17167

The recent trend of using Large Language Models (LLMs) as tool agents in real-world applications underscores the necessity for comprehensive evaluations of their capabilities, particularly in complex scenarios involving planning, creating, and using tools. However, existing benchmarks typically focus on simple synthesized queries that do not reflect real-world complexity, thereby offering limited perspectives in evaluating tool utilization. To address this issue, we present UltraTool, a novel benchmark designed to improve and evaluate LLMs' ability in tool utilization within real-world scenarios. UltraTool focuses on the entire process of using tools - from planning and creating to applying them in complex tasks. It emphasizes real-world complexities, demanding accurate, multi-step planning for effective problem-solving. A key feature of UltraTool is its independent evaluation of planning with natural language, which happens before tool usage and simplifies the task solving by mapping out the intermediate steps. Thus, unlike previous work, it eliminates the restriction of pre-defined toolset. Through extensive experiments on various LLMs, we offer novel insights into the evaluation of capabilities of LLMs in tool utilization, thereby contributing a fresh perspective to this rapidly evolving field. The benchmark is publicly available at https://github.com/JoeYing1019/UltraTool.

Related Topics

Concepts

Benchmarking Business Process management Computer science Knowledge management Marketing

Metadata

Type: preprint
Language: en
Landing Page: http://arxiv.org/abs/2401.17167
PDF: https://arxiv.org/pdf/2401.17167
OA Status: green
Related Works: 10
OpenAlex ID: https://openalex.org/W4391421481

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4391421481

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.48550/arxiv.2401.17167

Digital Object Identifier
Title: Planning, Creation, Usage: Benchmarking LLMs for Comprehensive Tool Utilization in Real-World Complex Scenarios

Work title
Type: preprint

OpenAlex work type
Language: en

Primary language
Publication year: 2024

Year of publication
Publication date: 2024-01-30

Full publication date if available
Authors: Shijue Huang, Wanjun Zhong, Jianqiao Lu, Qi Zhu, Jiahui Gao, Weiwen Liu, Yutai Hou, Xingshan Zeng, Yasheng Wang, Lifeng Shang, Xin Jiang, Ruifeng Xu, Qun Liu

List of authors in order
Landing page: https://arxiv.org/abs/2401.17167

Publisher landing page
PDF URL: https://arxiv.org/pdf/2401.17167

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/2401.17167

Direct OA link when available
Concepts: Benchmarking, Business, Process management, Computer science, Knowledge management, Marketing

