Model-Driven Discipline for Multi-Agent LLMs: Requirement-to-Verification Generation of Traceable System Models

• URL: http://arxiv.org/abs/2607.16708v1
• Date: Sat, 18 Jul 2026 08:50:55 GMT
• Title: Model-Driven Discipline for Multi-Agent LLMs: Requirement-to-Verification Generation of Traceable System Models
• Abstract summary: RADIANT is an engineering methodology that combines MDE with Multi-Agent Large Language Models.<n>It automatically generates heterogeneous models across engineering phases.<n>It provides exact, automated change-impact analysis.
• Score: 62.62160094849002
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Software complexity is a long-standing challenge for system engineers. Model-Driven Engineering (MDE) addresses it by treating models as first-class artefacts, but a typical MDE process spans many tools and produces heterogeneous models of different system aspects, making traceability, maintenance, and change management difficult. We propose RADIANT, an engineering methodology that combines MDE with Multi-Agent Large Language Models (LLMs) for complete model-based system development, with a focus on safety-critical systems. From a carefully specified requirement model, RADIANT automatically generates heterogeneous models across engineering phases -- a concept model, a domain-specific modelling language, a conforming system model, and a behaviour model -- together with executable, element-level traceability links, on top of which it provides exact, automated change-impact analysis. Generated behaviour models are translated into CSP and formally verified (e.g.\ for deadlock freedom and convergence) with a counterexample-driven repair loop. Evaluating RADIANT across three LLMs, we find that the multi-agent decomposition reliably improves the \emph{syntactic validity} of the generated formal artefacts over a single-agent baseline -- and their \emph{executability} where the model's code generation permits -- while gains in semantic accuracy are model-dependent. A six-participant study shows an order-of-magnitude ($10$--$15\times$) reduction in development time, and the unmodified pipeline transfers to a second domain.

Related papers

• M*: A Modular, Extensible, Serving System for Multimodal Models [62.77975969000349]
  We present M*, a universal serving system for efficient serving of composite AI models.<n>We show how it can concisely capture composite models from a broad range of families.<n>M* also outperforms the V-JEPA 2-AC rollout baseline for robotic planning by up to 12.5x.
  arXiv  Detail & Related papers  (2026-06-10T21:22:22Z)
• Agent2World: Learning to Generate Symbolic World Models via Adaptive Multi-Agent Feedback [51.22403664895878]
  Agent2World is a tool-augmented multi-agent framework that achieves strong inference-time world-model generation.<n>It also serves as a data engine for supervised fine-tuning, by grounding generation in multi-agent feedback.
  arXiv  Detail & Related papers  (2025-12-26T18:54:14Z)
• GLUE: Generative Latent Unification of Expertise-Informed Engineering Models [3.005158583027536]
  We introduce Generative Latent Unification of Expertise-Informed Engineering Models (GLUE)<n>GLUE orchestrates pre-trained, frozen subsystem generators while enforcing system-level feasibility, optimality, and diversity.<n>On a UAV design problem with five coupling constraints, we find that data-driven approaches yield diverse, high-performing designs but require large datasets to satisfy constraints reliably.
  arXiv  Detail & Related papers  (2025-12-22T15:23:19Z)
• Heterogeneous Model Alignment in Digital Twin [0.0]
  Key challenge in model-driven DTs is aligning heterogeneous models across abstraction layers.<n>Existing methods, relying on static mappings and manual updates, are often inflexible, error-prone, and risk compromising data integrity.<n>We present a heterogeneous model alignment approach for multi-layered, model-driven DTs.
  arXiv  Detail & Related papers  (2025-12-17T10:36:55Z)
• Modelling and Model-Checking a ROS2 Multi-Robot System using Timed Rebeca [1.3048920509133806]
  Timed Rebeca is an actor-based modelling language supporting reactive, concurrent and time semantics.<n>We show how to use models to design and verify a multi-robot system, how to discretely model a continuous system to do model-checking efficiently.<n>The released Rebeca and ROS2 codes can serve as a foundation for modelling multiple autonomous robots systems.
  arXiv  Detail & Related papers  (2025-11-19T08:28:30Z)
• Merge and Guide: Unifying Model Merging and Guided Decoding for Controllable Multi-Objective Generation [49.98025799046136]
  We introduce Merge-And-GuidE, a two-stage framework that leverages model merging for guided decoding.<n>In Stage 1, MAGE resolves a compatibility problem between the guidance and base models.<n>In Stage 2, we merge explicit and implicit value models into a unified guidance proxy, which then steers the decoding of the base model from Stage 1.
  arXiv  Detail & Related papers  (2025-10-04T11:10:07Z)
• Every Step Counts: Decoding Trajectories as Authorship Fingerprints of dLLMs [63.82840470917859]
  We show that the decoding mechanism of dLLMs can be used as a powerful tool for model attribution.<n>We propose a novel information extraction scheme called the Directed Decoding Map (DDM), which captures structural relationships between decoding steps and better reveals model-specific behaviors.
  arXiv  Detail & Related papers  (2025-10-02T06:25:10Z)
• OptMerge: Unifying Multimodal LLM Capabilities and Modalities via Model Merging [124.91183814854126]
  Model merging seeks to combine multiple expert models into a single model.<n>We introduce a benchmark for model merging research that clearly divides the tasks for MLLM training and evaluation.<n>We find that model merging offers a promising way for building improved MLLMs without requiring training data.
  arXiv  Detail & Related papers  (2025-05-26T12:23:14Z)
• A Model Is Not Built By A Single Prompt: LLM-Based Domain Modeling With Question Decomposition [4.123601037699469]
  In real-world domain modeling, engineers usually decompose complex tasks into easily solvable sub-tasks. We propose an LLM-based domain modeling approach via question decomposition, similar to developer's modeling process. Preliminary results show that our approach outperforms the single-prompt-based prompt.
  arXiv  Detail & Related papers  (2024-10-13T14:28:04Z)
• MAO: A Framework for Process Model Generation with Multi-Agent Orchestration [12.729855942941724]
  This article explores a framework for automatically generating process models with multi-agent orchestration (MAO) Large language models are prone to hallucinations, so the agents need to review and repair semantic hallucinations in process models. Experiments demonstrate that the process models generated by our framework surpass manual modeling by 89%, 61%, 52%, and 75% on four different datasets.
  arXiv  Detail & Related papers  (2024-08-04T03:32:17Z)
• EMR-Merging: Tuning-Free High-Performance Model Merging [55.03509900949149]
  We show that Elect, Mask & Rescale-Merging (EMR-Merging) shows outstanding performance compared to existing merging methods. EMR-Merging is tuning-free, thus requiring no data availability or any additional training while showing impressive performance.
  arXiv  Detail & Related papers  (2024-05-23T05:25:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.