2 citations · 10 across the 31 of their papers we have counts for
35 papers
Mitigating Uncertainty Interactions in GenAI-based Adaptive Systems: Vision, Challenges and Preliminary Guidelines
Karthik Vaidhyanathan, Norha Villegas, Raffaela Mirandola +5
Modern software-intensive systems increasingly incorporate GenAI components, including LLM and agentic subsystems, which introduce novel and compounding sources of uncertainty acro…
Can LLMs Extract Architectural Design Decisions from Source Code Commits? - A Preliminary Exploratory Study
Amey Karan, Rudra Dhar, Mohamed Soliman +1
Context: Architectural Design Decisions (ADDs) capture the rationale behind the structure and evolution of software systems but are rarely documented explicitly, and are often hidd…
Watts and Debts of Agentic Frameworks: An Empirical Study (Registered Report)
Aneetta Sara Shany, Chandrasekar S, Karthik Vaidhyanathan
Context: Every agentic AI system shipped to production carries two hidden risks: accumulated Technical Debt (TD) and unmonitored runtime energy costs. While functional benchmarking…
EnCoDe: Energy Estimation of Source Code At Design-Time
Shailender Goyal, Akhila Matathammal, Karthik Vaidhyanathan
Energy efficiency has emerged as a vital attribute of software quality, with significant implications for both environmental sustainability and operational costs. However, existing…
LLM-based Automated Architecture View Generation: Where Are We Now?
Miryala Sathvika, Rudra Dhar, Karthik Vaidhyanathan
Architecture views are essential for software architecture documentation, yet their manual creation is labor intensive and often leads to outdated artifacts. As systems grow in com…
ArchBench: Benchmarking Generative-AI for Software Architecture Tasks
Bassam Adnan, Aviral Gupta, Sreemaee Akshathala +1
Benchmarks for large language models (LLMs) have progressed from snippet-level function generation to repository-level issue resolution, yet they overwhelmingly target implementati…
Can AI Agents Generate Microservices? How Far are We?
Bassam Adnan, Matteo Esposito, Davide Taibi +1
LLMs have advanced code generation, but their use for generating microservices with explicit dependencies and API contracts remains understudied. We examine whether AI agents can g…
AgenticAKM : Enroute to Agentic Architecture Knowledge Management
Rudra Dhar, Karthik Vaidhyanathan, Vasudeva Varma
Architecture Knowledge Management (AKM) is crucial for maintaining current and comprehensive software Architecture Knowledge (AK) in a software project. However AKM is often a labo…
CALM: A Self-Adaptive Orchestration Approach for QoS-Aware Routing in Small Language Model based Systems
Hemang Jain, Divyansh Pandey, Karthik Vaidhyanathan
AI-enabled systems are subjected to various types of runtime uncertainties, ranging from dynamic workloads, resource requirements, model drift, etc. These uncertainties have a big…
Harmonica: A Self-Adaptation Exemplar for Sustainable MLOps
Ananya Halgatti, Shaunak Biswas, Hiya Bhatt +2
Machine learning enabled systems (MLS) often operate in settings where they regularly encounter uncertainties arising from changes in their surrounding environment. Without structu…
Architecting AgentOps Needs CHANGE
Shaunak Biswas, Hiya Bhatt, Karthik Vaidhyanathan
The emergence of Agentic AI systems has outpaced the architectural thinking required to operate them effectively. These agents differ fundamentally from traditional software: their…
Toward architecting self-coding information systems
Rodrigo Falcão, Frank Elberzhager, Karthik Vaidhyanathan
In this extended abstract, we propose a novel research topic in the field of agentic AI, which we refer to as self-coding information systems. These systems will be able to dynamic…
Beyond Task Completion: An Assessment Framework for Evaluating Agentic AI Systems
Sreemaee Akshathala, Bassam Adnan, Mahisha Ramesh +3
Recent advances in agentic AI have shifted the focus from standalone Large Language Models (LLMs) to integrated systems that combine LLMs with tools, memory, and other agents to pe…
POLARIS: Is Multi-Agentic Reasoning the Next Wave in Engineering Self-Adaptive Systems?
Divyansh Pandey, Vyakhya Gupta, Prakhar Singhal +1
The growing scale, complexity, interconnectivity, and autonomy of modern software ecosystems introduce unprecedented uncertainty, challenging the foundations of traditional self-ad…
Dissecting Transformers: A CLEAR Perspective towards Green AI
Hemang Jain, Shailender Goyal, Divyansh Pandey +1
The rapid adoption of Large Language Models (LLMs) has raised significant environmental concerns. Unlike the one-time cost of training, LLM inference occurs continuously and domina…
Generating Energy-Efficient Code via Large-Language Models -- Where are we now?
Radu Apsan, Vincenzo Stoico, Michel Albonico +3
Context. The rise of Large Language Models (LLMs) has led to their widespread adoption in development pipelines. Goal. We empirically assess the energy efficiency of Python code ge…
SCAR: State-Space Compression for Scalable AI-Based Network Management of Vehicular Services
Ioan-Sorin Comsa, Purav Shah, Karthik Vaidhyanathan +6
The increasing demand for connected vehicular services poses significant challenges for AI-based network and service management due to the high volume and rapid variability of netw…
HarmonE: A Self-Adaptive Approach to Architecting Sustainable MLOps
Hiya Bhatt, Shaunak Biswas, Srinivasan Rakhunathan +1
Machine Learning Enabled Systems (MLS) are becoming integral to real-world applications, but ensuring their sustainable performance over time remains a significant challenge. These…
Small Models, Big Tasks: An Exploratory Empirical Study on Small Language Models for Function Calling
Ishan Kavathekar, Raghav Donakanti, Ponnurangam Kumaraguru +1
Function calling is a complex task with widespread applications in domains such as information retrieval, software engineering and automation. For example, a query to book the shor…
DRAFT-ing Architectural Design Decisions using LLMs
Rudra Dhar, Adyansh Kakran, Amey Karan +2
Architectural Knowledge Management (AKM) is crucial for software development but remains challenging due to the lack of standardization and high manual effort. Architecture Decisio…
Generative AI for Software Architecture. Applications, Challenges, and Future Directions
Matteo Esposito, Xiaozhou Li, Sergio Moreschini +5
Context: Generative Artificial Intelligence (GenAI) is transforming much of software development, yet its application in software architecture is still in its infancy, and no prior…
Architecting Digital Twins for Intelligent Transportation Systems
Hiya Bhatt, Sahil, Karthik Vaidhyanathan +4
Modern transportation systems face growing challenges in managing traffic flow, ensuring safety, and maintaining operational efficiency amid dynamic traffic patterns. Addressing th…
EdgeMLBalancer: A Self-Adaptive Approach for Dynamic Model Switching on Resource-Constrained Edge Devices
Akhila Matathammal, Kriti Gupta, Larissa Lavanya +3
The widespread adoption of machine learning on edge devices, such as mobile phones, laptops, IoT devices, etc., has enabled real-time AI applications in resource-constrained enviro…
LLMs for Generation of Architectural Components: An Exploratory Empirical Study in the Serverless World
Shrikara Arun, Meghana Tedla, Karthik Vaidhyanathan
Recently, the exponential growth in capability and pervasiveness of Large Language Models (LLMs) has led to significant work done in the field of code generation. However, this gen…