Top concepts (fields/topics) attached by OpenAlex
Cited by: 0

Total citation count in OpenAlex
Related works (count): 10

Other works algorithmically related by OpenAlex

Full payload

id	https://openalex.org/W4391421481
doi	https://doi.org/10.48550/arxiv.2401.17167
ids.doi	https://doi.org/10.48550/arxiv.2401.17167
ids.openalex	https://openalex.org/W4391421481
fwci
type	preprint
title	Planning, Creation, Usage: Benchmarking LLMs for Comprehensive Tool Utilization in Real-World Complex Scenarios
biblio.issue
biblio.volume
biblio.last_page
biblio.first_page
topics[0].id	https://openalex.org/T11986
topics[0].field.id	https://openalex.org/fields/18
topics[0].field.display_name	Decision Sciences
topics[0].score	0.9359999895095825
topics[0].domain.id	https://openalex.org/domains/2
topics[0].domain.display_name	Social Sciences
topics[0].subfield.id	https://openalex.org/subfields/1802
topics[0].subfield.display_name	Information Systems and Management
topics[0].display_name	Scientific Computing and Data Management
topics[1].id	https://openalex.org/T10215
topics[1].field.id	https://openalex.org/fields/17
topics[1].field.display_name	Computer Science
topics[1].score	0.9311000108718872
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	Semantic Web and Ontologies
is_xpac	False
apc_list
apc_paid
concepts[0].id	https://openalex.org/C86251818
concepts[0].level	2
concepts[0].score	0.9006087183952332
concepts[0].wikidata	https://www.wikidata.org/wiki/Q816754
concepts[0].display_name	Benchmarking
concepts[1].id	https://openalex.org/C144133560
concepts[1].level	0
concepts[1].score	0.47957342863082886
concepts[1].wikidata	https://www.wikidata.org/wiki/Q4830453
concepts[1].display_name	Business
concepts[2].id	https://openalex.org/C195094911
concepts[2].level	1
concepts[2].score	0.43304911255836487
concepts[2].wikidata	https://www.wikidata.org/wiki/Q14167904
concepts[2].display_name	Process management
concepts[3].id	https://openalex.org/C41008148
concepts[3].level	0
concepts[3].score	0.3442903757095337
concepts[3].wikidata	https://www.wikidata.org/wiki/Q21198
concepts[3].display_name	Computer science
concepts[4].id	https://openalex.org/C56739046
concepts[4].level	1
concepts[4].score	0.3237224221229553
concepts[4].wikidata	https://www.wikidata.org/wiki/Q192060
concepts[4].display_name	Knowledge management
concepts[5].id	https://openalex.org/C162853370
concepts[5].level	1
concepts[5].score	0.1836000680923462
concepts[5].wikidata	https://www.wikidata.org/wiki/Q39809
concepts[5].display_name	Marketing
keywords[0].id	https://openalex.org/keywords/benchmarking
keywords[0].score	0.9006087183952332
keywords[0].display_name	Benchmarking
keywords[1].id	https://openalex.org/keywords/business
keywords[1].score	0.47957342863082886
keywords[1].display_name	Business
keywords[2].id	https://openalex.org/keywords/process-management
keywords[2].score	0.43304911255836487
keywords[2].display_name	Process management
keywords[3].id	https://openalex.org/keywords/computer-science
keywords[3].score	0.3442903757095337
keywords[3].display_name	Computer science
keywords[4].id	https://openalex.org/keywords/knowledge-management
keywords[4].score	0.3237224221229553
keywords[4].display_name	Knowledge management
keywords[5].id	https://openalex.org/keywords/marketing
keywords[5].score	0.1836000680923462
keywords[5].display_name	Marketing
language	en
locations[0].id	pmh:oai:arXiv.org:2401.17167
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/2401.17167
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/2401.17167
locations[1].id	doi:10.48550/arxiv.2401.17167
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.2401.17167
indexed_in	arxiv, datacite
authorships[0].author.id	https://openalex.org/A5067715252
authorships[0].author.orcid	https://orcid.org/0000-0001-9443-7948
authorships[0].author.display_name	Shijue Huang
authorships[0].author_position	first
authorships[0].raw_author_name	Huang, Shijue
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5019101763
authorships[1].author.orcid	https://orcid.org/0009-0007-2236-228X
authorships[1].author.display_name	Wanjun Zhong
authorships[1].author_position	middle
authorships[1].raw_author_name	Zhong, Wanjun
authorships[1].is_corresponding	False
authorships[2].author.id	https://openalex.org/A5113021849
authorships[2].author.orcid
authorships[2].author.display_name	Jianqiao Lu
authorships[2].author_position	middle
authorships[2].raw_author_name	Lu, Jianqiao
authorships[2].is_corresponding	False
authorships[3].author.id	https://openalex.org/A5100517805
authorships[3].author.orcid
authorships[3].author.display_name	Qi Zhu
authorships[3].author_position	middle
authorships[3].raw_author_name	Zhu, Qi
authorships[3].is_corresponding	False
authorships[4].author.id	https://openalex.org/A5067047605
