Beyond Task Completion: An Assessment Framework for Evaluating Agentic AI Systems

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 perform complex tasks. These multi-agent architectures enable coordinated reasoning, planning, and execution across diverse domains, allowing agents to collaboratively automate complex workflows. Despite these advances, evaluation and assessment of LLM agents and the multi-agent systems they constitute remain a fundamental challenge. Although various approaches have been proposed in the software engineering literature for evaluating conventional software components, existing methods for AI-based systems often overlook the non-deterministic nature of models. This non-determinism introduces behavioral uncertainty during execution, yet existing evaluations rely on binary task completion metrics that fail to capture it. Evaluating agentic systems therefore requires examining additional dimensions, including the agent ability to invoke tools, ingest and retrieve memory, collaborate with other agents, and interact effectively with its environment. These challenges emerged during our ongoing industry collaboration with MontyCloud Inc., when we deployed an agentic system in production. These limitations surfaced during deployment, highlighting practical gaps in the current evaluation methods and the need for a systematic assessment of agent behavior beyond task outcomes. Informed by these observations and established definitions of agentic systems, we propose an end-to-end Agent Assessment Framework with four evaluation pillars encompassing LLMs, Memory, Tools, and Environment. We validate the framework on a representative Autonomous CloudOps use case, where experiments reveal behavioral deviations overlooked by conventional metrics, demonstrating its effectiveness in capturing runtime uncertainties.

SWEnergy: An Empirical Study on Energy Efficiency in Agentic Issue Resolution Frameworks with SLMs

Context. LLM-based autonomous agents in software engineering rely on large, proprietary models, limiting local deployment. This has spurred interest in Small Language Models (SLMs), but their practical effectiveness and efficiency within complex agentic frameworks for automated issue resolution remain poorly understood. Goal. We investigate the performance, energy efficiency, and resource consumption of four leading agentic issue resolution frameworks when deliberately constrained to using SLMs. We aim to assess the viability of these systems for this task in resource-limited settings and characterize the resulting trade-offs. Method. We conduct a controlled evaluation of four leading agentic frameworks (SWE-Agent, OpenHands, Mini SWE Agent, AutoCodeRover) using two SLMs (Gemma-3 4B, Qwen-3 1.7B) on the SWE-bench Verified Mini benchmark. On fixed hardware, we measure energy, duration, token usage, and memory over 150 runs per configuration. Results. We find that framework architecture is the primary driver of energy consumption. The most energy-intensive framework, AutoCodeRover (Gemma), consumed 9.4x more energy on average than the least energy-intensive, OpenHands (Gemma). However, this energy is largely wasted. Task resolution rates were near-zero, demonstrating that current frameworks, when paired with SLMs, consume significant energy on unproductive reasoning loops. The SLM's limited reasoning was the bottleneck for success, but the framework's design was the bottleneck for efficiency. Conclusions. Current agentic frameworks, designed for powerful LLMs, fail to operate efficiently with SLMs. We find that framework architecture is the primary driver of energy consumption, but this energy is largely wasted due to the SLMs' limited reasoning. Viable low-energy solutions require shifting from passive orchestration to architectures that actively manage SLM weaknesses.

SCAR: State-Space Compression for AI-Driven Resource Management in 6G-Enabled Vehicular Infotainment Systems

The advent of 6G networks opens new possibilities for connected infotainment services in vehicular environments. However, traditional Radio Resource Management (RRM) techniques struggle with the increasing volume and complexity of data such as Channel Quality Indicators (CQI) from autonomous vehicles. To address this, we propose SCAR (State-Space Compression for AI-Driven Resource Management), an Edge AI-assisted framework that optimizes scheduling and fairness in vehicular infotainment. SCAR employs ML-based compression techniques (e.g., clustering and RBF networks) to reduce CQI data size while preserving essential features. These compressed states are used to train 6G-enabled Reinforcement Learning policies that maximize throughput while meeting fairness objectives defined by the NGMN. Simulations show that SCAR increases time in feasible scheduling regions by 14\% and reduces unfair scheduling time by 15\% compared to RL baselines without CQI compression. Furthermore, Simulated Annealing with Stochastic Tunneling (SAST)-based clustering reduces CQI clustering distortion by 10\%, confirming its efficiency. These results demonstrate SCAR's scalability and fairness benefits for dynamic vehicular networks.

