MARLIN: Multi-Agent Reinforcement Learning with Murmuration Intelligence and LLM Guidance for Reservoir Management Article Swipe
Heming Fu
,
Guojun Xiong
,
Shan Lin
·
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2509.25034
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2509.25034
As climate change intensifies extreme weather events, water disasters pose growing threats to global communities, making adaptive reservoir management critical for protecting vulnerable populations and ensuring water security. Modern water resource management faces unprecedented challenges from cascading uncertainties propagating through interconnected reservoir networks. These uncertainties, rooted in physical water transfer losses and environmental variability, make precise control difficult. For example, sending 10 tons downstream may yield only 8-12 tons due to evaporation and seepage. Traditional centralized optimization approaches suffer from exponential computational complexity and cannot effectively handle such real-world uncertainties, while existing multi-agent reinforcement learning (MARL) methods fail to achieve effective coordination under uncertainty. To address these challenges, we present MARLIN, a decentralized reservoir management framework inspired by starling murmurations intelligence. Integrating bio-inspired alignment, separation, and cohesion rules with MARL, MARLIN enables individual reservoirs to make local decisions while achieving emergent global coordination. In addition, a LLM provides real-time reward shaping signals, guiding agents to adapt to environmental changes and human-defined preferences. Experiments on real-world USGS data show that MARLIN improves uncertainty handling by 23\%, cuts computation by 35\%, and accelerates flood response by 68\%, exhibiting super-linear coordination, with complexity scaling 5.4x from 400 to 10,000 nodes. These results demonstrate MARLIN's potential for disaster prevention and protecting communities through intelligent, scalable water resource management.
Related Topics
Concepts
No concepts available.
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2509.25034
- https://arxiv.org/pdf/2509.25034
- OA Status
- green
- OpenAlex ID
- https://openalex.org/W4415337629
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4415337629Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2509.25034Digital Object Identifier
- Title
-
MARLIN: Multi-Agent Reinforcement Learning with Murmuration Intelligence and LLM Guidance for Reservoir ManagementWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2025Year of publication
- Publication date
-
2025-09-29Full publication date if available
- Authors
-
Heming Fu, Guojun Xiong, Shan LinList of authors in order
- Landing page
-
https://arxiv.org/abs/2509.25034Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2509.25034Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://arxiv.org/pdf/2509.25034Direct OA link when available
- Cited by
-
0Total citation count in OpenAlex
Full payload
| id | https://openalex.org/W4415337629 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2509.25034 |
| ids.doi | https://doi.org/10.48550/arxiv.2509.25034 |
| ids.openalex | https://openalex.org/W4415337629 |
| fwci | |
| type | preprint |
| title | MARLIN: Multi-Agent Reinforcement Learning with Murmuration Intelligence and LLM Guidance for Reservoir Management |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T11801 |
| topics[0].field.id | https://openalex.org/fields/22 |
| topics[0].field.display_name | Engineering |
| topics[0].score | 0.992900013923645 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/2212 |
| topics[0].subfield.display_name | Ocean Engineering |
| topics[0].display_name | Reservoir Engineering and Simulation Methods |
| topics[1].id | https://openalex.org/T12761 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9139999747276306 |
| 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 | Data Stream Mining Techniques |
| topics[2].id | https://openalex.org/T10462 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9039999842643738 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1702 |
| topics[2].subfield.display_name | Artificial Intelligence |
| topics[2].display_name | Reinforcement Learning in Robotics |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2509.25034 |
| 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/2509.25034 |
| 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/2509.25034 |
| locations[1].id | doi:10.48550/arxiv.2509.25034 |
| 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.2509.25034 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5023775015 |
