Multi-Location Software Model Completion

2026-01-20

AI Summary

This work addresses the limitation of existing approaches that support only single-point model completion, which is insufficient for scenarios requiring coordinated modifications across multiple locations in complex software models. To overcome this, we propose NextFocus—a next-focus predictor based on global embeddings and attention mechanisms—that leverages historical software model evolution data to predict additional locations that should be synchronously modified given an initial change. To our knowledge, this is the first approach enabling multi-location synchronous completion for complex software models. Experimental results on real-world projects demonstrate that NextFocus achieves a Precision@k of 0.98 (for k ≤ 10), significantly outperforming three baseline methods and effectively transcending the constraints of traditional single-point prediction paradigms.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

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.

Problem

• multi-location model completion
• software model evolution
• coordinated changes
• model-driven engineering
• large language models

Innovation

• multi-location model completion
• NextFocus
• global embedding
• attention mechanism
• software model evolution