Evaluating the effectiveness of LLM-based interoperability

TL;DR

This paper evaluates the ability of large language models to enable autonomous, runtime interoperability between heterogeneous systems, focusing on agricultural data exchange and comparing multiple models and strategies.

Contribution

It introduces an empirical evaluation of 13 open source LLMs for autonomous system interoperability, highlighting the effectiveness of specific models and strategies in a real-world use case.

Findings

qwen2.5-coder:32b achieved highest effectiveness with both strategies

Strategy CODEGEN outperformed DIRECT in complex dataset scenarios

Some LLMs can enable autonomous system interoperability

Abstract

Background: Systems of systems are becoming increasingly dynamic and heterogeneous, and this adds pressure on the long-standing challenge of interoperability. Besides its technical aspect, interoperability has also an economic side, as development time efforts are required to build the interoperability artifacts. Objectives: With the recent advances in the field of large language models (LLMs), we aim at analyzing the effectiveness of LLM-based strategies to make systems interoperate autonomously, at runtime, without human intervention. Method: We selected 13 open source LLMs and curated four versions of a dataset in the agricultural interoperability use case. We performed three runs of each model with each version of the dataset, using two different strategies. Then we compared the effectiveness of the models and the consistency of their results across multiple runs. Results: qwen2.5-coder:32b was the most effective model using both strategies DIRECT (average pass@1 >= 0.99) and CODEGEN (average pass@1 >= 0.89) in three out of four dataset versions. In the fourth dataset version, which included an unit conversion, all models using the strategy DIRECT failed, whereas using CODEGEN qwen2.5-coder:32b succeeded with an average pass@1 = 0.75. Conclusion: Some LLMs can make systems interoperate autonomously. Further evaluation in different domains is recommended, and further research on reliability strategies should be conducted.