Adopting Large Language Models to Automated System Integration

2025-04-11

AI Summary

Enterprise system integration faces challenges due to complex service composition, high manual labor costs, and the limited practicality of existing automation approaches—largely hindered by their reliance on formal modeling. Method: This paper proposes a large language model (LLM)-based, natural language–driven service integration framework. Contribution/Results: (1) We introduce the first natural language query benchmark specifically designed for service discovery and composition; (2) we propose Compositio Prompto, an LLM-native integration architecture optimized for service orchestration; and (3) we pioneer the application of retrieval-augmented generation (RAG) to open API service discovery. Experimental results demonstrate that our method automatically generates reusable service orchestration code directly from natural language specifications, significantly lowering the operational barrier for engineers while enabling fine-grained, semantics-aware service composition.

Technology Category

• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Planning, Routing, and Scheduling: Planning with Language Models
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Search and Retrieval-Augmented AI: Large language models for search
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Modern enterprise computing systems integrate numerous subsystems to resolve a common task by yielding emergent behavior. A widespread approach is using services implemented with Web technologies like REST or OpenAPI, which offer an interaction mechanism and service documentation standard, respectively. Each service represents a specific business functionality, allowing encapsulation and easier maintenance. Despite the reduced maintenance costs on an individual service level, increased integration complexity arises. Consequently, automated service composition approaches have arisen to mitigate this issue. Nevertheless, these approaches have not achieved high acceptance in practice due to their reliance on complex formal modeling. Within this Ph.D. thesis, we analyze the application of Large Language Models (LLMs) to automatically integrate the services based on a natural language input. The result is a reusable service composition, e.g., as program code. While not always generating entirely correct results, the result can still be helpful by providing integration engineers with a close approximation of a suitable solution, which requires little effort to become operational. Our research involves (i) introducing a software architecture for automated service composition using LLMs, (ii) analyzing Retrieval Augmented Generation (RAG) for service discovery, (iii) proposing a novel natural language query-based benchmark for service discovery, and (iv) extending the benchmark to complete service composition scenarios. We have presented our software architecture as Compositio Prompto, the analysis of RAG for service discovery, and submitted a proposal for the service discovery benchmark. Open topics are primarily the extension of the service discovery benchmark to service composition scenarios and the improvements of the service composition generation, e.g., using fine-tuning or LLM agents.

Problem

• Automating service integration complexity using Large Language Models
• Reducing reliance on formal modeling for service composition
• Generating reusable service compositions from natural language inputs

Innovation

• LLMs automate service integration via natural language
• RAG enhances service discovery in compositions
• Novel benchmark for query-based service discovery