Scholarlink

Multi-agent systems (MAS) are a highly promising technology in the development of sophisticated applications, by enabling the integration of various AI techniques in a distributed and decentralised manner. However, human interaction with or as part of MAS often occurs through very static protocols. The advancement of natural language processing (NLP) has enabled the development of conversational agents, commonly known as chatbots, which can communicate in natural language through text or voice, providing a user-friendly interface. In this paper, we propose the development of Rasa4JaCa, which is an interface between the Rasa framework for chatbot development, and JaCaMo, that is an open-source MAS development framework. We evaluated Rasa4JaCa using a case study implemented in other existing interfaces. As a result of this development, it becomes possible for users to interact in natural language with a MAS, contextualising the development of application into the field of Hybrid Intelligence, where human users and intelligent agents can work together to solve complex problems.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Rasa4JaCa - A Communication Interface Between Multi-agent Systems and Opensource Chatbot Technologies

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Marcelo Silva Custódio,
  • Débora C. Engelmann,
  • Rafael H. Bordini,
  • Roberto Rodrigues-Filho,
  • Stefan Sarkadi,
  • Alison R. Panisson

摘要

Multi-agent systems (MAS) are a highly promising technology in the development of sophisticated applications, by enabling the integration of various AI techniques in a distributed and decentralised manner. However, human interaction with or as part of MAS often occurs through very static protocols. The advancement of natural language processing (NLP) has enabled the development of conversational agents, commonly known as chatbots, which can communicate in natural language through text or voice, providing a user-friendly interface. In this paper, we propose the development of Rasa4JaCa, which is an interface between the Rasa framework for chatbot development, and JaCaMo, that is an open-source MAS development framework. We evaluated Rasa4JaCa using a case study implemented in other existing interfaces. As a result of this development, it becomes possible for users to interact in natural language with a MAS, contextualising the development of application into the field of Hybrid Intelligence, where human users and intelligent agents can work together to solve complex problems.