Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2601.10025 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915731545784320 |
|---|---|
| author | Wang, Jinpeng Jia, Xinyu Heng, Wei Wei Li, Yuquan Shi, Binbin Chen, Qianlei Chen, Guannan Zhang, Junxia Yin, Yuyu |
| author_facet | Wang, Jinpeng Jia, Xinyu Heng, Wei Wei Li, Yuquan Shi, Binbin Chen, Qianlei Chen, Guannan Zhang, Junxia Yin, Yuyu |
| contents | Large Language Models (LLMs) are increasingly shaping human-computer interaction (HCI), from personalized assistants to social simulations. Beyond language competence, researchers are exploring whether LLMs can exhibit human-like characteristics that influence engagement, decision-making, and perceived realism. Personality, in particular, is critical, yet existing approaches often struggle to achieve both nuanced and adaptable expression. We present a framework that models LLM personality via Jungian psychological types, integrating three mechanisms: a dominant-auxiliary coordination mechanism for coherent core expression, a reinforcement-compensation mechanism for temporary adaptation to context, and a reflection mechanism that drives long-term personality evolution. This design allows the agent to maintain nuanced traits while dynamically adjusting to interaction demands and gradually updating its underlying structure. Personality alignment is evaluated using Myers-Briggs Type Indicator questionnaires and tested under diverse challenge scenarios as a preliminary structured assessment. Findings suggest that evolving, personality-aware LLMs can support coherent, context-sensitive interactions, enabling naturalistic agent design in HCI. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_10025 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Structured Personality Control and Adaptation for LLM Agents Wang, Jinpeng Jia, Xinyu Heng, Wei Wei Li, Yuquan Shi, Binbin Chen, Qianlei Chen, Guannan Zhang, Junxia Yin, Yuyu Artificial Intelligence Large Language Models (LLMs) are increasingly shaping human-computer interaction (HCI), from personalized assistants to social simulations. Beyond language competence, researchers are exploring whether LLMs can exhibit human-like characteristics that influence engagement, decision-making, and perceived realism. Personality, in particular, is critical, yet existing approaches often struggle to achieve both nuanced and adaptable expression. We present a framework that models LLM personality via Jungian psychological types, integrating three mechanisms: a dominant-auxiliary coordination mechanism for coherent core expression, a reinforcement-compensation mechanism for temporary adaptation to context, and a reflection mechanism that drives long-term personality evolution. This design allows the agent to maintain nuanced traits while dynamically adjusting to interaction demands and gradually updating its underlying structure. Personality alignment is evaluated using Myers-Briggs Type Indicator questionnaires and tested under diverse challenge scenarios as a preliminary structured assessment. Findings suggest that evolving, personality-aware LLMs can support coherent, context-sensitive interactions, enabling naturalistic agent design in HCI. |
| title | Structured Personality Control and Adaptation for LLM Agents |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2601.10025 |