authorships[4].author.orcid	https://orcid.org/0000-0002-4244-174X
authorships[4].author.display_name	Jiahui Gao
authorships[4].author_position	middle
authorships[4].raw_author_name	Gao, Jiahui
authorships[4].is_corresponding	False
authorships[5].author.id	https://openalex.org/A5015039449
authorships[5].author.orcid	https://orcid.org/0000-0002-7632-9078
authorships[5].author.display_name	Weiwen Liu
authorships[5].author_position	middle
authorships[5].raw_author_name	Liu, Weiwen
authorships[5].is_corresponding	False
authorships[6].author.id	https://openalex.org/A5101299295
authorships[6].author.orcid
authorships[6].author.display_name	Yutai Hou
authorships[6].author_position	middle
authorships[6].raw_author_name	Hou, Yutai
authorships[6].is_corresponding	False
authorships[7].author.id	https://openalex.org/A5044933782
authorships[7].author.orcid	https://orcid.org/0000-0002-0455-5519
authorships[7].author.display_name	Xingshan Zeng
authorships[7].author_position	middle
authorships[7].raw_author_name	Zeng, Xingshan
authorships[7].is_corresponding	False
authorships[8].author.id	https://openalex.org/A5115592503
authorships[8].author.orcid
authorships[8].author.display_name	Yasheng Wang
authorships[8].author_position	middle
authorships[8].raw_author_name	Wang, Yasheng
authorships[8].is_corresponding	False
authorships[9].author.id	https://openalex.org/A5046228314
authorships[9].author.orcid
authorships[9].author.display_name	Lifeng Shang
authorships[9].author_position	middle
authorships[9].raw_author_name	Shang, Lifeng
authorships[9].is_corresponding	False
authorships[10].author.id	https://openalex.org/A5086603207
authorships[10].author.orcid	https://orcid.org/0000-0002-9117-8247
authorships[10].author.display_name	Xin Jiang
authorships[10].author_position	middle
authorships[10].raw_author_name	Jiang, Xin
authorships[10].is_corresponding	False
authorships[11].author.id	https://openalex.org/A5100517769
authorships[11].author.orcid
authorships[11].author.display_name	Ruifeng Xu
authorships[11].author_position	middle
authorships[11].raw_author_name	Xu, Ruifeng
authorships[11].is_corresponding	False
authorships[12].author.id	https://openalex.org/A5100426170
authorships[12].author.orcid	https://orcid.org/0000-0002-7000-1792
authorships[12].author.display_name	Qun Liu
authorships[12].author_position	last
authorships[12].raw_author_name	Liu, Qun
authorships[12].is_corresponding	False
has_content.pdf	True
has_content.grobid_xml	True
is_paratext	False
open_access.is_oa	True
open_access.oa_url	https://arxiv.org/pdf/2401.17167
open_access.oa_status	green
open_access.any_repository_has_fulltext	False
created_date	2024-02-01T00:00:00
display_name	Planning, Creation, Usage: Benchmarking LLMs for Comprehensive Tool Utilization in Real-World Complex Scenarios
has_fulltext	False
is_retracted	False
updated_date	2025-11-06T06:51:31.235846
primary_topic.id	https://openalex.org/T11986
primary_topic.field.id	https://openalex.org/fields/18
primary_topic.field.display_name	Decision Sciences
primary_topic.score	0.9359999895095825
primary_topic.domain.id	https://openalex.org/domains/2
primary_topic.domain.display_name	Social Sciences
primary_topic.subfield.id	https://openalex.org/subfields/1802
primary_topic.subfield.display_name	Information Systems and Management
primary_topic.display_name	Scientific Computing and Data Management
related_works	https://openalex.org/W2748952813, https://openalex.org/W4238897586, https://openalex.org/W435179959, https://openalex.org/W2619091065, https://openalex.org/W2059640416, https://openalex.org/W1490753184, https://openalex.org/W2284465472, https://openalex.org/W2291782699, https://openalex.org/W1993948687, https://openalex.org/W2011676020
cited_by_count	0
locations_count	2
best_oa_location.id	pmh:oai:arXiv.org:2401.17167
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/2401.17167
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/2401.17167
primary_location.id	pmh:oai:arXiv.org:2401.17167
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/2401.17167
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/2401.17167
publication_date	2024-01-30
publication_year	2024
referenced_works_count	0
abstract_inverted_index.-	89
abstract_inverted_index.A	111
abstract_inverted_index.a	64, 174
abstract_inverted_index.It	100
abstract_inverted_index.To	57
abstract_inverted_index.as	9
abstract_inverted_index.at	187
abstract_inverted_index.by	135
abstract_inverted_index.do	44
abstract_inverted_index.in	12, 25, 53, 74, 97, 169
abstract_inverted_index.is	116, 184
abstract_inverted_index.it	145
abstract_inverted_index.of	3, 21, 86, 114, 120, 149, 165, 167
abstract_inverted_index.on	39, 82, 155
abstract_inverted_index.to	68, 94, 177
abstract_inverted_index.we	61, 158
abstract_inverted_index.The	0, 182
