Marin Litoiu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Marin Litoiu has a total of 103 co-authors. Here are the top co-authors by number of shared publications:
- Emilio Incerto
IMT School for Advanced Studies Lucca, Lucca, Italy
4 shared publications - Marik Shtern
The Hebrew University of Jerusalem
4 shared publications - Daniele Masti
Gran Sasso Science Institute, L'Aquila, Italy
3 shared publications - Komal Sarda
York University, Toronto, Canada
3 shared publications - Larisa Shwartz
IBM T. J. Watson Research Center, Yorktown Heights, NY, USA
3 shared publications - Patrizio Pelliccione
Department of Computer Science, Gran Sasso Science Institute, L’Aquila, Italy
3 shared publications
Latest Publications
- Open Access
- 9 September 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Autonomous and Adaptive Systems
Uncertainty Interaction in Software-Intensive Systems: A Community Roadmap
Despite substantial progress in managing uncertainty in software-intensive systems, existing methods often treat uncertainty sources independently and provide limited support for understanding their combined effects. When multiple uncertainties propagate through system elements and converge at shared variables, models, or decision points, they may interact in ways that alter system behavior, compromise requirements, or invalidate assurance arguments. This challenge, referred to as the uncertainty interaction problem, remains insufficiently understood. This roadmap paper reports the outcomes of the NII Shonan Seminar No. 232 on Uncertainty Interaction in Software-Intensive Systems (UNISON), held in March 2026. It develops a shared conceptual vocabulary for distinguishing uncertainty sources, propagation, confluence, interaction, and relevance; proposes an abstract workflow for identifying, filtering, and assessing relevant uncertainty interactions; and introduces a lifecycle-oriented framework for characterizing and selecting mitigation strategies. Building on these foundations, the paper organizes open challenges into a staged research roadmap spanning conceptual consolidation, reusable methods, engineering integration, validation, tooling, and community adoption. The roadmap provides a common reference point for researchers and practitioners working across software engineering, self-adaptive systems, control, artificial intelligence, formal methods, and assurance.
- 9 September 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Autonomous and Adaptive Systems
Open AccessUncertainty Interaction in Software-Intensive Systems: A Community Roadmap
Despite substantial progress in managing uncertainty in software-intensive systems, existing methods often treat uncertainty sources independently and provide limited support for understanding their combined effects. When multiple uncertainties propagate through system elements and converge at shared variables, models, or decision points, they may interact in ways that alter system behavior, compromise requirements, or invalidate assurance arguments. This challenge, referred to as the uncertainty interaction problem, remains insufficiently understood. This roadmap paper reports the outcomes of the NII Shonan Seminar No. 232 on Uncertainty Interaction in Software-Intensive Systems (UNISON), held in March 2026. It develops a shared conceptual vocabulary for distinguishing uncertainty sources, propagation, confluence, interaction, and relevance; proposes an abstract workflow for identifying, filtering, and assessing relevant uncertainty interactions; and introduces a lifecycle-oriented framework for characterizing and selecting mitigation strategies. Building on these foundations, the paper organizes open challenges into a staged research roadmap spanning conceptual consolidation, reusable methods, engineering integration, validation, tooling, and community adoption. The roadmap provides a common reference point for researchers and practitioners working across software engineering, self-adaptive systems, control, artificial intelligence, formal methods, and assurance.
