SAGAI-MID: A Generative AI-Driven Middleware for Dynamic Runtime Interoperability
2026-03-30 • Software Engineering
Software EngineeringArtificial Intelligence
AI summaryⓘ
The authors created SAGAI-MID, a middleware that uses large language models (LLMs) to automatically detect and fix differences in data formats between various services and devices as they communicate, without needing manual coding. Their system uses a multi-step process including both pattern detection and semantic analysis, plus strategies that either transform data on the fly or generate reusable adapter code. They tested SAGAI-MID across different real-world scenarios and showed it performs well, with one approach consistently better than another. The authors also found that more expensive models don't necessarily give better results, which is important for designing software using LLMs at runtime.
middlewareschema mismatchlarge language modelsFastAPIREST APIGraphQLIoTruntime adaptationadapter codeinteroperability
Authors
Oliver Aleksander Larsen, Mahyar T. Moghaddam
Abstract
Modern distributed systems integrate heterogeneous services, REST APIs with different schema versions, GraphQL endpoints, and IoT devices with proprietary payloads that suffer from persistent schema mismatches. Traditional static adapters require manual coding for every schema pair and cannot handle novel combinations at runtime. We present SAGAI-MID, a FastAPI-based middleware that uses large language models (LLMs) to dynamically detect and resolve schema mismatches at runtime. The system employs a five-layer pipeline: hybrid detection (structural diff plus LLM semantic analysis), dual resolution strategies (per-request LLM transformation and LLM-generated reusable adapter code), and a three-tier safeguard stack (validation, ensemble voting, rule-based fallback). We frame the architecture through Bass et al.'s interoperability tactics, transforming them from design-time artifacts into runtime capabilities. We evaluate SAGAI-MID on 10 interoperability scenarios spanning REST version migration, IoT-to-analytics bridging, and GraphQL protocol conversion across six LLMs from two providers. The best-performing configuration achieves 0.90 pass@1 accuracy. The CODEGEN strategy consistently outperforms DIRECT (0.83 vs 0.77 mean pass@1), while cost varies by over 30x across models with no proportional accuracy gain; the most accurate model is also the cheapest. We discuss implications for software architects adopting LLMs as runtime architectural components.