| authorships[0].author.orcid | https://orcid.org/0000-0002-2221-0143 |
| authorships[0].author.display_name | Heming Fu |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Fu, Heming |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5102620407 |
| authorships[1].author.orcid | |
| authorships[1].author.display_name | Guojun Xiong |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Xiong, Guojun |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5003166096 |
| authorships[2].author.orcid | https://orcid.org/0000-0001-6362-2972 |
| authorships[2].author.display_name | Shan Lin |
| authorships[2].author_position | last |
| authorships[2].raw_author_name | Lin, Shan |
| authorships[2].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/2509.25034 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-19T00:00:00 |
| display_name | MARLIN: Multi-Agent Reinforcement Learning with Murmuration Intelligence and LLM Guidance for Reservoir Management |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T11801 |
| primary_topic.field.id | https://openalex.org/fields/22 |
| primary_topic.field.display_name | Engineering |
| primary_topic.score | 0.992900013923645 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/2212 |
| primary_topic.subfield.display_name | Ocean Engineering |
| primary_topic.display_name | Reservoir Engineering and Simulation Methods |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2509.25034 |
| 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/2509.25034 |
| 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/2509.25034 |
| primary_location.id | pmh:oai:arXiv.org:2509.25034 |
| 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/2509.25034 |
| 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/2509.25034 |
| publication_date | 2025-09-29 |
| publication_year | 2025 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 111, 145 |
| abstract_inverted_index.10 | 61 |
| abstract_inverted_index.As | 0 |
| abstract_inverted_index.In | 143 |
| abstract_inverted_index.To | 104 |
| abstract_inverted_index.by | 117, 173, 177, 183 |
| abstract_inverted_index.in | 46 |
| abstract_inverted_index.on | 163 |
| abstract_inverted_index.to | 12, 70, 98, 134, 154, 156, 194 |
| abstract_inverted_index.we | 108 |
| abstract_inverted_index.400 | 193 |
| abstract_inverted_index.For | 58 |
| abstract_inverted_index.LLM | 146 |
| abstract_inverted_index.and | 24, 51, 72, 83, 125, 159, 179, 205 |
| abstract_inverted_index.due | 69 |
| abstract_inverted_index.for | 20, 202 |
| abstract_inverted_index.may | 64 |
| abstract_inverted_index.5.4x | 191 |
| abstract_inverted_index.8-12 | 67 |
| abstract_inverted_index.USGS | 165 |
| abstract_inverted_index.cuts | 175 |
| abstract_inverted_index.data | 166 |
| abstract_inverted_index.fail | 97 |
| abstract_inverted_index.from | 35, 79, 192 |
| abstract_inverted_index.make | 54, 135 |
| abstract_inverted_index.only | 66 |
| abstract_inverted_index.pose | 9 |
| abstract_inverted_index.show | 167 |
| abstract_inverted_index.such | 87 |
| abstract_inverted_index.that | 168 |
| abstract_inverted_index.tons | 62, 68 |
| abstract_inverted_index.with | 128, 188 |
| abstract_inverted_index.23\%, | 174 |
| abstract_inverted_index.35\%, | 178 |
| abstract_inverted_index.68\%, | 184 |
| abstract_inverted_index.MARL, | 129 |
| abstract_inverted_index.These | 43, 197 |
| abstract_inverted_index.adapt | 155 |
| abstract_inverted_index.faces | 32 |
| abstract_inverted_index.flood | 181 |
| abstract_inverted_index.local | 136 |
| abstract_inverted_index.rules | 127 |
| abstract_inverted_index.these | 106 |
| abstract_inverted_index.under | 102 |
| abstract_inverted_index.water | 7, 26, 29, 48, 211 |
| abstract_inverted_index.while | 90, 138 |
| abstract_inverted_index.yield | 65 |
| abstract_inverted_index.(MARL) | 95 |
| abstract_inverted_index.10,000 | 195 |
| abstract_inverted_index.MARLIN | 130, 169 |
| abstract_inverted_index.Modern | 28 |
| abstract_inverted_index.agents | 153 |
| abstract_inverted_index.cannot | 84 |
| abstract_inverted_index.change | 2 |
| abstract_inverted_index.global | 13, 141 |
| abstract_inverted_index.handle | 86 |
| abstract_inverted_index.losses | 50 |
| abstract_inverted_index.making | 15 |
| abstract_inverted_index.nodes. | 196 |
| abstract_inverted_index.reward | 149 |
| abstract_inverted_index.rooted | 45 |
| abstract_inverted_index.suffer | 78 |
| abstract_inverted_index.MARLIN, | 110 |
| abstract_inverted_index.achieve | 99 |
| abstract_inverted_index.address | 105 |
| abstract_inverted_index.changes | 158 |
| abstract_inverted_index.climate | 1 |
| abstract_inverted_index.control | 56 |
| abstract_inverted_index.enables | 131 |
