2022
DOI: 10.4204/eptcs.362.5
|View full text |Cite
|
Sign up to set email alerts
|

RV4JaCa – Runtime Verification for Multi-Agent Systems

Abstract: This paper presents a Runtime Verification (RV) approach for Multi-Agent Systems (MAS) using the JaCaMo framework. Our objective is to bring a layer of security to the MAS. This layer is capable of controlling events during the execution of the system without needing a specific implementation in the behaviour of each agent to recognise the events. MAS have been used in the context of hybrid intelligence. This use requires communication between software agents and human beings. In some cases, communication take… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1

Citation Types

0
2
0
1

Year Published

2023
2023
2024
2024

Publication Types

Select...
3
2
2

Relationship

1
6

Authors

Journals

citations
Cited by 9 publications
(3 citation statements)
references
References 32 publications
0
2
0
1
Order By: Relevance
“…The JaCaMo framework is also used in developing mobile apps as personal assistant agents [ 16 ]. RV4JaCa is a runtime verification approach for MAS using the JaCaMo framework that improves the security level controlling events during the execution of the system without needing a specific implementation in the behavior of each agent to recognize the events [ 17 ]. Using the artifact frameworks, developers can create more flexible and dynamic MAS to adapt to the environment-changing conditions at runtime.…”
Section: State Of the Artmentioning
confidence: 99%
“…The JaCaMo framework is also used in developing mobile apps as personal assistant agents [ 16 ]. RV4JaCa is a runtime verification approach for MAS using the JaCaMo framework that improves the security level controlling events during the execution of the system without needing a specific implementation in the behavior of each agent to recognize the events [ 17 ]. Using the artifact frameworks, developers can create more flexible and dynamic MAS to adapt to the environment-changing conditions at runtime.…”
Section: State Of the Artmentioning
confidence: 99%
“…Dentre as contribuic ¸ões desta tese destaca-se: (i) identificac ¸ão das formas como a comunidade científica tem utilizado técnicas de argumentac ¸ão para alcanc ¸ar inteligência artificial explicável em sistemas de diálogo incluídas em levantamento bibliográfico publicado em [Engelmann et al 2022a]; (ii) desenvolvimento da estrutura MAIDS [Engelmann et al 2023] para apoiar o desenvolvimento de sistemas de diálogo explicáveis baseados em agentes BDI para auxiliar humanos na tomada de decisões; (iii) introduc ¸ão e formalizac ¸ão de uma base de crenc ¸as multipartes para uma linguagem de programac ¸ão de agentes BDI e uma abordagem estruturada para diálogos onde os agentes discutem sobre as informac ¸ões do componente principal da base de crenc ¸as, mas podem passar para sub-diálogos para discutir questões específicas relacionadas ao componente ontológico ou o componente ToM da base de crenc ¸a multipartes; (iv) criac ¸ão do framework Dial4JaCa [Engelmann et al 2021b, Engelmann et al 2021a] para permitir que agentes inteligentes se comuniquem com humanos através da interac ¸ão em linguagem natural; (v) criac ¸ão do framework Onto4JaCa para dar aos agentes inteligentes a capacidade de usar e gerenciar as informac ¸ões contidas nas ontologias durante seus processos de raciocínio [Ferreira et al 2022]; (vi) criac ¸ão do framework RV4JaCa [Engelmann et al 2022b] que suporta o uso de verificac ¸ão em tempo de execuc ¸ão em sistemas multi-agentes desenvolvidos na plataforma Ja-CaMo [Boissier et al 2020]; (vii) implementac ¸ão de um sistema explicável baseado na estrutura do MAIDS para auxiliar na tomada de decisões sobre alocac ¸ão de leitos hospitalares; (viii) avaliac ¸ão do sistema criado a partir de dados hospitalares reais e com o auxílio de profissionais responsáveis pela alocac ¸ão de leitos em um hospital.…”
Section: Principais Contribuic ¸õEsunclassified
“…Finally, the addition of such new beliefs inside the JaCaMo agent's belief base will cause a reaction driven by the most suitable plan among those in the agent's plan base. The use of Jason and JaCaMo paves the way to supporting those advanced features mentioned in Section 1, namely sophisticated reasoning capabilities and goal-driven planning [17][18][19], exploitation of formal and semiformal methods to implement monitoring and safety checks [20][21][22][23], explainability, also in connection with Dialogflow thanks to Dial4JaCa [24,25].…”
mentioning
confidence: 99%