Runtime Composition in Dynamic System of Systems: A Systematic Review of Challenges, Solutions, Tools, and Evaluation Methods

• URL: http://arxiv.org/abs/2510.12616v1
• Date: Tue, 14 Oct 2025 15:14:57 GMT
• Title: Runtime Composition in Dynamic System of Systems: A Systematic Review of Challenges, Solutions, Tools, and Evaluation Methods
• Authors: Muhammad Ashfaq, Ahmed R. Sadik, Teerath Das, Muhammad Waseem, Niko Makitalo, Tommi Mikkonen,
• Abstract summary: Despite growing interest, the literature lacks a synthesis of runtime composition in dynamic SoSs.<n>This study synthesizes research on runtime composition in dynamic SoSs and identifies core challenges, solution strategies, supporting tools, and evaluation methods.
• Score: 2.172969718238335
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Context: Modern Systems of Systems (SoSs) increasingly operate in dynamic environments (e.g., smart cities, autonomous vehicles) where runtime composition -- the on-the-fly discovery, integration, and coordination of constituent systems (CSs)--is crucial for adaptability. Despite growing interest, the literature lacks a cohesive synthesis of runtime composition in dynamic SoSs. Objective: This study synthesizes research on runtime composition in dynamic SoSs and identifies core challenges, solution strategies, supporting tools, and evaluation methods. Methods: We conducted a Systematic Literature Review (SLR), screening 1,774 studies published between 2019 and 2024 and selecting 80 primary studies for thematic analysis (TA). Results: Challenges fall into four categories: modeling and analysis, resilient operations, system orchestration, and heterogeneity of CSs. Solutions span seven areas: co-simulation and digital twins, semantic ontologies, integration frameworks, adaptive architectures, middleware, formal methods, and AI-driven resilience. Service-oriented frameworks for composition and integration dominate tooling, while simulation platforms support evaluation. Interoperability across tools, limited cross-toolchain workflows, and the absence of standardized benchmarks remain key gaps. Evaluation approaches include simulation-based, implementation-driven, and human-centered studies, which have been applied in domains such as smart cities, healthcare, defense, and industrial automation. Conclusions: The synthesis reveals tensions, including autonomy versus coordination, the modeling-reality gap, and socio-technical integration. It calls for standardized evaluation metrics, scalable decentralized architectures, and cross-domain frameworks. The analysis aims to guide researchers and practitioners in developing and implementing dynamically composable SoSs.

