PlanGEN: A Multi-Agent Framework for Generating Planning and Reasoning Trajectories for Complex Problem Solving Article Swipe

PDF

Mihir Parmar , Xin Liu , Palash Goyal , Yanfei Chen , Long Bao Le , Swaroop Mishra , Hossein Mobahi , Jindong Gu , Zifeng Wang , Hootan Nakhost , Chitta Baral , Chen-Yu Lee , Tomas Pfister , Hamid Palangi ·

YOU? · · 2025 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2502.16111

Recent agent frameworks and inference-time algorithms often struggle with complex planning problems due to limitations in verifying generated plans or reasoning and varying complexity of instances within a single task. Many existing methods for these tasks either perform task-level verification without considering constraints or apply inference-time algorithms without adapting to instance-level complexity. To address these limitations, we propose PlanGEN, a model-agnostic and easily scalable agent framework with three key components: constraint, verification, and selection agents. Specifically, our approach proposes constraint-guided iterative verification to enhance performance of inference-time algorithms--Best of N, Tree-of-Thought, and REBASE. In PlanGEN framework, the selection agent optimizes algorithm choice based on instance complexity, ensuring better adaptability to complex planning problems. Experimental results demonstrate significant improvements over the strongest baseline across multiple benchmarks, achieving state-of-the-art results on NATURAL PLAN ($\sim$8%$\uparrow$), OlympiadBench ($\sim$4%$\uparrow$), DocFinQA ($\sim$7%$\uparrow$), and GPQA ($\sim$1%$\uparrow$). Our key finding highlights that constraint-guided iterative verification improves inference-time algorithms, and adaptive selection further boosts performance on complex planning and reasoning problems.

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/2502.16111
PDF: https://arxiv.org/pdf/2502.16111
OA Status: green
OpenAlex ID: https://openalex.org/W4414837915

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4414837915

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.48550/arxiv.2502.16111

Digital Object Identifier
Title: PlanGEN: A Multi-Agent Framework for Generating Planning and Reasoning Trajectories for Complex Problem Solving

Work title
Type: preprint

OpenAlex work type
Language: en

Primary language
Publication year: 2025

Year of publication
Publication date: 2025-02-22

Full publication date if available
Authors: Mihir Parmar, Xin Liu, Palash Goyal, Yanfei Chen, Long Bao Le, Swaroop Mishra, Hossein Mobahi, Jindong Gu, Zifeng Wang, Hootan Nakhost, Chitta Baral, Chen-Yu Lee, Tomas Pfister, Hamid Palangi

