system capability modeling

This paper addresses the lack of formal modeling tools in the capability approach. It introduces, for the first time, a mathematically rigorous model grounded in set theory and preference relations: functionings are aggregated via a structured mapping into a feasible capability set, while a utility function enables interdimensional comparability and ordinal ranking of multidimensional capabilities. The model formally axiomatizes Amartya Sen’s conception of capability, unifying the representation of an individual’s substantive freedom—i.e., their effective choice space—under constraints of resources, liberties, and environmental conditions. Key contributions include: (i) an axiomatic definition of the capability set; (ii) a well-defined mapping from combinations of functionings to capability sets; and (iii) guaranteed theoretical coherence and cross-contextual extensibility. By providing a computationally tractable and empirically testable foundation, the framework advances the capability approach from normative theory toward quantitative, evidence-based social welfare assessment.

Engineering models (e.g., SysML) lack formal planning semantics—such as preconditions, effects, resource constraints, and temporal bounds—hindering task reachability and performance evaluation across system variants. Method: This paper proposes a model-driven approach natively integrated into SysML, leveraging a custom SysML profile to embed symbolic planning semantics directly into engineering models. It enables fully automated, bidirectional transformation from SysML models to PDDL domain and problem files—without external models or manual intervention—ensuring semantic consistency and model reusability. The method synergistically combines model transformation algorithms with symbolic planning techniques. Contribution/Results: Evaluated on an aircraft assembly case study, the approach validates functional feasibility and execution efficiency across multiple system variants. It significantly enhances interoperability between Model-Based Systems Engineering (MBSE) and AI planning, advancing automation and rigor in early-phase system design and analysis.

Current cybersecurity capability maturity models (CCMMs) suffer from structural rigidity, dimensional fragmentation—across technical, organizational, and human factors—overreliance on qualitative assessment, insufficient quantification, and poor contextual adaptability, resulting in fragmented evaluations and weak operational applicability. To address these limitations, this paper proposes an organization-centric cybersecurity capability maturity assessment framework. It introduces a novel dynamic modeling approach that integrates multi-dimensional capability domains, establishing a holistic, flexible, and quantitative evaluation system spanning technical, organizational, and human-factor dimensions. The framework incorporates hierarchical maturity scales, customizable scenario-adaptation mechanisms, and cross-domain consistency validation to significantly enhance assessment coverage and practical implementation. Evaluated across three representative organizational types, the framework achieves a 37% improvement in maturity identification accuracy and reduces assessment duration by 52%.

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.

Systematic Literature Reviews (SLRs) in software engineering frequently suffer from validity threats due to omitted or inadequately executed steps, and lack an actionable, quality-improvement framework. Method: This paper introduces, for the first time, the Capability Maturity Model Integration (CMMI) maturity paradigm into SLR process modeling, proposing MM4SLR—a five-level, incremental maturity model grounded in 39 key practices, 9 goals, and 5 process areas. The model was designed via literature-driven identification, clustering analysis, and level mapping, and empirically validated across four published SLRs. Contribution/Results: MM4SLR enables effective diagnosis of SLR quality deficiencies, supports researchers in selecting context-appropriate practices, and facilitates continuous process improvement. It constitutes the first structured, assessable, and evolutionary maturity framework for enhancing the rigor, standardization, and credibility of SLRs in software engineering.

This work proposes a systematic approach to derive task effectiveness requirements in the absence of explicit user needs. The method deconstructs task intent into context, functionality, constraints, critical dimensions, performance attributes, and architectural solutions, and introduces a task complexity factor to quantify the impact of external challenges and technology maturity. By integrating Best-Worst Scaling, it prioritizes critical dimensions based on stakeholder judgments. Through task decomposition modeling and quantitative complexity analysis, the framework supports integration with UAF/SysML artifacts and establishes a traceable mechanism for generating Tier 1 and Tier 2 requirements. The approach is validated using a close air support mission case study, effectively addressing a critical gap in requirements engineering when clear initial inputs are unavailable.

This work addresses the lack of interpretable feedback in industrial automation capability planning under infeasible conditions and the difficulty in adapting to dynamic operational environments. The paper proposes the first hybrid decision-support system that integrates SMT-based symbolic planning with large language models (LLMs), enabling natural-language explanations of planning outcomes and user-authorized, adaptive updates to the knowledge model. Leveraging a human-in-the-loop mechanism and a routed multi-agent workflow, the system successfully completed all four feasible planning tasks and nine out of ten knowledge queries across 23 test cases. For three out of four infeasible scenarios, it generated actionable repair suggestions, and in five adaptation scenarios, it achieved feasible plans through user-approved knowledge modifications—establishing the first capability planning framework that is interpretable, interactive, iterative, and formally correct.

This work addresses the growing risks of misuse and loss of control associated with the broad applicability of foundation models, which existing alignment methods struggle to mitigate through hard behavioral constraints. It establishes capability control as a core objective distinct from alignment and introduces a defense-in-depth framework spanning data, learning, and system layers to enforce multi-granular behavioral constraints throughout the model lifecycle. By integrating techniques such as data distribution shaping, representational intervention, and runtime input/output/action-level safeguards, the paper systematically constructs pathways for capability control. It further identifies critical challenges—including the dual-use nature of knowledge and combinatorial generalization—offering a new paradigm for developing safe and controllable AI systems.