Large Language Model-based Human-Agent Collaboration for Complex Task Solving Article Swipe
Xueyang Feng
,
Zhiyuan Chen
,
Yujia Qin
,
Yankai Lin
,
Xu Chen
,
Zhiyuan Liu
,
Ji-Rong Wen
·
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2402.12914
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2402.12914
In recent developments within the research community, the integration of Large Language Models (LLMs) in creating fully autonomous agents has garnered significant interest. Despite this, LLM-based agents frequently demonstrate notable shortcomings in adjusting to dynamic environments and fully grasping human needs. In this work, we introduce the problem of LLM-based human-agent collaboration for complex task-solving, exploring their synergistic potential. In addition, we propose a Reinforcement Learning-based Human-Agent Collaboration method, ReHAC. This approach includes a policy model designed to determine the most opportune stages for human intervention within the task-solving process. We construct a human-agent collaboration dataset to train this policy model in an offline reinforcement learning environment. Our validation tests confirm the model's effectiveness. The results demonstrate that the synergistic efforts of humans and LLM-based agents significantly improve performance in complex tasks, primarily through well-planned, limited human intervention. Datasets and code are available at: https://github.com/XueyangFeng/ReHAC.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2402.12914
- https://arxiv.org/pdf/2402.12914
- OA Status
- green
- Cited By
- 2
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4392012743
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4392012743Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2402.12914Digital Object Identifier
- Title
-
Large Language Model-based Human-Agent Collaboration for Complex Task SolvingWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2024Year of publication
- Publication date
-
2024-02-20Full publication date if available
- Authors
-
Xueyang Feng, Zhiyuan Chen, Yujia Qin, Yankai Lin, Xu Chen, Zhiyuan Liu, Ji-Rong WenList of authors in order
- Landing page
-
https://arxiv.org/abs/2402.12914Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2402.12914Direct 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/2402.12914Direct OA link when available
- Concepts
-
Task (project management), Computer science, Human–computer interaction, Language model, Knowledge management, Natural language processing, Cognitive science, Psychology, Systems engineering, EngineeringTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
2Total citation count in OpenAlex
- Citations by year (recent)
-
2025: 1, 2024: 1Per-year citation counts (last 5 years)
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4392012743 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2402.12914 |
| ids.doi | https://doi.org/10.48550/arxiv.2402.12914 |
| ids.openalex | https://openalex.org/W4392012743 |
| fwci | |
| type | preprint |
| title | Large Language Model-based Human-Agent Collaboration for Complex Task Solving |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T10456 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.6773999929428101 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1702 |
| topics[0].subfield.display_name | Artificial Intelligence |
| topics[0].display_name | Multi-Agent Systems and Negotiation |
| topics[1].id | https://openalex.org/T13382 |
| topics[1].field.id | https://openalex.org/fields/22 |
| topics[1].field.display_name | Engineering |
| topics[1].score | 0.6044999957084656 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/2207 |
| topics[1].subfield.display_name | Control and Systems Engineering |
| topics[1].display_name | Robotics and Automated Systems |
| topics[2].id | https://openalex.org/T10215 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.5705000162124634 |
| 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 | Semantic Web and Ontologies |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C2780451532 |
| concepts[0].level | 2 |
| concepts[0].score | 0.6961185336112976 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q759676 |
| concepts[0].display_name | Task (project management) |
| concepts[1].id | https://openalex.org/C41008148 |
| concepts[1].level | 0 |
| concepts[1].score | 0.6789149641990662 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[1].display_name | Computer science |
| concepts[2].id | https://openalex.org/C107457646 |
| concepts[2].level | 1 |
| concepts[2].score | 0.42795974016189575 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q207434 |
| concepts[2].display_name | Human–computer interaction |
| concepts[3].id | https://openalex.org/C137293760 |
| concepts[3].level | 2 |
| concepts[3].score | 0.42285069823265076 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q3621696 |
| concepts[3].display_name | Language model |
| concepts[4].id | https://openalex.org/C56739046 |
| concepts[4].level | 1 |
| concepts[4].score | 0.3658800721168518 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q192060 |
| concepts[4].display_name | Knowledge management |
| concepts[5].id | https://openalex.org/C204321447 |
| concepts[5].level | 1 |
| concepts[5].score | 0.34334754943847656 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q30642 |
| concepts[5].display_name | Natural language processing |
| concepts[6].id | https://openalex.org/C188147891 |