List of authors in order
Landing page: https://arxiv.org/abs/2502.16111

Publisher landing page
PDF URL: https://arxiv.org/pdf/2502.16111

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/2502.16111

Direct OA link when available
Cited by: 0

Total citation count in OpenAlex

Full payload

id	https://openalex.org/W4414837915
doi	https://doi.org/10.48550/arxiv.2502.16111
ids.doi	https://doi.org/10.48550/arxiv.2502.16111
ids.openalex	https://openalex.org/W4414837915
fwci
type	preprint
title	PlanGEN: A Multi-Agent Framework for Generating Planning and Reasoning Trajectories for Complex Problem Solving
biblio.issue
biblio.volume
biblio.last_page
biblio.first_page
topics[0].id	https://openalex.org/T11810
topics[0].field.id	https://openalex.org/fields/18
topics[0].field.display_name	Decision Sciences
topics[0].score	0.9611999988555908
topics[0].domain.id	https://openalex.org/domains/2
topics[0].domain.display_name	Social Sciences
topics[0].subfield.id	https://openalex.org/subfields/1803
topics[0].subfield.display_name	Management Science and Operations Research
topics[0].display_name	Complex Systems and Decision Making
is_xpac	False
apc_list
apc_paid
language	en
locations[0].id	pmh:oai:arXiv.org:2502.16111
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/2502.16111
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/2502.16111
locations[1].id	doi:10.48550/arxiv.2502.16111
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.2502.16111
indexed_in	arxiv, datacite
authorships[0].author.id	https://openalex.org/A5106524687
authorships[0].author.orcid
authorships[0].author.display_name	Mihir Parmar
authorships[0].author_position	first
authorships[0].raw_author_name	Parmar, Mihir
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5100352352
authorships[1].author.orcid	https://orcid.org/0000-0003-4864-2849
authorships[1].author.display_name	Xin Liu
authorships[1].author_position	middle
authorships[1].raw_author_name	Liu, Xin
authorships[1].is_corresponding	False
authorships[2].author.id	https://openalex.org/A5011797382
authorships[2].author.orcid	https://orcid.org/0000-0003-2455-2160
authorships[2].author.display_name	Palash Goyal
authorships[2].author_position	middle
authorships[2].raw_author_name	Goyal, Palash
authorships[2].is_corresponding	False
authorships[3].author.id	https://openalex.org/A5100658754
authorships[3].author.orcid	https://orcid.org/0000-0001-5346-9679
authorships[3].author.display_name	Yanfei Chen
authorships[3].author_position	middle
authorships[3].raw_author_name	Chen, Yanfei
authorships[3].is_corresponding	False
authorships[4].author.id	https://openalex.org/A5029986211
authorships[4].author.orcid	https://orcid.org/0000-0003-3577-6530
authorships[4].author.display_name	Long Bao Le
authorships[4].author_position	middle
authorships[4].raw_author_name	Le, Long
authorships[4].is_corresponding	False
authorships[5].author.id	https://openalex.org/A5063722751
authorships[5].author.orcid	https://orcid.org/0009-0001-6413-7001
authorships[5].author.display_name	Swaroop Mishra
authorships[5].author_position	middle
authorships[5].raw_author_name	Mishra, Swaroop
authorships[5].is_corresponding	False
authorships[6].author.id	https://openalex.org/A5003384169
authorships[6].author.orcid
authorships[6].author.display_name	Hossein Mobahi
authorships[6].author_position	middle
authorships[6].raw_author_name	Mobahi, Hossein
authorships[6].is_corresponding	False
authorships[7].author.id	https://openalex.org/A5055994909
authorships[7].author.orcid	https://orcid.org/0009-0000-0574-0129
authorships[7].author.display_name	Jindong Gu
authorships[7].author_position	middle
authorships[7].raw_author_name	Gu, Jindong
authorships[7].is_corresponding	False
authorships[8].author.id	https://openalex.org/A5083937465
authorships[8].author.orcid	https://orcid.org/0000-0002-5292-8885
authorships[8].author.display_name	Zifeng Wang
authorships[8].author_position	middle
authorships[8].raw_author_name	Wang, Zifeng
authorships[8].is_corresponding	False
authorships[9].author.id	https://openalex.org/A5060969697
authorships[9].author.orcid
authorships[9].author.display_name	Hootan Nakhost
authorships[9].author_position	middle
authorships[9].raw_author_name	Nakhost, Hootan
authorships[9].is_corresponding	False
authorships[10].author.id	https://openalex.org/A5083735830
authorships[10].author.orcid	https://orcid.org/0000-0002-7549-723X
authorships[10].author.display_name	Chitta Baral
authorships[10].author_position	middle
authorships[10].raw_author_name	Baral, Chitta
authorships[10].is_corresponding	False
authorships[11].author.id	https://openalex.org/A5005652285
authorships[11].author.orcid	https://orcid.org/0009-0008-3275-6028
authorships[11].author.display_name	Chen-Yu Lee
authorships[11].author_position	middle
authorships[11].raw_author_name	Lee, Chen-Yu
authorships[11].is_corresponding	False
authorships[12].author.id	https://openalex.org/A5092595935
authorships[12].author.orcid	https://orcid.org/0009-0004-4088-8718
authorships[12].author.display_name	Tomas Pfister
authorships[12].author_position	middle
authorships[12].raw_author_name	Pfister, Tomas
authorships[12].is_corresponding	False
authorships[13].author.id	https://openalex.org/A5033846851
authorships[13].author.orcid	https://orcid.org/0000-0003-2912-4579
authorships[13].author.display_name	Hamid Palangi
authorships[13].author_position	last
authorships[13].raw_author_name	Palangi, Hamid
authorships[13].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/2502.16111
open_access.oa_status	green
open_access.any_repository_has_fulltext	False
created_date	2025-10-10T00:00:00
display_name	PlanGEN: A Multi-Agent Framework for Generating Planning and Reasoning Trajectories for Complex Problem Solving