HarmonE: A Self-Adaptive Approach to Architecting Sustainable MLOps

Machine Learning Enabled Systems (MLS) are becoming integral to real-world applications, but ensuring their sustainable performance over time remains a significant challenge. These systems operate in dynamic environments and face runtime uncertainties like data drift and model degradation, which affect the sustainability of MLS across multiple dimensions: technical, economical, environmental, and social. While Machine Learning Operations (MLOps) addresses the technical dimension by streamlining the ML model lifecycle, it overlooks other dimensions. Furthermore, some traditional practices, such as frequent retraining, incur substantial energy and computational overhead, thus amplifying sustainability concerns. To address them, we introduce HarmonE, an architectural approach that enables self-adaptive capabilities in MLOps pipelines using the MAPE-K loop. HarmonE allows system architects to define explicit sustainability goals and adaptation thresholds at design time, and performs runtime monitoring of key metrics, such as prediction accuracy, energy consumption, and data distribution shifts, to trigger appropriate adaptation strategies. We validate our approach using a Digital Twin (DT) of an Intelligent Transportation System (ITS), focusing on traffic flow prediction as our primary use case. The DT employs time series ML models to simulate real-time traffic and assess various flow scenarios. Our results show that HarmonE adapts effectively to evolving conditions while maintaining accuracy and meeting sustainability goals.

Small Models, Big Tasks: An Exploratory Empirical Study on Small Language Models for Function Calling

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 shortest flight from New York to London on January 15 requires identifying the correct parameters to generate accurate function calls. Large Language Models (LLMs) can automate this process but are computationally expensive and impractical in resource-constrained settings. In contrast, Small Language Models (SLMs) can operate efficiently, offering faster response times, and lower computational demands, making them potential candidates for function calling on edge devices. In this exploratory empirical study, we evaluate the efficacy of SLMs in generating function calls across diverse domains using zero-shot, few-shot, and fine-tuning approaches, both with and without prompt injection, while also providing the finetuned models to facilitate future applications. Furthermore, we analyze the model responses across a range of metrics, capturing various aspects of function call generation. Additionally, we perform experiments on an edge device to evaluate their performance in terms of latency and memory usage, providing useful insights into their practical applicability. Our findings show that while SLMs improve from zero-shot to few-shot and perform best with fine-tuning, they struggle significantly with adhering to the given output format. Prompt injection experiments further indicate that the models are generally robust and exhibit only a slight decline in performance. While SLMs demonstrate potential for the function call generation task, our results also highlight areas that need further refinement for real-time functioning.

DRAFT-ing Architectural Design Decisions using LLMs

Architectural Knowledge Management (AKM) is crucial for software development but remains challenging due to the lack of standardization and high manual effort. Architecture Decision Records (ADRs) provide a structured approach to capture Architecture Design Decisions (ADDs), but their adoption is limited due to the manual effort involved and insufficient tool support. Our previous work has shown that Large Language Models (LLMs) can assist in generating ADDs. However, simply prompting the LLM does not produce quality ADDs. Moreover, using third-party LLMs raises privacy concerns, while self-hosting them poses resource challenges. To this end, we experimented with different approaches like few-shot, retrieval-augmented generation (RAG) and fine-tuning to enhance LLM's ability to generate ADDs. Our results show that both techniques improve effectiveness. Building on this, we propose Domain Specific Retreival Augumented Few Shot Fine Tuninng, DRAFT, which combines the strengths of all these three approaches for more effective ADD generation. DRAFT operates in two phases: an offline phase that fine-tunes an LLM on generating ADDs augmented with retrieved examples and an online phase that generates ADDs by leveraging retrieved ADRs and the fine-tuned model. We evaluated DRAFT against existing approaches on a dataset of 4,911 ADRs and various LLMs and analyzed them using automated metrics and human evaluations. Results show DRAFT outperforms all other approaches in effectiveness while maintaining efficiency. Our findings indicate that DRAFT can aid architects in drafting ADDs while addressing privacy and resource constraints.

