AutoAgents: A Framework for Automatic Agent Generation
Abstract
In multi-agent systems, especially in cybersecurity, the dynamic interplay between attackers and defenders is crucial to the security and resilience of the system. Traditional methods often assume static game models and fail to account for the strategic adaptation of the environment to the actions of the players. This paper presents Coalition Obstruction Temporal Logic (COTL), a formal framework for analyzing defender coalitions in dynamic game scenarios. Within this framework, defenders, conceptualized as demons, can actively obstruct attackers by selectively disabling certain actions in response to perceived threats. We establish the formal semantics of COTL and propose a model checking algorithm to verify complex security properties in systems with evolving adversarial dynamics. The utility of the framework is demonstrated through its application to a coalition of defenders that collaboratively defend a system against coordinated attacks.
Cite
Text
Chen et al. "AutoAgents: A Framework for Automatic Agent Generation." International Joint Conference on Artificial Intelligence, 2024. doi:10.24963/ijcai.2024/3Markdown
[Chen et al. "AutoAgents: A Framework for Automatic Agent Generation." International Joint Conference on Artificial Intelligence, 2024.](https://mlanthology.org/ijcai/2024/chen2024ijcai-autoagents/) doi:10.24963/ijcai.2024/3BibTeX
@inproceedings{chen2024ijcai-autoagents,
title = {{AutoAgents: A Framework for Automatic Agent Generation}},
author = {Chen, Guangyao and Dong, Siwei and Shu, Yu and Zhang, Ge and Sesay, Jaward and Karlsson, Börje and Fu, Jie and Shi, Yemin},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2024},
pages = {22-30},
doi = {10.24963/ijcai.2024/3},
url = {https://mlanthology.org/ijcai/2024/chen2024ijcai-autoagents/}
}