Multi-Location Software Model Completion

TL;DR

This paper introduces NextFocus, a neural network-based approach for multi-location software model completion, enabling automated, coordinated changes across large models, significantly improving over existing single-location methods.

Contribution

We propose NextFocus, the first global embedding-based predictor capable of multi-location model completion, trained on real-world evolution data.

Findings

Achieves an average Precision@k score of 0.98 for k ≤ 10

Outperforms three baseline approaches significantly

Effectively handles heavily spread multi-location changes

Abstract

In model-driven engineering and beyond, software models are key development artifacts. In practice, they often grow to substantial size and complexity, undergoing thousands of modifications over time due to evolution, refactoring, and maintenance. The rise of AI has sparked interest in how software modeling activities can be automated. Recently, LLM-based approaches for software model completion have been proposed, however, the state of the art supports only single-location model completion by predicting changes at a specific location. Going beyond, we aim to bridge the gap toward handling coordinated changes that span multiple locations across large, complex models. Specifically, we propose a novel global embedding-based next focus predictor, NextFocus, which is capable of multi-location model completion for the first time. The predictor consists of a neural network with an attention mechanism that is trained on historical software model evolution data. Starting from an existing change, it predicts further model elements to change, potentially spanning multiple parts of the model. We evaluate our approach on multi-location model changes that have actually been performed by developers in real-world projects. NextFocus achieves promising results for multi-location model completion, even when changes are heavily spread across the model. It achieves an average Precision@k score of 0.98 for $k \leq 10$, significantly outperforming the three baseline approaches.