arXiv subjects

Erik Johannes Husom

Publications and source records attributed to Erik Johannes Husom.

6 recordsLinked to original sources

arXiv2026

Engineering Sustainable Agents: A Systematic Comparison of Agentic LLMs for Developer Workflows

Large language models (LLMs) are increasingly used in software engineering, including agentic systems that coordinate multiple agents, but impose higher computational and environmental costs. In this paper, we present a comprehensive empirical study of agentic LLM systems across five software engineering tasks: code generation, technical debt identification, code vulnerability detection, log parsing, and log analysis. For each task, we compare LLM configurations that range from a non-agentic single-query baseline to multi-agent workflows, using six open-weight LLMs, two prompt strategies, and three hardware platforms. We assess each configuration in terms of accuracy, inference latency, and energy consumption. Our results reveal substantial trade-offs between agentic complexity and energy efficiency: multi-agent designs consume on average 6.36$\times$ as much energy and run 6.07$\times$ as long as the non-agentic baseline, with worst-case slowdowns of up to 160$\times$ for individual task--hardware pairs. Accuracy gains from additional agents are limited and task-specific: multi-agent improves average vulnerability-detection accuracy, but lightweight non-agentic and single-agent configurations still dominate the Pareto front, accounting for 59 of 66 Pareto-optimal configurations. Model and prompt choice act as task-specific levers whose effective direction varies between tasks rather than as global defaults. We translate these findings into design guidelines for sustainable, task-aware LLM-based development tools.

cs.SE↗

arXiv2026

Wasted large language models: A life cycle thinking approach

Large Language Models (LLMs) are machine learning (ML) models that have an increasingly large carbon footprint through their development and use. Efforts to increase the energy efficiency of these models have not translated into reduced consumption due to rebound effects such as Jevons Paradox - that increased efficiency drives increased use. There is therefore a need for additional measures to solve this problem. We suggest that one possible way forward is to use life cycle thinking, and view LLMs as products that can become waste. With this perspective, we investigate the potential of the waste hierarchy from the EU's Waste Framework Directive, which suggests five different measures for how to manage waste: prevention, reuse, recycling, recovery, and disposal. We examine how these measures can inform and motivate new types of thinking and approaches to reducing LLM waste and their environmental impact in general. Applying the waste hierarchy to LLMs highlights that preventing waste is essential for reducing the models' environmental impact, mainly because it reduces the need for training new models. Prevention can be achieved through many existing methods for reusing, "recycling", and "recovering" LLMs. Additionally, disposal can be important both for saving energy and for keeping a considerate attitude to the resources being spent on training LLMs. We also call to attention that prevention of unnecessary use of LLMs carry huge potential for lowering the climate impact of the models.

cs.CY↗

arXiv2026

Overview over the first decade of LIMITS

Computing within limits is a promising field, that follows principles of a) questioning endless growth narrative, b) considering and preparing for models of scarcity and c) reducing energy and material consumption, while considering d) a global spatial scale and e) long time frames. With computing's environmental impact growing and ecological limits becoming increasingly pressing, the LIMITS workshop has served as a central venue for this community since its inception in 2015, but an overview of the research published there has yet to be described. This paper addresses this gap by analyzing 160 publications from the LIMITS workshop in the period 2015 to 2025 to identify its international spread, contributions and developments in relation to field's core concerns, combining programmatic analysis with a manual review. Our findings indicate that the field has increasingly mentioned degrowth and post-growth, especially in 2024-2025. It has broadened its global perspective, with a growing, but still limited, representation of work beyond the Global North. The majority of papers are positional or observational, while artifact-producing research remains relatively scarce, though solution-oriented output has grown in recent years. This paper contributes to the LIMITS community by mapping its first decade and current trends to support future research and enhance its global impact.

cs.CY↗

arXiv2026

The Price of Prompting: Profiling Energy Use in Large Language Models Inference

In the rapidly evolving realm of artificial intelligence, deploying large language models (LLMs) poses increasingly pressing computational and environmental challenges. This paper introduces MELODI - Monitoring Energy Levels and Optimization for Data-driven Inference - a multifaceted framework crafted to monitor and analyze the energy consumed during LLM inference processes. MELODI enables detailed observations of power consumption dynamics and facilitates the creation of a comprehensive dataset reflective of energy efficiency across varied deployment scenarios. The dataset, generated using MELODI, encompasses a broad spectrum of LLM deployment frameworks, multiple language models, and extensive prompt datasets, enabling a comparative analysis of energy use. Using the dataset, we investigate how prompt attributes, including length and complexity, correlate with energy expenditure. Our findings indicate substantial disparities in energy efficiency, suggesting ample scope for optimization and adoption of sustainable measures in LLM deployment. Our contribution lies not only in the MELODI framework but also in the novel dataset, a resource that can be expanded by other researchers. Thus, MELODI is a foundational tool and dataset for advancing research into energy-conscious LLM deployment, steering the field toward a more sustainable future.

cs.CY↗

arXiv2025

Sustainable LLM Inference for Edge AI: Evaluating Quantized LLMs for Energy Efficiency, Output Accuracy, and Inference Latency

Deploying Large Language Models (LLMs) on edge devices presents significant challenges due to computational constraints, memory limitations, inference speed, and energy consumption. Model quantization has emerged as a key technique to enable efficient LLM inference by reducing model size and computational overhead. In this study, we conduct a comprehensive analysis of 28 quantized LLMs from the Ollama library, which applies by default Post-Training Quantization (PTQ) and weight-only quantization techniques, deployed on an edge device (Raspberry Pi 4 with 4GB RAM). We evaluate energy efficiency, inference performance, and output accuracy across multiple quantization levels and task types. Models are benchmarked on five standardized datasets (CommonsenseQA, BIG-Bench Hard, TruthfulQA, GSM8K, and HumanEval), and we employ a high-resolution, hardware-based energy measurement tool to capture real-world power consumption. Our findings reveal the trade-offs between energy efficiency, inference speed, and accuracy in different quantization settings, highlighting configurations that optimize LLM deployment for resource-constrained environments. By integrating hardware-level energy profiling with LLM benchmarking, this study provides actionable insights for sustainable AI, bridging a critical gap in existing research on energy-aware LLM deployment.

cs.CY↗

arXiv2021

On The Reliability Of Machine Learning Applications In Manufacturing Environments

The increasing deployment of advanced digital technologies such as Internet of Things (IoT) devices and Cyber-Physical Systems (CPS) in industrial environments is enabling the productive use of machine learning (ML) algorithms in the manufacturing domain. As ML applications transcend from research to productive use in real-world industrial environments, the question of reliability arises. Since the majority of ML models are trained and evaluated on static datasets, continuous online monitoring of their performance is required to build reliable systems. Furthermore, concept and sensor drift can lead to degrading accuracy of the algorithm over time, thus compromising safety, acceptance and economics if undetected and not properly addressed. In this work, we exemplarily highlight the severity of the issue on a publicly available industrial dataset which was recorded over the course of 36 months and explain possible sources of drift. We assess the robustness of ML algorithms commonly used in manufacturing and show, that the accuracy strongly declines with increasing drift for all tested algorithms. We further investigate how uncertainty estimation may be leveraged for online performance estimation as well as drift detection as a first step towards continually learning applications. The results indicate, that ensemble algorithms like random forests show the least decay of confidence calibration under drift.

cs.LG↗