Requirement Patterns for Engineering Multiagent Interaction Protocols
Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence. Main Track. Pages 38-46.
https://doi.org/10.24963/ijcai.2025/5
Keywords
- Agent-based and Multi-agent Systems: MAS: Agent communication
- Agent-based and Multi-agent Systems: MAS: Engineering methods, platforms, languages and tools
Abstract
An interaction protocol specifies how the member agents of a decentralized multiagent system may communicate to satisfy their respective stakeholders' requirements. We focus on information protocols, which are fully declarative specifications of interaction and support asynchronous communication. We offer Mambo, an approach for protocol design. Mambo identifies common patterns of requirements, provides a notation to express them, and a verification procedure. Mambo incorporates heuristics to generate small internal representations for efficiency. Experimental results demonstrate Mambo's effectiveness on practical protocols.
@inproceedings{ijcai2025p5,
title = {Requirement Patterns for Engineering Multiagent Interaction Protocols},
author = {Chopra, Amit K. and Christie V., Samuel H. and Singh, Munindar P.},
booktitle = {Proceedings of the Thirty-Fourth International Joint Conference on
Artificial Intelligence, {IJCAI-25}},
publisher = {International Joint Conferences on Artificial Intelligence Organization},
editor = {James Kwok},
pages = {38--46},
year = {2025},
month = {8},
note = {Main Track},
doi = {10.24963/ijcai.2025/5},
url = {https://doi.org/10.24963/ijcai.2025/5},
}
TY - CPAPER TI - Requirement Patterns for Engineering Multiagent Interaction Protocols AU - Chopra, Amit K. AU - Christie V., Samuel H. AU - Singh, Munindar P. T2 - Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25 PB - International Joint Conferences on Artificial Intelligence Organization PY - 2025 SP - 38 EP - 46 DO - 10.24963/ijcai.2025/5 UR - https://doi.org/10.24963/ijcai.2025/5 ER -Copied
Machine-readable versions of this paper, for tools and AI agents: