TimeHC-RL: Temporal-aware Hierarchical Cognitive Reinforcement Learning for Enhancing LLMs' Social Intelligence Article Swipe
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2505.24500
Recently, Large Language Models (LLMs) have made significant progress in IQ-related domains that require careful thinking, such as mathematics and coding. However, enhancing LLMs' cognitive development in social domains, particularly from a post-training perspective, remains underexplored. Recognizing that the social world follows a distinct timeline and requires a richer blend of cognitive modes (from intuitive reactions (System 1) and surface-level thinking to deliberate thinking (System 2)) than mathematics, which primarily relies on System 2 cognition (careful, step-by-step reasoning), we introduce Temporal-aware Hierarchical Cognitive Reinforcement Learning (TimeHC-RL) for enhancing LLMs' social intelligence. In our experiments, we systematically explore improving LLMs' social intelligence and validate the effectiveness of the TimeHC-RL method, through five other post-training paradigms and two test-time intervention paradigms on eight datasets with diverse data patterns. Experimental results reveal the superiority of our proposed TimeHC-RL method compared to the widely adopted System 2 RL method. It gives the 7B backbone model wings, enabling it to rival the performance of advanced models like DeepSeek-R1 and OpenAI-O3. Additionally, the systematic exploration from post-training and test-time interventions perspectives to improve LLMs' social intelligence has uncovered several valuable insights.
Related Topics
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2505.24500
- https://arxiv.org/pdf/2505.24500
- OA Status
- green
- OpenAlex ID
- https://openalex.org/W4414857714
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4414857714Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2505.24500Digital Object Identifier
- Title
-
TimeHC-RL: Temporal-aware Hierarchical Cognitive Reinforcement Learning for Enhancing LLMs' Social IntelligenceWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2025Year of publication
- Publication date
-
2025-05-30Full publication date if available
- Authors
-
Guiyang Hou, Xing Gao, Yuchuan Wu, Xiang Huang, Wenqi Zhang, Zhe Zheng, Yongliang Shen, Jialu Du, Fei Huang, Yongbin Li, Weiming LüList of authors in order
- Landing page
-
https://arxiv.org/abs/2505.24500Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2505.24500Direct 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/2505.24500Direct OA link when available
- Cited by
-
0Total citation count in OpenAlex
Full payload
| id | https://openalex.org/W4414857714 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2505.24500 |
| ids.doi | https://doi.org/10.48550/arxiv.2505.24500 |
| ids.openalex | https://openalex.org/W4414857714 |
| fwci | |
| type | preprint |
| title | TimeHC-RL: Temporal-aware Hierarchical Cognitive Reinforcement Learning for Enhancing LLMs' Social Intelligence |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T11902 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9228000044822693 |
| 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 | Intelligent Tutoring Systems and Adaptive Learning |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2505.24500 |
| 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/2505.24500 |
| 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/2505.24500 |
| locations[1].id | doi:10.48550/arxiv.2505.24500 |
| 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.2505.24500 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5101963058 |
| authorships[0].author.orcid | https://orcid.org/0009-0009-9163-0633 |
| authorships[0].author.display_name | Guiyang Hou |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Hou, Guiyang |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5070256668 |
| authorships[1].author.orcid | https://orcid.org/0000-0002-4118-3152 |
| authorships[1].author.display_name | Xing Gao |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Gao, Xing |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5036775649 |
| authorships[2].author.orcid | https://orcid.org/0000-0001-8487-7587 |
| authorships[2].author.display_name | Yuchuan Wu |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Wu, Yuchuan |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5015041976 |
| authorships[3].author.orcid | https://orcid.org/0000-0003-4811-4544 |
| authorships[3].author.display_name | Xiang Huang |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Huang, Xiang |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5100457807 |
