Shall We Team Up: Exploring Spontaneous Cooperation of Competing LLM Agents
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916456423227392 |
|---|---|
| author | Wu, Zengqing Peng, Run Zheng, Shuyuan Liu, Qianying Han, Xu Kwon, Brian Inhyuk Onizuka, Makoto Tang, Shaojie Xiao, Chuan |
| author_facet | Wu, Zengqing Peng, Run Zheng, Shuyuan Liu, Qianying Han, Xu Kwon, Brian Inhyuk Onizuka, Makoto Tang, Shaojie Xiao, Chuan |
| contents | Large Language Models (LLMs) have increasingly been utilized in social simulations, where they are often guided by carefully crafted instructions to stably exhibit human-like behaviors during simulations. Nevertheless, we doubt the necessity of shaping agents' behaviors for accurate social simulations. Instead, this paper emphasizes the importance of spontaneous phenomena, wherein agents deeply engage in contexts and make adaptive decisions without explicit directions. We explored spontaneous cooperation across three competitive scenarios and successfully simulated the gradual emergence of cooperation, findings that align closely with human behavioral data. This approach not only aids the computational social science community in bridging the gap between simulations and real-world dynamics but also offers the AI community a novel method to assess LLMs' capability of deliberate reasoning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_12327 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Shall We Team Up: Exploring Spontaneous Cooperation of Competing LLM Agents Wu, Zengqing Peng, Run Zheng, Shuyuan Liu, Qianying Han, Xu Kwon, Brian Inhyuk Onizuka, Makoto Tang, Shaojie Xiao, Chuan Artificial Intelligence Computation and Language Computers and Society Multiagent Systems General Economics Economics Large Language Models (LLMs) have increasingly been utilized in social simulations, where they are often guided by carefully crafted instructions to stably exhibit human-like behaviors during simulations. Nevertheless, we doubt the necessity of shaping agents' behaviors for accurate social simulations. Instead, this paper emphasizes the importance of spontaneous phenomena, wherein agents deeply engage in contexts and make adaptive decisions without explicit directions. We explored spontaneous cooperation across three competitive scenarios and successfully simulated the gradual emergence of cooperation, findings that align closely with human behavioral data. This approach not only aids the computational social science community in bridging the gap between simulations and real-world dynamics but also offers the AI community a novel method to assess LLMs' capability of deliberate reasoning. |
| title | Shall We Team Up: Exploring Spontaneous Cooperation of Competing LLM Agents |
| topic | Artificial Intelligence Computation and Language Computers and Society Multiagent Systems General Economics Economics |
| url | https://arxiv.org/abs/2402.12327 |