Skip to content
Book Open access

Typed Edits, Reviewable Models: Toward LLM-Supported Blended Co-Modeling

Oct 2026 · ACM/IEEE International Conference on Model Driven Engineering Languages and Systems · 0 citations · 16 references
Computer Science

TL;DR

LLM-supported blended co-modeling is proposed: a semantic-delta protocol in which LLMs submit versioned, typed edit proposals to a modeling kernel instead of mutating models directly, which evaluates protocol executability and failure containment, not LLM or human effectiveness.

Abstract

Blended modeling organizes one or more concrete syntaxes over a shared abstract syntax; under this inclusive definition, conventional single-syntax modeling is a special case. The distinctive multi-syntax case additionally requires cross-notation synchronization, impact analysis, and coherent review. We propose LLM-supported blended co-modeling: a semantic-delta protocol in which LLMs submit versioned, typed edit proposals to a modeling kernel instead of mutating models directly. The kernel interprets each operation against the current model state, returns operation-local diagnostics and affected projections, confines repair to an explicit budget, and commits only changes authorized by a human-defined review policy. Thus every AI-originated change remains reviewable, although low-risk changes may be pre-authorized. We instantiate the protocol in a reference architecture and workflow and report an executable replay over 15 tasks in a prototype with textual, tabular, and structural projections. The scripted proposal generators are deterministic test fixtures rather than proxies for LLM behavior; the replay therefore evaluates protocol executability and failure containment, not LLM or human effectiveness. Within this controlled setting, one bounded-repair round recovered 4 of 7 predefined invalid typed proposals, raising final validity from 8/15 to 12/15, and every accepted plan produced mutually consistent projections.

Read PDF

Similar papers

Book Open access Oct 2026

Automatic Generation of Local-First, Collaborative Modeling Languages

Modeling languages provide engineers with shared, domain-specific concepts for collaboratively structuring domain knowledge. Although modern language workbenches can generate much of the language-specific tooling from a metamodel, collaborative editing usually relies on external infrastructure that requires additional...

Léo Olivier, Marcos Didonet Del Fabro, S. Gérard et al. · 0 citations
Book Open access Oct 2026

Beyond Single-run Correctness: Nondeterminism-aware Evaluation of LLM-based Model Transformations

N nondeterminism-aware evaluation for LLM-based MDE evaluation is introduced, which suggests that LLM-based MDE evaluation should treat correctness, reproducibility, and variation meaning as distinct dimensions.

Riccardo Rubei, Alessio Bucaioni, A. Di Salle · 0 citations
Book Open access Oct 2026

From Natural Language to Formal Specifications: A Metamodel-Driven LLM Pipeline

This case study assesses the feasibility of combining LLM-based extraction, metamodel-guided refinement, automated validation, and human correction for requirements formalization and evaluates the approach on the ten published ACAS Xu safety properties.

Sally Ismail, Patrick Tessier · 0 citations
Book Open access Oct 2026

ReOCL: An Incremental OCL Core for Reactive Web-Based Modeling

Constraint languages such as OCL are commonly used to add precision to domain models and meta-models, typically built using UML class diagrams and Ecore, respectively. However, current constraint languages and their tooling are poorly aligned with modern web-based modeling stacks, which demand reactive execution enviro...

Francisco Martínez-Lasaca, Esther Guerra, J. de Lara · 0 citations
Book Open access Oct 2026

How Well Do LLMs Suggest Metamodel Mappings? A Multi-Provider Benchmark on Hand-Written ATL Transformations

This work presents a multi-provider benchmark of LLM-based metamodel-mapping suggestion, integrated in the Jjodel platform and run over eight canonical ATL Transformation Zoo transformations, with a ground truth reverse-engineered automatically from the hand-written .atl sources and a partial-match-aware comparison sch...

Antonio Bucchiarone, J. Di Rocco, A. Pierantonio · 0 citations
Open access 2026

From Context to Code: Codifying Cross-System Reasoning for LLM-Assisted Operations

Large language model (LLM)-assisted operations often rely on many independent tools, with the operator or agent stitching partial answers together client-side. This can produce correct answers, but the reasoning remains brittle, session-local, and difficult to reuse. We present Axiom, a production federated query engin...

Tanmay Chaudhry · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.