| authorships[4].author.orcid | https://orcid.org/0000-0002-8312-0184 |
| authorships[4].author.display_name | Wenqi Zhang |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Zhang, Wenqi |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5101676901 |
| authorships[5].author.orcid | https://orcid.org/0000-0002-2061-0645 |
| authorships[5].author.display_name | Zhe Zheng |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Zheng, Zhe |
| authorships[5].is_corresponding | False |
| authorships[6].author.id | https://openalex.org/A5004615610 |
| authorships[6].author.orcid | https://orcid.org/0000-0003-0975-3554 |
| authorships[6].author.display_name | Yongliang Shen |
| authorships[6].author_position | middle |
| authorships[6].raw_author_name | Shen, Yongliang |
| authorships[6].is_corresponding | False |
| authorships[7].author.id | https://openalex.org/A5068206682 |
| authorships[7].author.orcid | https://orcid.org/0000-0002-8308-040X |
| authorships[7].author.display_name | Jialu Du |
| authorships[7].author_position | middle |
| authorships[7].raw_author_name | Du, Jialu |
| authorships[7].is_corresponding | False |
| authorships[8].author.id | https://openalex.org/A5101488344 |
| authorships[8].author.orcid | https://orcid.org/0000-0002-3709-5053 |
| authorships[8].author.display_name | Fei Huang |
| authorships[8].author_position | middle |
| authorships[8].raw_author_name | Huang, Fei |
| authorships[8].is_corresponding | False |
| authorships[9].author.id | https://openalex.org/A5100644428 |
| authorships[9].author.orcid | https://orcid.org/0009-0008-4504-2163 |
| authorships[9].author.display_name | Yongbin Li |
| authorships[9].author_position | middle |
| authorships[9].raw_author_name | Li, Yongbin |
| authorships[9].is_corresponding | False |
| authorships[10].author.id | https://openalex.org/A5026310569 |
| authorships[10].author.orcid | https://orcid.org/0000-0003-1561-2467 |
| authorships[10].author.display_name | Weiming Lü |
| authorships[10].author_position | last |
| authorships[10].raw_author_name | Lu, Weiming |
| authorships[10].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/2505.24500 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | TimeHC-RL: Temporal-aware Hierarchical Cognitive Reinforcement Learning for Enhancing LLMs' Social Intelligence |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T11902 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9228000044822693 |
| 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 | Intelligent Tutoring Systems and Adaptive Learning |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2505.24500 |
| 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/2505.24500 |
| 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/2505.24500 |
| primary_location.id | pmh:oai:arXiv.org:2505.24500 |
| 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/2505.24500 |
| 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/2505.24500 |
| publication_date | 2025-05-30 |
| publication_year | 2025 |
| referenced_works_count | 0 |
| abstract_inverted_index.2 | 73, 142 |
| abstract_inverted_index.a | 31, 42, 47 |
| abstract_inverted_index.1) | 57 |
| abstract_inverted_index.7B | 148 |
| abstract_inverted_index.In | 91 |
| abstract_inverted_index.It | 145 |
| abstract_inverted_index.RL | 143 |
| abstract_inverted_index.as | 17 |
| abstract_inverted_index.in | 9, 26 |
| abstract_inverted_index.it | 153 |
| abstract_inverted_index.of | 50, 105, 131, 158 |
| abstract_inverted_index.on | 71, 119 |
| abstract_inverted_index.to | 61, 137, 154, 175 |
| abstract_inverted_index.we | 78, 94 |
| abstract_inverted_index.2)) | 65 |
| abstract_inverted_index.and | 19, 45, 58, 101, 114, 163, 171 |
| abstract_inverted_index.for | 86 |
| abstract_inverted_index.has | 180 |
| abstract_inverted_index.our | 92, 132 |
| abstract_inverted_index.the | 38, 103, 106, 129, 138, 147, 156, 166 |
| abstract_inverted_index.two | 115 |
| abstract_inverted_index.data | 124 |
| abstract_inverted_index.five | 110 |
| abstract_inverted_index.from | 30, 169 |
| abstract_inverted_index.have | 5 |
| abstract_inverted_index.like | 161 |
| abstract_inverted_index.made | 6 |
| abstract_inverted_index.such | 16 |
| abstract_inverted_index.than | 66 |
| abstract_inverted_index.that | 12, 37 |
| abstract_inverted_index.with | 122 |
| abstract_inverted_index.(from | 53 |
| abstract_inverted_index.LLMs' | 23, 88, 98, 177 |
| abstract_inverted_index.Large | 1 |
| abstract_inverted_index.blend | 49 |
| abstract_inverted_index.eight | 120 |
