Research & Development Projects

A showcase of prototypes, libraries, tools, and standardized configuration schemas developed throughout my Ph.D. research.

FeaturedJuly 2025 - Sept 2025

EMF Server

Main Developer

A stateless API server exposing a set of routes for metamodel-independent operations. It enables generic and dynamic path operations on any model element, providing interoperability between web applications and EMF models.

Model ManagementEMFREST API
FeaturedDec 2024 - December 2025

Model Management Agents

Research & Architecture

LLM-based agents for model transformation (ATL) and model editing (EMF), exposed via MCP servers. Combines dedicated per-tool interfaces with a relevance-score-based tool filtering mechanism to improve tool selection accuracy and scalability as the number of available tools grows. Includes a reusable dataset generation methodology and 1,200+ labeled instruction–tool-call pairs for evaluation.

PythonLangGraphATLEMFMCPLLM Agents
Nov 2024 - Dec 2024

ATL Transformation Server

Developer / Integrator

A REST API server for managing and executing ATL transformations. It links directly to the `ATL_Zoo` to search and apply transformation rules on models dynamically.

JavaAPIEMFATL Transformationz
FeaturedSeptember 2025 - April 2026

Megamodel-based Agent Evaluation

Research & Architecture

A megamodel-based approach for evaluating ecosystems of LLM-based modeling agents. Unifies modeling artifacts, tools, agent workflows, and execution traces in a single structured repository, supporting three complementary capabilities: automated model discovery from existing execution logs, dataset augmentation from small seed samples, and systematic agent benchmarking. Validated on LLM-based agents for ATL transformation and EMF model-handling tasks, discovering 16,000+ megamodel elements from real execution logs and enabling regression testing across agent versions.

PythonLangSmithATLEMFLLM Agents
Oct 2024 - Nov 2024

ATL_Zoo

Standardization Engineer

Standardization of the Eclipse ATL Zoo. Developed configuration schemas and automated generation pipelines to encapsulate and validate critical parameters (e.g. source/target metamodels) for each transformation in the repository.

JSONAutomationMetadata