TimeHC-RL: Temporal-aware Hierarchical Cognitive Reinforcement Learning for Enhancing LLMs' Social Intelligence

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hou, Guiyang, Gao, Xing, Wu, Yuchuan, Huang, Xiang, Zhang, Wenqi, Zheng, Zhe, Shen, Yongliang, Du, Jialu, Huang, Fei, Li, Yongbin, Lu, Weiming
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910975975751680
author Hou, Guiyang
Gao, Xing
Wu, Yuchuan
Huang, Xiang
Zhang, Wenqi
Zheng, Zhe
Shen, Yongliang
Du, Jialu
Huang, Fei
Li, Yongbin
Lu, Weiming
author_facet Hou, Guiyang
Gao, Xing
Wu, Yuchuan
Huang, Xiang
Zhang, Wenqi
Zheng, Zhe
Shen, Yongliang
Du, Jialu
Huang, Fei
Li, Yongbin
Lu, Weiming
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_24500
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle TimeHC-RL: Temporal-aware Hierarchical Cognitive Reinforcement Learning for Enhancing LLMs' Social Intelligence
Hou, Guiyang
Gao, Xing
Wu, Yuchuan
Huang, Xiang
Zhang, Wenqi
Zheng, Zhe
Shen, Yongliang
Du, Jialu
Huang, Fei
Li, Yongbin
Lu, Weiming
Computation and Language
Artificial Intelligence
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.
title TimeHC-RL: Temporal-aware Hierarchical Cognitive Reinforcement Learning for Enhancing LLMs' Social Intelligence
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2505.24500