Related papers

• Advances and Frontiers of LLM-based Issue Resolution in Software Engineering: A Comprehensive Survey [59.3507264893654]
  Issue resolution is a complex Software Engineering task integral to real-world development.<n> benchmarks like SWE-bench revealed this task as profoundly difficult for large language models.<n>This paper presents a systematic survey of this emerging domain.
  arXiv  Detail & Related papers  (2026-01-15T18:55:03Z)
• A Comprehensive Survey on Benchmarks and Solutions in Software Engineering of LLM-Empowered Agentic System [54.933911409697714]
  This survey presents the first holistic analysis of LLM-empowered software engineering.<n>We analyze 150+ recent papers and organize them into a comprehensive taxonomy spanning two major dimensions.<n>Our analysis reveals how the field has evolved from simple prompt engineering to complex agentic systems.
  arXiv  Detail & Related papers  (2025-10-10T06:56:50Z)
• The Emergence of Social Science of Large Language Models [0.8582203861502194]
  The social science of large language models (LLMs) examines how these systems evoke mind attributions, interact with one another, and transform human activity and institutions.<n>LLMs as Social Minds examines whether and when models display behaviors that elicit attributions of cognition, morality and bias, while addressing challenges such as test leakage and surface cues.<n>LLMs as Human Interactions examines how LLMs reshape tasks, learning, trust, work and governance, and how risks arise at the human-AI interface.
  arXiv  Detail & Related papers  (2025-09-29T14:55:14Z)
• Agentic Services Computing [51.50424046053763]
  We propose Agentic Services Computing, a paradigm that reimagines services as autonomous, adaptive, and collaborative agents.<n>We organize ASC around a four-phase lifecycle: Design, Deployment, Operation, and Evolution.
  arXiv  Detail & Related papers  (2025-09-29T07:29:18Z)
• A Survey on Cloud-Edge-Terminal Collaborative Intelligence in AIoT Networks [49.90474228895655]
  Cloud-edge-terminal collaborative intelligence (CETCI) is a fundamental paradigm within the artificial intelligence of things (AIoT) community.<n>CETCI has made significant progress with emerging AIoT applications, moving beyond isolated layer optimization to deployable collaborative intelligence systems.<n>This survey describes foundational architectures, enabling technologies, and scenarios of CETCI paradigms, offering a tutorial-style review for CISAIOT beginners.
  arXiv  Detail & Related papers  (2025-08-26T08:38:01Z)
• Modeling and Visualization Reasoning for Stakeholders in Education and Industry Integration Systems: Research on Structured Synthetic Dialogue Data Generation Based on NIST Standards [3.5516803380598074]
  This study addresses the structural complexity and semantic ambiguity in stakeholder interactions within the Education-Industry Integration (EII) system.<n>We propose a structural modeling paradigm based on the National Institute of Standards and Technology (NIST) synthetic data quality framework.
  arXiv  Detail & Related papers  (2025-06-20T12:37:43Z)
• From Standalone LLMs to Integrated Intelligence: A Survey of Compound Al Systems [6.284317913684068]
  Compound Al Systems (CAIS) is an emerging paradigm that integrates large language models (LLMs) with external components, such as retrievers, agents, tools, and orchestrators.<n>Despite growing adoption in both academia and industry, the CAIS landscape remains fragmented, lacking a unified framework for analysis, taxonomy, and evaluation.<n>This survey aims to provide researchers and practitioners with a comprehensive foundation for understanding, developing, and advancing the next generation of system-level artificial intelligence.
  arXiv  Detail & Related papers  (2025-06-05T02:34:43Z)
• Edge-Cloud Collaborative Computing on Distributed Intelligence and Model Optimization: A Survey [58.50944604905037]
  Edge-cloud collaborative computing (ECCC) has emerged as a pivotal paradigm for addressing the computational demands of modern intelligent applications.<n>Recent advancements in AI, particularly deep learning and large language models (LLMs), have dramatically enhanced the capabilities of these distributed systems.<n>This survey provides a structured tutorial on fundamental architectures, enabling technologies, and emerging applications.
  arXiv  Detail & Related papers  (2025-05-03T13:55:38Z)
• Robo-taxi Fleet Coordination at Scale via Reinforcement Learning [21.266509380044912]
  This work introduces a novel decision-making framework that unites mathematical modeling with data-driven techniques.<n>We present the AMoD coordination problem through the lens of reinforcement learning and propose a graph network-based framework.<n>In particular, we present the AMoD coordination problem through the lens of reinforcement learning and propose a graph network-based framework.
  arXiv  Detail & Related papers  (2025-04-08T15:19:41Z)
• Advancing Human-Machine Teaming: Concepts, Challenges, and Applications [11.61824291102382]
  Human-Machine Teaming (HMT) is revolutionizing collaboration across domains such as defense, healthcare, and autonomous systems by integrating AI-driven decision-making, trust calibration, and adaptive teaming.<n>This survey presents a comprehensive taxonomy of HMT, analyzing theoretical models, including reinforcement learning, instance-based learning, and interdependence theory, alongside interdisciplinary methodologies.
  arXiv  Detail & Related papers  (2025-03-16T19:32:17Z)
• An Extensible Benchmark Suite for Learning to Simulate Physical Systems [60.249111272844374]
  We introduce a set of benchmark problems to take a step towards unified benchmarks and evaluation protocols. We propose four representative physical systems, as well as a collection of both widely used classical time-based and representative data-driven methods.
  arXiv  Detail & Related papers  (2021-08-09T17:39:09Z)

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.