- Open Access
- 5 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 840-850
Leveraging LLMs for Alert Summarization and Mitigation Plan Generation
- 5 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 840-850
Open AccessLeveraging LLMs for Alert Summarization and Mitigation Plan Generation
- Open Access
- 3 May 2026
- Published by Association for Computing Machinery (ACM)
- p. 406-418
An Evaluation Study of Generative AI Systems: Framework-Aware Performance Under Real-World Constraints
- 3 May 2026
- Published by Association for Computing Machinery (ACM)
- p. 406-418
Open AccessAn Evaluation Study of Generative AI Systems: Framework-Aware Performance Under Real-World Constraints
- Open Access
- 3 May 2026
- Published by Association for Computing Machinery (ACM)
- p. 254
AIPerfLLM: 4th International Workshop on Performance Optimization in the LLM World
- 3 May 2026
- Published by Association for Computing Machinery (ACM)
- p. 254
Open AccessAIPerfLLM: 4th International Workshop on Performance Optimization in the LLM World
- Open Access
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 142-147
ASTL: An Adaptive Serving Stack for LLMs to Balance Utilization and Tail Latency
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 142-147
Open AccessASTL: An Adaptive Serving Stack for LLMs to Balance Utilization and Tail Latency
- Open Access
- 22 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 215-218
Demo of LearnedWMP: Workload Memory Prediction Using Deep Query Template Representations
- 22 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 215-218
Open AccessDemo of LearnedWMP: Workload Memory Prediction Using Deep Query Template Representations
- Open Access
- 5 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 93-94
AIPerfLLM: 3rd International Workshop on Performance Optimization in the LLM world
- 5 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 93-94
Open AccessAIPerfLLM: 3rd International Workshop on Performance Optimization in the LLM world
- Open Access
- 10 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 358-369
Leveraging Large Language Models for the Auto-remediation of Microservice Applications: An Experimental Study
Runtime auto-remediation is crucial for ensuring the reliability and efficiency of distributed systems, especially within complex microservice-based applications. However, the complexity of modern microservice deployments often surpasses the capabilities of traditional manual remediation and existing autonomic computing methods. Our proposed solution harnesses large language models (LLMs) to generate and execute Ansible playbooks automatically to address issues within these complex environments. Ansible playbooks, a widely adopted markup language for IT task automation, facilitate critical actions such as addressing network failures, resource constraints, configuration errors, and application bugs prevalent in managing microservices. We apply in-context learning on pre-trained LLMs using our custom-made Ansible-based remediation dataset, equipping these models to comprehend diverse remediation tasks within microservice environments. Then, these tuned LLMs efficiently generate precise Ansible scripts tailored to specific issues encountered, surpassing current state-of-the-art techniques with high functional correctness (95.45%) and average correctness (98.86%).
- 10 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 358-369
Open AccessLeveraging Large Language Models for the Auto-remediation of Microservice Applications: An Experimental Study
Runtime auto-remediation is crucial for ensuring the reliability and efficiency of distributed systems, especially within complex microservice-based applications. However, the complexity of modern microservice deployments often surpasses the capabilities of traditional manual remediation and existing autonomic computing methods. Our proposed solution harnesses large language models (LLMs) to generate and execute Ansible playbooks automatically to address issues within these complex environments. Ansible playbooks, a widely adopted markup language for IT task automation, facilitate critical actions such as addressing network failures, resource constraints, configuration errors, and application bugs prevalent in managing microservices. We apply in-context learning on pre-trained LLMs using our custom-made Ansible-based remediation dataset, equipping these models to comprehend diverse remediation tasks within microservice environments. Then, these tuned LLMs efficiently generate precise Ansible scripts tailored to specific issues encountered, surpassing current state-of-the-art techniques with high functional correctness (95.45%) and average correctness (98.86%).
- Open Access
- 7 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 258-259
Closing the Loop: Building Self-Adaptive Software for Continuous Performance Engineering
Cloud computing and cloud-native platforms have rendered runtime environments more malleable. Simultaneously, the growing demand for flexible and agile software applications and services has driven the emergence of self-adaptive architectures. These architectures, in turn, facilitate software performance modeling, tuning, optimization, and scaling in a continuous manner, blurring the boundary between development-time and run-time. Self-adaptive software employs feedback loop controllers inspired by control theory or variations of the Monitoring-Analysis-Planning-Acting (MAPE) architecture. Whether implemented in a centralized or decentralized manner, most controllers utilize performance models that are learned or tuned at run-time. This shift implies that software is designed to be observable and controllable during execution, presupposing the co-design of software applications and their runtime controllers. This talk commences with a succinct overview of the evolution of self-adaptive software, accentuating key milestones along the journey. Subsequently, recent advancements in software performance modeling at runtime and the role of learning-enabled performance management during software operation are presented. Two recent works are highlighted: one focusing on constructing robust performance models to sustain continuous operation and deployment of cloud-native software, and the other on utilizing multimodal models for performance anomaly detection. The former supports cloud operations like continuous deployment of co-located applications, migration, consolidation of services, or scaling in response to workloads or interferences. The latter is tailored to support performance anomaly detection, localization, and identification of root causes, facilitating swift remediation of faults using generative AI. The final segment of the talk delves into current challenges in developing self-adaptive systems, presenting insights from a recent survey on the state of self-adaptive software in the industry and the challenges perceived by practitioners.