| concepts[6].level | 1 |
| concepts[6].score | 0.32012391090393066 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q147638 |
| concepts[6].display_name | Cognitive science |
| concepts[7].id | https://openalex.org/C15744967 |
| concepts[7].level | 0 |
| concepts[7].score | 0.20757830142974854 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q9418 |
| concepts[7].display_name | Psychology |
| concepts[8].id | https://openalex.org/C201995342 |
| concepts[8].level | 1 |
| concepts[8].score | 0.14689567685127258 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q682496 |
| concepts[8].display_name | Systems engineering |
| concepts[9].id | https://openalex.org/C127413603 |
| concepts[9].level | 0 |
| concepts[9].score | 0.1267898678779602 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q11023 |
| concepts[9].display_name | Engineering |
| keywords[0].id | https://openalex.org/keywords/task |
| keywords[0].score | 0.6961185336112976 |
| keywords[0].display_name | Task (project management) |
| keywords[1].id | https://openalex.org/keywords/computer-science |
| keywords[1].score | 0.6789149641990662 |
| keywords[1].display_name | Computer science |
| keywords[2].id | https://openalex.org/keywords/human–computer-interaction |
| keywords[2].score | 0.42795974016189575 |
| keywords[2].display_name | Human–computer interaction |
| keywords[3].id | https://openalex.org/keywords/language-model |
| keywords[3].score | 0.42285069823265076 |
| keywords[3].display_name | Language model |
| keywords[4].id | https://openalex.org/keywords/knowledge-management |
| keywords[4].score | 0.3658800721168518 |
| keywords[4].display_name | Knowledge management |
| keywords[5].id | https://openalex.org/keywords/natural-language-processing |
| keywords[5].score | 0.34334754943847656 |
| keywords[5].display_name | Natural language processing |
| keywords[6].id | https://openalex.org/keywords/cognitive-science |
| keywords[6].score | 0.32012391090393066 |
| keywords[6].display_name | Cognitive science |
| keywords[7].id | https://openalex.org/keywords/psychology |
| keywords[7].score | 0.20757830142974854 |
| keywords[7].display_name | Psychology |
| keywords[8].id | https://openalex.org/keywords/systems-engineering |
| keywords[8].score | 0.14689567685127258 |
| keywords[8].display_name | Systems engineering |
| keywords[9].id | https://openalex.org/keywords/engineering |
| keywords[9].score | 0.1267898678779602 |
| keywords[9].display_name | Engineering |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2402.12914 |
| 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/2402.12914 |
| 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/2402.12914 |
| locations[1].id | doi:10.48550/arxiv.2402.12914 |
| 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.2402.12914 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5101929118 |
| authorships[0].author.orcid | https://orcid.org/0000-0003-4426-5732 |
| authorships[0].author.display_name | Xueyang Feng |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Feng, Xueyang |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5100438512 |
| authorships[1].author.orcid | https://orcid.org/0000-0002-4915-1593 |
| authorships[1].author.display_name | Zhiyuan Chen |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Chen, Zhi-Yuan |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5102894085 |
| authorships[2].author.orcid | https://orcid.org/0000-0003-3608-5061 |
| authorships[2].author.display_name | Yujia Qin |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Qin, Yujia |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5043098453 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-0151-6178 |
| authorships[3].author.display_name | Yankai Lin |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Lin, Yankai |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5100385692 |
| authorships[4].author.orcid | https://orcid.org/0000-0001-9943-6020 |
| authorships[4].author.display_name | Xu Chen |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Chen, Xu |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5100320723 |
| authorships[5].author.orcid | https://orcid.org/0000-0002-7709-2543 |
| authorships[5].author.display_name | Zhiyuan Liu |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Liu, Zhiyuan |
| authorships[5].is_corresponding | False |
| authorships[6].author.id | https://openalex.org/A5025631695 |
| authorships[6].author.orcid | https://orcid.org/0000-0002-9777-9676 |
| authorships[6].author.display_name | Ji-Rong Wen |
| authorships[6].author_position | last |
| authorships[6].raw_author_name | Wen, Ji-Rong |
| authorships[6].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/2402.12914 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2024-02-22T00:00:00 |
| display_name | Large Language Model-based Human-Agent Collaboration for Complex Task Solving |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T10456 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.6773999929428101 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1702 |
| primary_topic.subfield.display_name | Artificial Intelligence |
| primary_topic.display_name | Multi-Agent Systems and Negotiation |
| related_works | https://openalex.org/W2169518243, https://openalex.org/W2548721895, https://openalex.org/W2373456246, https://openalex.org/W2013265273, https://openalex.org/W4238809000, https://openalex.org/W2786646446, https://openalex.org/W2252095989, https://openalex.org/W2331739042, https://openalex.org/W3196817267, https://openalex.org/W3098003361 |