has_fulltext	False
is_retracted	False
updated_date	2025-11-06T06:51:31.235846
primary_topic.id	https://openalex.org/T11810
primary_topic.field.id	https://openalex.org/fields/18
primary_topic.field.display_name	Decision Sciences
primary_topic.score	0.9611999988555908
primary_topic.domain.id	https://openalex.org/domains/2
primary_topic.domain.display_name	Social Sciences
primary_topic.subfield.id	https://openalex.org/subfields/1803
primary_topic.subfield.display_name	Management Science and Operations Research
primary_topic.display_name	Complex Systems and Decision Making
cited_by_count	0
locations_count	2
best_oa_location.id	pmh:oai:arXiv.org:2502.16111
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/2502.16111
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/2502.16111
primary_location.id	pmh:oai:arXiv.org:2502.16111
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/2502.16111
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/2502.16111
publication_date	2025-02-22
publication_year	2025
referenced_works_count	0
abstract_inverted_index.a	27, 59
abstract_inverted_index.In	93
abstract_inverted_index.N,	89
abstract_inverted_index.To	52
abstract_inverted_index.in	15
abstract_inverted_index.of	24, 85, 88
abstract_inverted_index.on	103, 128, 156
abstract_inverted_index.or	19, 43
abstract_inverted_index.to	13, 49, 82, 109
abstract_inverted_index.we	56
abstract_inverted_index.Our	139
abstract_inverted_index.and	3, 21, 61, 72, 91, 136, 150, 159
abstract_inverted_index.due	12
abstract_inverted_index.for	33
abstract_inverted_index.key	68, 140
abstract_inverted_index.our	76
abstract_inverted_index.the	96, 119
abstract_inverted_index.GPQA	137
abstract_inverted_index.Many	30
abstract_inverted_index.PLAN	130
abstract_inverted_index.over	118
abstract_inverted_index.that	143
abstract_inverted_index.with	8, 66
abstract_inverted_index.agent	1, 64, 98
abstract_inverted_index.apply	44
abstract_inverted_index.based	102
abstract_inverted_index.often	6
abstract_inverted_index.plans	18
abstract_inverted_index.task.	29
abstract_inverted_index.tasks	35
abstract_inverted_index.these	34, 54
abstract_inverted_index.three	67
abstract_inverted_index.Recent	0
abstract_inverted_index.across	122
abstract_inverted_index.better	107
abstract_inverted_index.boosts	154
abstract_inverted_index.choice	101
abstract_inverted_index.easily	62
abstract_inverted_index.either	36
abstract_inverted_index.single	28
abstract_inverted_index.within	26
abstract_inverted_index.NATURAL	129
abstract_inverted_index.PlanGEN	94
abstract_inverted_index.REBASE.	92
abstract_inverted_index.address	53
abstract_inverted_index.agents.	74
abstract_inverted_index.complex	9, 110, 157
abstract_inverted_index.enhance	83
abstract_inverted_index.finding	141
abstract_inverted_index.further	153
abstract_inverted_index.methods	32
abstract_inverted_index.perform	37
abstract_inverted_index.propose	57
abstract_inverted_index.results	114, 127
abstract_inverted_index.varying	22
abstract_inverted_index.without	40, 47
abstract_inverted_index.DocFinQA	134
abstract_inverted_index.PlanGEN,	58
abstract_inverted_index.adapting	48
abstract_inverted_index.adaptive	151
abstract_inverted_index.approach	77
abstract_inverted_index.baseline	121
abstract_inverted_index.ensuring	106
abstract_inverted_index.existing	31
abstract_inverted_index.improves	147
abstract_inverted_index.instance	104
abstract_inverted_index.multiple	123
abstract_inverted_index.planning	10, 111, 158
abstract_inverted_index.problems	11
abstract_inverted_index.proposes	78
abstract_inverted_index.scalable	63
abstract_inverted_index.struggle	7
abstract_inverted_index.achieving	125
abstract_inverted_index.algorithm	100
abstract_inverted_index.framework	65
abstract_inverted_index.generated	17
abstract_inverted_index.instances	25
abstract_inverted_index.iterative	80, 145
abstract_inverted_index.optimizes	99
abstract_inverted_index.problems.	112, 161
abstract_inverted_index.reasoning	20, 160
abstract_inverted_index.selection	73, 97, 152
abstract_inverted_index.strongest	120
abstract_inverted_index.verifying	16
abstract_inverted_index.algorithms	5, 46
abstract_inverted_index.complexity	23
abstract_inverted_index.framework,	95
abstract_inverted_index.frameworks	2
abstract_inverted_index.highlights	142
abstract_inverted_index.task-level	38
abstract_inverted_index.algorithms,	149
abstract_inverted_index.benchmarks,	124
abstract_inverted_index.complexity,	105
abstract_inverted_index.complexity.	51
abstract_inverted_index.components:	69
abstract_inverted_index.considering	41
abstract_inverted_index.constraint,	70
abstract_inverted_index.constraints	42
abstract_inverted_index.demonstrate	115
abstract_inverted_index.limitations	14
abstract_inverted_index.performance	84, 155
abstract_inverted_index.significant	116
abstract_inverted_index.Experimental	113
abstract_inverted_index.adaptability	108
abstract_inverted_index.improvements	117
abstract_inverted_index.limitations,	55
abstract_inverted_index.verification	39, 81, 146
abstract_inverted_index.OlympiadBench	132
abstract_inverted_index.Specifically,	75
abstract_inverted_index.verification,	71
abstract_inverted_index.inference-time	4, 45, 86, 148
abstract_inverted_index.instance-level	50
abstract_inverted_index.model-agnostic	60
abstract_inverted_index.Tree-of-Thought,	90
abstract_inverted_index.algorithms--Best	87
abstract_inverted_index.state-of-the-art	126
abstract_inverted_index.constraint-guided	79, 144
abstract_inverted_index.($\sim$1%$\uparrow$).	138
abstract_inverted_index.($\sim$4%$\uparrow$),	133
abstract_inverted_index.($\sim$7%$\uparrow$),	135
abstract_inverted_index.($\sim$8%$\uparrow$),	131
cited_by_percentile_year
countries_distinct_count	0
institutions_distinct_count	14
citation_normalized_percentile