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

TL;DR

Bel Esprit is a multi-agent conversational framework that dynamically constructs AI model pipelines from user requirements, effectively handling ambiguous queries and demonstrating promising results in pipeline generation.

Contribution

This paper introduces Bel Esprit, a novel multi-agent system that automates AI pipeline creation based on user input, advancing the integration of collaborative agents in AI development.

Findings

Effective pipeline generation from ambiguous queries

Successful use of human-curated and synthetic data

Identified challenges in pipeline validation

Abstract

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.