pipeline integration

Traditional engineering analysis automation relies on fixed workflows and rigid interfaces, making it ill-suited to accommodate changes in data formats, units, or methodologies driven by product evolution. This work proposes DUCTILE, a novel framework that introduces large language model (LLM) agents into engineering analysis automation for the first time. By decoupling adaptive task orchestration from deterministic tool execution, DUCTILE dynamically interprets design documentation and adjusts processing pipelines under engineer supervision. The approach ensures both regulatory compliance and robustness while supporting structured document parsing, seamless tool integration, and human oversight. Evaluated on structural analysis tasks in aerospace manufacturing, DUCTILE successfully handled input variations, consistently producing results meeting expert standards across multiple independent runs and demonstrating practical viability through deployment by frontline engineers.

Modeling complex concurrent and timing-sensitive systems faces challenges in multi-objective compilation (for simulation, deployment, and formal verification), weak semantic consistency across targets, and the lack of expressive, unified modeling languages. Method: This paper introduces M, a textual modeling language grounded in the Actor model and discrete-event scheduling semantics, supporting temporal/state-triggered behaviors and asynchronous message passing. We design the first reusable, multi-target model compilation framework that uses M as a unified intermediate representation to enable semantics-preserving model transformations and code generation across heterogeneous targets. Contribution/Results: M serves as a common anchor for diverse domain-specific modeling languages, significantly enhancing model reusability and toolchain interoperability. The framework provides a general-purpose compilation infrastructure for heterogeneous system development—bridging simulation, implementation, and formal verification—while ensuring end-to-end semantic fidelity across compilation targets.

This study addresses the limitations of traditional Design Structure Matrix (DSM) modularization approaches, which rely solely on graph-based optimization and lack engineering semantic context, often failing to align with practical design requirements. The authors propose a novel DSM modularization paradigm integrating large language models (LLMs), leveraging prompt engineering and iterative refinement to embed system-level semantic information directly into the partitioning process—achieving high-quality results without custom optimization code. Central to this work is the "semantic alignment hypothesis," which elucidates how improper incorporation of domain knowledge can degrade performance. Through systematic experiments across five representative engineering cases using three mainstream LLMs, the method demonstrates convergence to reference-quality modularization within 30 iterations, offering a reproducible and practical pathway for LLM-driven engineering design optimization.

This study addresses the challenge faced by production system engineers in automatically verifying production line layouts due to limited knowledge of PDDL and planning theory. To bridge this gap, the authors propose a novel approach based on an Asset Administration Shell (AAS) capability model that natively generates complete PDDL planning problems directly from domain-level descriptions, eliminating the need for PDDL-specific submodels. The method integrates four Industry 4.0 standards—VDI 3682, IEC 61360-1, IDTA 02011, and IDTA 02016—to construct the AAS and employs an extraction algorithm to automatically translate multi-AAS architectures into PDDL domains. In a laboratory case study, the approach enabled engineers to systematically compare four layout variants by modifying only the AAS model, significantly lowering the barrier to adopting automated planning in industrial settings.

This study addresses the insufficient automation capability of Model-Driven Engineering (MDE) and the diminishing role of engineers in the AI era. Methodologically, it synthesizes metamodeling, AI-assisted modeling, model transformation, formal verification, and human factors engineering to establish a human–machine collaborative modeling paradigm, featuring multi-granularity model coordination and real-time feedback mechanisms. Key contributions include: (1) the first systematic identification of three fundamental bottlenecks—semantic gap, dynamic adaptability, and trustworthiness with explainability; (2) the distillation of six emerging engineering activities requiring automation across the full system lifecycle; and (3) the proposal of a theoretically grounded, industrially viable framework and research roadmap for intelligent MDE evolution, which balances automation efficacy with sustained engineer agency and domain expertise.

This study addresses the interoperability challenges in automotive domain modeling arising from the coexistence of heterogeneous tools, multiple modeling languages, and a mix of proprietary and open-source environments. To tackle this issue, the work proposes a novel automated approach that leverages large language models (LLMs) to map and merge source model instances into target metamodels based on Ecore and SysML v2. A structural validation mechanism is integrated to ensure semantic consistency and syntactic correctness of the generated models. Experimental evaluation on real-world automotive cases demonstrates that the method substantially reduces manual transformation effort while efficiently producing target models that are both structurally valid and aligned with user requirements, thereby establishing a viable new paradigm for cross-tool modeling interoperability.

This work addresses the limitations of traditional industrial automation systems, which rely on fixed rules and struggle to autonomously interpret tasks or adapt in dynamic environments. The authors propose a novel three-layer framework that integrates large language models (LLMs) with digital twins, employing TPSR-based task modeling to translate natural language instructions into executable workflows. Four distinct LLM agent roles are designed to enable goal-directed, adaptive behavior. This study presents the first systematic integration of LLM agents and digital twins, endowing industrial systems with generalized reasoning and autonomous decision-making capabilities to support dynamic task planning and human–machine collaboration. Prototype experiments demonstrate high task executability, instruction fidelity, and generation accuracy, significantly reducing manual intervention while enhancing system adaptability and usability.

This study addresses the challenges of high latency, unstable concurrency, and security risks faced by large language model (LLM) agents in automating asset lifecycle management within Industry 4.0. The authors propose a Plan-then-Execute architecture that generates verifiable workflow graphs and integrates a topology-aware parallel scheduling mechanism to enable controlled inference overlap while ensuring functional correctness and security. Key technical contributions include topological-sort-based multi-agent scheduling, structured context pruning, dependency-aware concurrency control, and graceful degradation under fault injection. Evaluated on the AssetOpsBench benchmark, the system reduces median end-to-end latency by 1.6× (up to 1.8× for highly parallel tasks) and cuts inference overhead by approximately 30% through context pruning, all while maintaining stable task completion rates and output quality.

This work addresses the challenge of implicit, fragmented, and recursive dependencies in large language model (LLM) development, which are difficult to trace manually and lead to licensing non-compliance, evaluation bias, and documentation inconsistencies. The authors propose ModSleuth, a system that formalizes LLM dependency types for the first time and employs an operation-centric modeling approach. ModSleuth leverages agents to automatically and recursively extract and verify dependencies from public artifacts, accurately distinguishing between direct and indirect dependencies while resolving entity alignment across disparate names, versions, and repositories. Evaluated on four LLM releases, the system identifies 1,060 source-verified dependencies, uncovering critical issues such as multi-hop licensing obligations, training-evaluation coupling, and documentation mismatches. The system and its dependency graphs are publicly released.

This work addresses the limitations of ROS launch files, which, being text-based, struggle to clearly represent inter-module connections and interfaces, often leading to configuration errors and poor readability. To overcome these challenges, the authors propose a model-driven, visual modeling approach based on WebGME, implementing a dedicated environment called ROSLaunchVisual. This framework enables graphical design of nodes, topic-based communication, and parameter configurations, while supporting semantic validation, automated import/export of launch files, and accurate communication mapping. The proposed method significantly enhances the intuitiveness of launch file development, improves system comprehensibility, and facilitates collaborative efficiency, thereby reducing misconfiguration rates. It is particularly well-suited for the efficient development and maintenance of large-scale or collaboratively engineered robotic systems.