- 7 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 258-259
Open AccessClosing the Loop: Building Self-Adaptive Software for Continuous Performance Engineering
Cloud computing and cloud-native platforms have rendered runtime environments more malleable. Simultaneously, the growing demand for flexible and agile software applications and services has driven the emergence of self-adaptive architectures. These architectures, in turn, facilitate software performance modeling, tuning, optimization, and scaling in a continuous manner, blurring the boundary between development-time and run-time. Self-adaptive software employs feedback loop controllers inspired by control theory or variations of the Monitoring-Analysis-Planning-Acting (MAPE) architecture. Whether implemented in a centralized or decentralized manner, most controllers utilize performance models that are learned or tuned at run-time. This shift implies that software is designed to be observable and controllable during execution, presupposing the co-design of software applications and their runtime controllers. This talk commences with a succinct overview of the evolution of self-adaptive software, accentuating key milestones along the journey. Subsequently, recent advancements in software performance modeling at runtime and the role of learning-enabled performance management during software operation are presented. Two recent works are highlighted: one focusing on constructing robust performance models to sustain continuous operation and deployment of cloud-native software, and the other on utilizing multimodal models for performance anomaly detection. The former supports cloud operations like continuous deployment of co-located applications, migration, consolidation of services, or scaling in response to workloads or interferences. The latter is tailored to support performance anomaly detection, localization, and identification of root causes, facilitating swift remediation of faults using generative AI. The final segment of the talk delves into current challenges in developing self-adaptive systems, presenting insights from a recent survey on the state of self-adaptive software in the industry and the challenges perceived by practitioners.
- Open Access
- 7 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 236-246
A Learning-Based Caching Mechanism for Edge Content Delivery
With the advent of 5G networks and the rise of the Internet of Things (IoT), Content Delivery Networks (CDNs) are increasingly extending into the network edge. This shift introduces unique challenges, particularly due to the limited cache storage and the diverse request patterns at the edge. These edge environments can host traffic classes characterized by varied object-size distributions and object-access patterns. Such complexity makes it difficult for traditional caching strategies, which often rely on metrics like request frequency or time intervals, to be effective. Despite these complexities, the optimization of edge caching is crucial. Improved byte hit rates at the edge not only alleviate the load on the network backbone but also minimize operational costs and expedite content delivery to end-users. In this paper, we introduce HR-Cache, a comprehensive learning-based caching framework grounded in the principles of Hazard Rate (HR) ordering, a rule originally formulated to compute an upper bound on cache performance. HR-Cache leverages this rule to guide future object eviction decisions. It employs a lightweight machine learning model to learn from caching decisions made based on HR ordering, subsequently predicting the "cache-friendliness'' of incoming requests. Objects deemed "cache-averse'' are placed into cache as priority candidates for eviction. Through extensive experimentation, we demonstrate that HR-Cache not only consistently enhances byte hit rates compared to existing state-of-the-art methods but also achieves this with minimal prediction overhead. Our experimental results, using three real-world traces and one synthetic trace, indicate that HR-Cache consistently achieves 2.2-14.6% greater WAN traffic savings than LRU. It outperforms not only heuristic caching strategies but also the state-of-the-art learning-based algorithm.
- 7 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 236-246
Open AccessA Learning-Based Caching Mechanism for Edge Content Delivery
With the advent of 5G networks and the rise of the Internet of Things (IoT), Content Delivery Networks (CDNs) are increasingly extending into the network edge. This shift introduces unique challenges, particularly due to the limited cache storage and the diverse request patterns at the edge. These edge environments can host traffic classes characterized by varied object-size distributions and object-access patterns. Such complexity makes it difficult for traditional caching strategies, which often rely on metrics like request frequency or time intervals, to be effective. Despite these complexities, the optimization of edge caching is crucial. Improved byte hit rates at the edge not only alleviate the load on the network backbone but also minimize operational costs and expedite content delivery to end-users. In this paper, we introduce HR-Cache, a comprehensive learning-based caching framework grounded in the principles of Hazard Rate (HR) ordering, a rule originally formulated to compute an upper bound on cache performance. HR-Cache leverages this rule to guide future object eviction decisions. It employs a lightweight machine learning model to learn from caching decisions made based on HR ordering, subsequently predicting the "cache-friendliness'' of incoming requests. Objects deemed "cache-averse'' are placed into cache as priority candidates for eviction. Through extensive experimentation, we demonstrate that HR-Cache not only consistently enhances byte hit rates compared to existing state-of-the-art methods but also achieves this with minimal prediction overhead. Our experimental results, using three real-world traces and one synthetic trace, indicate that HR-Cache consistently achieves 2.2-14.6% greater WAN traffic savings than LRU. It outperforms not only heuristic caching strategies but also the state-of-the-art learning-based algorithm.