| abstract_inverted_index.gives | 146 |
| abstract_inverted_index.model | 150 |
| abstract_inverted_index.modes | 52 |
| abstract_inverted_index.other | 111 |
| abstract_inverted_index.rival | 155 |
| abstract_inverted_index.which | 68 |
| abstract_inverted_index.world | 40 |
| abstract_inverted_index.(LLMs) | 4 |
| abstract_inverted_index.Models | 3 |
| abstract_inverted_index.System | 72, 141 |
| abstract_inverted_index.method | 135 |
| abstract_inverted_index.models | 160 |
| abstract_inverted_index.relies | 70 |
| abstract_inverted_index.reveal | 128 |
| abstract_inverted_index.richer | 48 |
| abstract_inverted_index.social | 27, 39, 89, 99, 178 |
| abstract_inverted_index.widely | 139 |
| abstract_inverted_index.wings, | 151 |
| abstract_inverted_index.(System | 56, 64 |
| abstract_inverted_index.adopted | 140 |
| abstract_inverted_index.careful | 14 |
| abstract_inverted_index.coding. | 20 |
| abstract_inverted_index.diverse | 123 |
| abstract_inverted_index.domains | 11 |
| abstract_inverted_index.explore | 96 |
| abstract_inverted_index.follows | 41 |
| abstract_inverted_index.improve | 176 |
| abstract_inverted_index.method, | 108 |
| abstract_inverted_index.method. | 144 |
| abstract_inverted_index.remains | 34 |
| abstract_inverted_index.require | 13 |
| abstract_inverted_index.results | 127 |
| abstract_inverted_index.several | 182 |
| abstract_inverted_index.through | 109 |
| abstract_inverted_index.However, | 21 |
| abstract_inverted_index.Language | 2 |
| abstract_inverted_index.Learning | 84 |
| abstract_inverted_index.advanced | 159 |
| abstract_inverted_index.backbone | 149 |
| abstract_inverted_index.compared | 136 |
| abstract_inverted_index.datasets | 121 |
| abstract_inverted_index.distinct | 43 |
| abstract_inverted_index.domains, | 28 |
| abstract_inverted_index.enabling | 152 |
| abstract_inverted_index.progress | 8 |
| abstract_inverted_index.proposed | 133 |
| abstract_inverted_index.requires | 46 |
| abstract_inverted_index.thinking | 60, 63 |
| abstract_inverted_index.timeline | 44 |
| abstract_inverted_index.validate | 102 |
| abstract_inverted_index.valuable | 183 |
| abstract_inverted_index.(careful, | 75 |
| abstract_inverted_index.Cognitive | 82 |
| abstract_inverted_index.Recently, | 0 |
| abstract_inverted_index.TimeHC-RL | 107, 134 |
| abstract_inverted_index.cognition | 74 |
| abstract_inverted_index.cognitive | 24, 51 |
| abstract_inverted_index.enhancing | 22, 87 |
| abstract_inverted_index.improving | 97 |
| abstract_inverted_index.insights. | 184 |
| abstract_inverted_index.introduce | 79 |
| abstract_inverted_index.intuitive | 54 |
| abstract_inverted_index.paradigms | 113, 118 |
| abstract_inverted_index.patterns. | 125 |
| abstract_inverted_index.primarily | 69 |
| abstract_inverted_index.reactions | 55 |
| abstract_inverted_index.test-time | 116, 172 |
| abstract_inverted_index.thinking, | 15 |
| abstract_inverted_index.uncovered | 181 |
| abstract_inverted_index.IQ-related | 10 |
| abstract_inverted_index.OpenAI-O3. | 164 |
| abstract_inverted_index.deliberate | 62 |
| abstract_inverted_index.systematic | 167 |
| abstract_inverted_index.(TimeHC-RL) | 85 |
| abstract_inverted_index.DeepSeek-R1 | 162 |
| abstract_inverted_index.Recognizing | 36 |
| abstract_inverted_index.development | 25 |
| abstract_inverted_index.exploration | 168 |
| abstract_inverted_index.mathematics | 18 |
| abstract_inverted_index.performance | 157 |
| abstract_inverted_index.reasoning), | 77 |
| abstract_inverted_index.significant | 7 |
| abstract_inverted_index.superiority | 130 |
| abstract_inverted_index.Experimental | 126 |
| abstract_inverted_index.Hierarchical | 81 |
| abstract_inverted_index.experiments, | 93 |
| abstract_inverted_index.intelligence | 100, 179 |
| abstract_inverted_index.intervention | 117 |
| abstract_inverted_index.mathematics, | 67 |
| abstract_inverted_index.particularly | 29 |
| abstract_inverted_index.perspective, | 33 |
| abstract_inverted_index.perspectives | 174 |
| abstract_inverted_index.step-by-step | 76 |
| abstract_inverted_index.Additionally, | 165 |
| abstract_inverted_index.Reinforcement | 83 |
| abstract_inverted_index.effectiveness | 104 |
| abstract_inverted_index.intelligence. | 90 |
| abstract_inverted_index.interventions | 173 |
| abstract_inverted_index.post-training | 32, 112, 170 |
| abstract_inverted_index.surface-level | 59 |
| abstract_inverted_index.Temporal-aware | 80 |
| abstract_inverted_index.systematically | 95 |
| abstract_inverted_index.underexplored. | 35 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 11 |
| citation_normalized_percentile |