| cited_by_count | 2 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 1 |
| counts_by_year[1].year | 2024 |
| counts_by_year[1].cited_by_count | 1 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2402.12914 |
| 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/2402.12914 |
| 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/2402.12914 |
| primary_location.id | pmh:oai:arXiv.org:2402.12914 |
| 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/2402.12914 |
| 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/2402.12914 |
| publication_date | 2024-02-20 |
| publication_year | 2024 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 63, 73, 92 |
| abstract_inverted_index.In | 0, 41, 59 |
| abstract_inverted_index.We | 90 |
| abstract_inverted_index.an | 102 |
| abstract_inverted_index.in | 14, 31, 101, 129 |
| abstract_inverted_index.of | 9, 48, 121 |
| abstract_inverted_index.to | 33, 77, 96 |
| abstract_inverted_index.we | 44, 61 |
| abstract_inverted_index.Our | 107 |
| abstract_inverted_index.The | 114 |
| abstract_inverted_index.and | 36, 123, 139 |
| abstract_inverted_index.are | 141 |
| abstract_inverted_index.at: | 143 |
| abstract_inverted_index.for | 52, 83 |
| abstract_inverted_index.has | 19 |
| abstract_inverted_index.the | 4, 7, 46, 79, 87, 111, 118 |
| abstract_inverted_index.This | 70 |
| abstract_inverted_index.code | 140 |
| abstract_inverted_index.most | 80 |
| abstract_inverted_index.that | 117 |
| abstract_inverted_index.this | 42, 98 |
| abstract_inverted_index.Large | 10 |
| abstract_inverted_index.fully | 16, 37 |
| abstract_inverted_index.human | 39, 84, 136 |
| abstract_inverted_index.model | 75, 100 |
| abstract_inverted_index.tests | 109 |
| abstract_inverted_index.their | 56 |
| abstract_inverted_index.this, | 24 |
| abstract_inverted_index.train | 97 |
| abstract_inverted_index.work, | 43 |
| abstract_inverted_index.(LLMs) | 13 |
| abstract_inverted_index.Models | 12 |
| abstract_inverted_index.ReHAC. | 69 |
| abstract_inverted_index.agents | 18, 26, 125 |
| abstract_inverted_index.humans | 122 |
| abstract_inverted_index.needs. | 40 |
| abstract_inverted_index.policy | 74, 99 |
| abstract_inverted_index.recent | 1 |
| abstract_inverted_index.stages | 82 |
| abstract_inverted_index.tasks, | 131 |
| abstract_inverted_index.within | 3, 86 |
| abstract_inverted_index.Despite | 23 |
| abstract_inverted_index.complex | 53, 130 |
| abstract_inverted_index.confirm | 110 |
| abstract_inverted_index.dataset | 95 |
| abstract_inverted_index.dynamic | 34 |
| abstract_inverted_index.efforts | 120 |
| abstract_inverted_index.improve | 127 |
| abstract_inverted_index.limited | 135 |
| abstract_inverted_index.method, | 68 |
| abstract_inverted_index.model's | 112 |
| abstract_inverted_index.notable | 29 |
| abstract_inverted_index.offline | 103 |
| abstract_inverted_index.problem | 47 |
| abstract_inverted_index.propose | 62 |
| abstract_inverted_index.results | 115 |
| abstract_inverted_index.through | 133 |
| abstract_inverted_index.Datasets | 138 |
| abstract_inverted_index.Language | 11 |
| abstract_inverted_index.approach | 71 |
| abstract_inverted_index.creating | 15 |
| abstract_inverted_index.designed | 76 |
| abstract_inverted_index.garnered | 20 |
| abstract_inverted_index.grasping | 38 |
| abstract_inverted_index.includes | 72 |
| abstract_inverted_index.learning | 105 |
| abstract_inverted_index.process. | 89 |
| abstract_inverted_index.research | 5 |
| abstract_inverted_index.LLM-based | 25, 49, 124 |
| abstract_inverted_index.addition, | 60 |
| abstract_inverted_index.adjusting | 32 |
| abstract_inverted_index.available | 142 |
| abstract_inverted_index.construct | 91 |
| abstract_inverted_index.determine | 78 |
| abstract_inverted_index.exploring | 55 |
| abstract_inverted_index.interest. | 22 |
| abstract_inverted_index.introduce | 45 |
| abstract_inverted_index.opportune | 81 |
| abstract_inverted_index.primarily | 132 |
| abstract_inverted_index.autonomous | 17 |
| abstract_inverted_index.community, | 6 |
| abstract_inverted_index.frequently | 27 |
| abstract_inverted_index.potential. | 58 |
| abstract_inverted_index.validation | 108 |
| abstract_inverted_index.Human-Agent | 66 |
| abstract_inverted_index.demonstrate | 28, 116 |
| abstract_inverted_index.human-agent | 50, 93 |
| abstract_inverted_index.integration | 8 |
| abstract_inverted_index.performance | 128 |
| abstract_inverted_index.significant | 21 |
| abstract_inverted_index.synergistic | 57, 119 |
| abstract_inverted_index.developments | 2 |
| abstract_inverted_index.environment. | 106 |
| abstract_inverted_index.environments | 35 |
| abstract_inverted_index.intervention | 85 |
| abstract_inverted_index.shortcomings | 30 |
| abstract_inverted_index.task-solving | 88 |
| abstract_inverted_index.Collaboration | 67 |
| abstract_inverted_index.Reinforcement | 64 |
| abstract_inverted_index.collaboration | 51, 94 |
| abstract_inverted_index.intervention. | 137 |
| abstract_inverted_index.reinforcement | 104 |
| abstract_inverted_index.significantly | 126 |
| abstract_inverted_index.task-solving, | 54 |
| abstract_inverted_index.well-planned, | 134 |
| abstract_inverted_index.Learning-based | 65 |
| abstract_inverted_index.effectiveness. | 113 |
| abstract_inverted_index.https://github.com/XueyangFeng/ReHAC. | 144 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 7 |
| citation_normalized_percentile |