Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2509.22546 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915516701999104 |
|---|---|
| author | Zhou, Jinfeng Chen, Zheyu Wang, Shuai Dai, Quanyu Dong, Zhenhua Wang, Hongning Huang, Minlie |
| author_facet | Zhou, Jinfeng Chen, Zheyu Wang, Shuai Dai, Quanyu Dong, Zhenhua Wang, Hongning Huang, Minlie |
| contents | LLMs trained for logical reasoning excel at step-by-step deduction to reach verifiable answers. However, this paradigm is ill-suited for navigating social situations, which induce an interpretive process of analyzing ambiguous cues that rarely yield a definitive outcome. To bridge this gap, we introduce Cognitive Reasoning, a paradigm modeled on human social cognition. It formulates the interpretive process into a structured cognitive flow of interconnected cognitive units (e.g., observation or attribution), which combine adaptively to enable effective social thinking and responses. We then propose CogFlow, a complete framework that instills this capability in LLMs. CogFlow first curates a dataset of cognitive flows by simulating the associative and progressive nature of human thought via tree-structured planning. After instilling the basic cognitive reasoning capability via supervised fine-tuning, CogFlow adopts reinforcement learning to enable the model to improve itself via trial and error, guided by a multi-objective reward that optimizes both cognitive flow and response quality. Extensive experiments show that CogFlow effectively enhances the social cognitive capabilities of LLMs, and even humans, leading to more effective social decision-making. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_22546 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Think Socially via Cognitive Reasoning Zhou, Jinfeng Chen, Zheyu Wang, Shuai Dai, Quanyu Dong, Zhenhua Wang, Hongning Huang, Minlie Computation and Language LLMs trained for logical reasoning excel at step-by-step deduction to reach verifiable answers. However, this paradigm is ill-suited for navigating social situations, which induce an interpretive process of analyzing ambiguous cues that rarely yield a definitive outcome. To bridge this gap, we introduce Cognitive Reasoning, a paradigm modeled on human social cognition. It formulates the interpretive process into a structured cognitive flow of interconnected cognitive units (e.g., observation or attribution), which combine adaptively to enable effective social thinking and responses. We then propose CogFlow, a complete framework that instills this capability in LLMs. CogFlow first curates a dataset of cognitive flows by simulating the associative and progressive nature of human thought via tree-structured planning. After instilling the basic cognitive reasoning capability via supervised fine-tuning, CogFlow adopts reinforcement learning to enable the model to improve itself via trial and error, guided by a multi-objective reward that optimizes both cognitive flow and response quality. Extensive experiments show that CogFlow effectively enhances the social cognitive capabilities of LLMs, and even humans, leading to more effective social decision-making. |
| title | Think Socially via Cognitive Reasoning |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2509.22546 |