Towards Formal Verification of Neuro-Symbolic Multi-Agent Systems

Abstract

This paper outlines some of the key methods we developed towards the formal verification of multi- agent systems, covering both symbolic and connectionist systems. It discusses logic-based methods for the verification of unbounded multi-agent systems (i.e., systems composed of an arbitrary number of homogeneous agents, e.g., robot swarms), optimisation approaches for establishing the robustness of neural network models, and methods for analysing properties of neuro-symbolic multi-agent systems.

Cite

Text

Kouvaros. "Towards Formal Verification of Neuro-Symbolic Multi-Agent Systems." International Joint Conference on Artificial Intelligence, 2023. doi:10.24963/IJCAI.2023/800

Markdown

[Kouvaros. "Towards Formal Verification of Neuro-Symbolic Multi-Agent Systems." International Joint Conference on Artificial Intelligence, 2023.](https://mlanthology.org/ijcai/2023/kouvaros2023ijcai-formal/) doi:10.24963/IJCAI.2023/800

BibTeX

@inproceedings{kouvaros2023ijcai-formal,
  title     = {{Towards Formal Verification of Neuro-Symbolic Multi-Agent Systems}},
  author    = {Kouvaros, Panagiotis},
  booktitle = {International Joint Conference on Artificial Intelligence},
  year      = {2023},
  pages     = {7014-7019},
  doi       = {10.24963/IJCAI.2023/800},
  url       = {https://mlanthology.org/ijcai/2023/kouvaros2023ijcai-formal/}
}