| abstract_inverted_index.events, | 6 |
| abstract_inverted_index.extreme | 4 |
| abstract_inverted_index.growing | 10 |
| abstract_inverted_index.guiding | 152 |
| abstract_inverted_index.methods | 96 |
| abstract_inverted_index.precise | 55 |
| abstract_inverted_index.present | 109 |
| abstract_inverted_index.results | 198 |
| abstract_inverted_index.scaling | 190 |
| abstract_inverted_index.sending | 60 |
| abstract_inverted_index.shaping | 150 |
| abstract_inverted_index.threats | 11 |
| abstract_inverted_index.through | 39, 208 |
| abstract_inverted_index.weather | 5 |
| abstract_inverted_index.MARLIN's | 200 |
| abstract_inverted_index.adaptive | 16 |
| abstract_inverted_index.cohesion | 126 |
| abstract_inverted_index.critical | 19 |
| abstract_inverted_index.disaster | 203 |
| abstract_inverted_index.emergent | 140 |
| abstract_inverted_index.ensuring | 25 |
| abstract_inverted_index.example, | 59 |
| abstract_inverted_index.existing | 91 |
| abstract_inverted_index.handling | 172 |
| abstract_inverted_index.improves | 170 |
| abstract_inverted_index.inspired | 116 |
| abstract_inverted_index.learning | 94 |
| abstract_inverted_index.physical | 47 |
| abstract_inverted_index.provides | 147 |
| abstract_inverted_index.resource | 30, 212 |
| abstract_inverted_index.response | 182 |
| abstract_inverted_index.scalable | 210 |
| abstract_inverted_index.seepage. | 73 |
| abstract_inverted_index.signals, | 151 |
| abstract_inverted_index.starling | 118 |
| abstract_inverted_index.transfer | 49 |
| abstract_inverted_index.achieving | 139 |
| abstract_inverted_index.addition, | 144 |
| abstract_inverted_index.cascading | 36 |
| abstract_inverted_index.decisions | 137 |
| abstract_inverted_index.disasters | 8 |
| abstract_inverted_index.effective | 100 |
| abstract_inverted_index.framework | 115 |
| abstract_inverted_index.networks. | 42 |
| abstract_inverted_index.potential | 201 |
| abstract_inverted_index.real-time | 148 |
| abstract_inverted_index.reservoir | 17, 41, 113 |
| abstract_inverted_index.security. | 27 |
| abstract_inverted_index.alignment, | 123 |
| abstract_inverted_index.approaches | 77 |
| abstract_inverted_index.challenges | 34 |
| abstract_inverted_index.complexity | 82, 189 |
| abstract_inverted_index.difficult. | 57 |
| abstract_inverted_index.downstream | 63 |
| abstract_inverted_index.exhibiting | 185 |
| abstract_inverted_index.individual | 132 |
| abstract_inverted_index.management | 18, 31, 114 |
| abstract_inverted_index.prevention | 204 |
| abstract_inverted_index.protecting | 21, 206 |
| abstract_inverted_index.real-world | 88, 164 |
| abstract_inverted_index.reservoirs | 133 |
| abstract_inverted_index.vulnerable | 22 |
| abstract_inverted_index.Experiments | 162 |
| abstract_inverted_index.Integrating | 121 |
| abstract_inverted_index.Traditional | 74 |
| abstract_inverted_index.accelerates | 180 |
| abstract_inverted_index.centralized | 75 |
| abstract_inverted_index.challenges, | 107 |
| abstract_inverted_index.communities | 207 |
| abstract_inverted_index.computation | 176 |
| abstract_inverted_index.demonstrate | 199 |
| abstract_inverted_index.effectively | 85 |
| abstract_inverted_index.evaporation | 71 |
| abstract_inverted_index.exponential | 80 |
| abstract_inverted_index.intensifies | 3 |
| abstract_inverted_index.management. | 213 |
| abstract_inverted_index.multi-agent | 92 |
| abstract_inverted_index.populations | 23 |
| abstract_inverted_index.propagating | 38 |
| abstract_inverted_index.separation, | 124 |
| abstract_inverted_index.uncertainty | 171 |
| abstract_inverted_index.bio-inspired | 122 |
| abstract_inverted_index.communities, | 14 |
| abstract_inverted_index.coordination | 101 |
| abstract_inverted_index.intelligent, | 209 |
| abstract_inverted_index.murmurations | 119 |
| abstract_inverted_index.optimization | 76 |
| abstract_inverted_index.preferences. | 161 |
| abstract_inverted_index.super-linear | 186 |
| abstract_inverted_index.uncertainty. | 103 |
| abstract_inverted_index.variability, | 53 |
| abstract_inverted_index.computational | 81 |
| abstract_inverted_index.coordination, | 187 |
| abstract_inverted_index.coordination. | 142 |
| abstract_inverted_index.decentralized | 112 |
| abstract_inverted_index.environmental | 52, 157 |
| abstract_inverted_index.human-defined | 160 |
| abstract_inverted_index.intelligence. | 120 |
| abstract_inverted_index.reinforcement | 93 |
| abstract_inverted_index.uncertainties | 37 |
| abstract_inverted_index.unprecedented | 33 |
| abstract_inverted_index.interconnected | 40 |
| abstract_inverted_index.uncertainties, | 44, 89 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 3 |
| citation_normalized_percentile |