abstract_inverted_index.and	31, 70, 92, 130
abstract_inverted_index.for	18, 108
abstract_inverted_index.its	117
abstract_inverted_index.key	112
abstract_inverted_index.not	45
abstract_inverted_index.out	137
abstract_inverted_index.the	16, 83, 132, 138, 147, 163
abstract_inverted_index.LLMs	168
abstract_inverted_index.from	90
abstract_inverted_index.into	162
abstract_inverted_index.task	133
abstract_inverted_index.that	43
abstract_inverted_index.them	96
abstract_inverted_index.this	59, 178
abstract_inverted_index.tool	10, 55, 75, 128, 170
abstract_inverted_index.with	122
abstract_inverted_index.LLMs'	72
abstract_inverted_index.LLMs,	157
abstract_inverted_index.Large	5
abstract_inverted_index.Thus,	141
abstract_inverted_index.focus	38
abstract_inverted_index.fresh	175
abstract_inverted_index.novel	65, 160
abstract_inverted_index.offer	159
abstract_inverted_index.their	22
abstract_inverted_index.tools	88
abstract_inverted_index.trend	2
abstract_inverted_index.usage	129
abstract_inverted_index.using	4, 32, 87
abstract_inverted_index.which	125
abstract_inverted_index.work,	144
abstract_inverted_index.(LLMs)	8
abstract_inverted_index.Models	7
abstract_inverted_index.agents	11
abstract_inverted_index.before	127
abstract_inverted_index.entire	84
abstract_inverted_index.field.	181
abstract_inverted_index.issue,	60
abstract_inverted_index.recent	1
abstract_inverted_index.simple	40
abstract_inverted_index.steps.	140
abstract_inverted_index.tasks.	99
abstract_inverted_index.tools.	33
abstract_inverted_index.unlike	142
abstract_inverted_index.within	77
abstract_inverted_index.Through	152
abstract_inverted_index.ability	73
abstract_inverted_index.address	58
abstract_inverted_index.complex	26, 98
abstract_inverted_index.feature	113
abstract_inverted_index.focuses	81
abstract_inverted_index.happens	126
abstract_inverted_index.improve	69
abstract_inverted_index.limited	51
abstract_inverted_index.mapping	136
abstract_inverted_index.natural	123
abstract_inverted_index.present	62
abstract_inverted_index.process	85
abstract_inverted_index.queries	42
abstract_inverted_index.rapidly	179
abstract_inverted_index.reflect	46
abstract_inverted_index.solving	134
abstract_inverted_index.thereby	49, 172
abstract_inverted_index.various	156
abstract_inverted_index.However,	34
abstract_inverted_index.Language	6
abstract_inverted_index.applying	95
abstract_inverted_index.creating	93
abstract_inverted_index.designed	67
abstract_inverted_index.evaluate	71
abstract_inverted_index.evolving	180
abstract_inverted_index.existing	35
abstract_inverted_index.insights	161
abstract_inverted_index.offering	50
abstract_inverted_index.planning	91, 107, 121
abstract_inverted_index.previous	143
abstract_inverted_index.publicly	185
abstract_inverted_index.toolset.	151
abstract_inverted_index.UltraTool	80, 115
abstract_inverted_index.accurate,	105
abstract_inverted_index.available	186
abstract_inverted_index.benchmark	66, 183
abstract_inverted_index.creating,	30
abstract_inverted_index.demanding	104
abstract_inverted_index.effective	109
abstract_inverted_index.extensive	153
abstract_inverted_index.involving	28
abstract_inverted_index.language,	124
abstract_inverted_index.necessity	17
abstract_inverted_index.planning,	29
abstract_inverted_index.scenarios	27
abstract_inverted_index.typically	37
abstract_inverted_index.UltraTool,	63
abstract_inverted_index.benchmarks	36
abstract_inverted_index.eliminates	146
abstract_inverted_index.emphasizes	101
abstract_inverted_index.evaluating	54
abstract_inverted_index.evaluation	119, 164
abstract_inverted_index.multi-step	106
abstract_inverted_index.real-world	13, 47, 78, 102
abstract_inverted_index.scenarios.	79
abstract_inverted_index.simplifies	131
abstract_inverted_index.complexity,	48
abstract_inverted_index.evaluations	20
abstract_inverted_index.experiments	154
abstract_inverted_index.independent	118
abstract_inverted_index.perspective	176
abstract_inverted_index.pre-defined	150
abstract_inverted_index.restriction	148
abstract_inverted_index.synthesized	41
abstract_inverted_index.underscores	15
abstract_inverted_index.utilization	76
abstract_inverted_index.applications	14
abstract_inverted_index.capabilities	166
abstract_inverted_index.contributing	173
abstract_inverted_index.intermediate	139
abstract_inverted_index.particularly	24
abstract_inverted_index.perspectives	52
abstract_inverted_index.utilization,	171
abstract_inverted_index.utilization.	56
abstract_inverted_index.capabilities,	23
abstract_inverted_index.complexities,	103
abstract_inverted_index.comprehensive	19
abstract_inverted_index.problem-solving.	110
abstract_inverted_index.https://github.com/JoeYing1019/UltraTool.	188
cited_by_percentile_year
countries_distinct_count	0
institutions_distinct_count	13
citation_normalized_percentile