Generative AI for Software Architecture. Applications, Trends, Challenges, and Future Directions

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 study has systematically addressed the topic. Aim: We aim to systematically synthesize the use, rationale, contexts, usability, and future challenges of GenAI in software architecture. Method: We performed a multivocal literature review (MLR), analyzing peer-reviewed and gray literature, identifying current practices, models, adoption contexts, and reported challenges, extracting themes via open coding. Results: Our review identified significant adoption of GenAI for architectural decision support and architectural reconstruction. OpenAI GPT models are predominantly applied, and there is consistent use of techniques such as few-shot prompting and retrieved-augmented generation (RAG). GenAI has been applied mostly to initial stages of the Software Development Life Cycle (SDLC), such as Requirements-to-Architecture and Architecture-to-Code. Monolithic and microservice architectures were the dominant targets. However, rigorous testing of GenAI outputs was typically missing from the studies. Among the most frequent challenges are model precision, hallucinations, ethical aspects, privacy issues, lack of architecture-specific datasets, and the absence of sound evaluation frameworks. Conclusions: GenAI shows significant potential in software design, but several challenges remain on its path to greater adoption. Research efforts should target designing general evaluation methodologies, handling ethics and precision, increasing transparency and explainability, and promoting architecture-specific datasets and benchmarks to bridge the gap between theoretical possibilities and practical use.

Architecting Digital Twins for Intelligent Transportation Systems

Modern transportation systems face growing challenges in managing traffic flow, ensuring safety, and maintaining operational efficiency amid dynamic traffic patterns. Addressing these challenges requires intelligent solutions capable of real-time monitoring, predictive analytics, and adaptive control. This paper proposes an architecture for DigIT, a Digital Twin (DT) platform for Intelligent Transportation Systems (ITS), designed to overcome the limitations of existing frameworks by offering a modular and scalable solution for traffic management. Built on a Domain Concept Model (DCM), the architecture systematically models key ITS components enabling seamless integration of predictive modeling and simulations. The architecture leverages machine learning models to forecast traffic patterns based on historical and real-time data. To adapt to evolving traffic patterns, the architecture incorporates adaptive Machine Learning Operations (MLOps), automating the deployment and lifecycle management of predictive models. Evaluation results highlight the effectiveness of the architecture in delivering accurate predictions and computational efficiency.

LoCoML: A Framework for Real-World ML Inference Pipelines

The widespread adoption of machine learning (ML) has brought forth diverse models with varying architectures, and data requirements, introducing new challenges in integrating these systems into real-world applications. Traditional solutions often struggle to manage the complexities of connecting heterogeneous models, especially when dealing with varied technical specifications. These limitations are amplified in large-scale, collaborative projects where stakeholders contribute models with different technical specifications. To address these challenges, we developed LoCoML, a low-code framework designed to simplify the integration of diverse ML models within the context of the \textit{Bhashini Project} - a large-scale initiative aimed at integrating AI-driven language technologies such as automatic speech recognition, machine translation, text-to-speech, and optical character recognition to support seamless communication across more than 20 languages. Initial evaluations show that LoCoML adds only a small amount of computational load, making it efficient and effective for large-scale ML integration. Our practical insights show that a low-code approach can be a practical solution for connecting multiple ML models in a collaborative environment.

Engineering LLM Powered Multi-agent Framework for Autonomous CloudOps

Cloud Operations (CloudOps) is a rapidly growing field focused on the automated management and optimization of cloud infrastructure which is essential for organizations navigating increasingly complex cloud environments. MontyCloud Inc. is one of the major companies in the CloudOps domain that leverages autonomous bots to manage cloud compliance, security, and continuous operations. To make the platform more accessible and effective to the customers, we leveraged the use of GenAI. Developing a GenAI-based solution for autonomous CloudOps for the existing MontyCloud system presented us with various challenges such as i) diverse data sources; ii) orchestration of multiple processes; and iii) handling complex workflows to automate routine tasks. To this end, we developed MOYA, a multi-agent framework that leverages GenAI and balances autonomy with the necessary human control. This framework integrates various internal and external systems and is optimized for factors like task orchestration, security, and error mitigation while producing accurate, reliable, and relevant insights by utilizing Retrieval Augmented Generation (RAG). Evaluations of our multi-agent system with the help of practitioners as well as using automated checks demonstrate enhanced accuracy, responsiveness, and effectiveness over non-agentic approaches across complex workflows.