Bel Esprit: Multi-Agent Framework for Building AI Model Pipelines

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Kim, Yunsu, Abdelaziz, AhmedElmogtaba, Ferreira, Thiago Castro, Al-Badrashiny, Mohamed, Sawaf, Hassan
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911004060811264
author Kim, Yunsu
Abdelaziz, AhmedElmogtaba
Ferreira, Thiago Castro
Al-Badrashiny, Mohamed
Sawaf, Hassan
author_facet Kim, Yunsu
Abdelaziz, AhmedElmogtaba
Ferreira, Thiago Castro
Al-Badrashiny, Mohamed
Sawaf, Hassan
contents As the demand for artificial intelligence (AI) grows to address complex real-world tasks, single models are often insufficient, requiring the integration of multiple models into pipelines. This paper introduces Bel Esprit, a conversational agent designed to construct AI model pipelines based on user-defined requirements. Bel Esprit employs a multi-agent framework where subagents collaborate to clarify requirements, build, validate, and populate pipelines with appropriate models. We demonstrate the effectiveness of this framework in generating pipelines from ambiguous user queries, using both human-curated and synthetic data. A detailed error analysis highlights ongoing challenges in pipeline construction. Bel Esprit is available for a free trial at https://belesprit.aixplain.com.
format Preprint
id arxiv_https___arxiv_org_abs_2412_14684
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Bel Esprit: Multi-Agent Framework for Building AI Model Pipelines
Kim, Yunsu
Abdelaziz, AhmedElmogtaba
Ferreira, Thiago Castro
Al-Badrashiny, Mohamed
Sawaf, Hassan
Artificial Intelligence
Human-Computer Interaction
Multiagent Systems
As the demand for artificial intelligence (AI) grows to address complex real-world tasks, single models are often insufficient, requiring the integration of multiple models into pipelines. This paper introduces Bel Esprit, a conversational agent designed to construct AI model pipelines based on user-defined requirements. Bel Esprit employs a multi-agent framework where subagents collaborate to clarify requirements, build, validate, and populate pipelines with appropriate models. We demonstrate the effectiveness of this framework in generating pipelines from ambiguous user queries, using both human-curated and synthetic data. A detailed error analysis highlights ongoing challenges in pipeline construction. Bel Esprit is available for a free trial at https://belesprit.aixplain.com.
title Bel Esprit: Multi-Agent Framework for Building AI Model Pipelines
topic Artificial Intelligence
Human-Computer Interaction
Multiagent Systems
url https://arxiv.org/abs/2412.14684