Towards Sustainable Web Agents: A Plea for Transparency and Dedicated Metrics for Energy Consumption

• URL: http://arxiv.org/abs/2502.17903v1
• Date: Tue, 25 Feb 2025 06:58:40 GMT
• Title: Towards Sustainable Web Agents: A Plea for Transparency and Dedicated Metrics for Energy Consumption
• Authors: Lars Krupp, Daniel Geißler, Paul Lukowicz, Jakob Karolus,
• Abstract summary: This study explores the energy and CO2 cost associated with web agents.<n>Results show how different philosophies in web agent creation can severely impact the associated expended energy.<n>Our work advocates a change in thinking when evaluating web agents, warranting dedicated metrics for energy consumption and sustainability.
• Score: 4.614707355759162
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Improvements in the area of large language models have shifted towards the construction of models capable of using external tools and interpreting their outputs. These so-called web agents have the ability to interact autonomously with the internet. This allows them to become powerful daily assistants handling time-consuming, repetitive tasks while supporting users in their daily activities. While web agent research is thriving, the sustainability aspect of this research direction remains largely unexplored. We provide an initial exploration of the energy and CO2 cost associated with web agents. Our results show how different philosophies in web agent creation can severely impact the associated expended energy. We highlight lacking transparency regarding the disclosure of model parameters and processes used for some web agents as a limiting factor when estimating energy consumption. As such, our work advocates a change in thinking when evaluating web agents, warranting dedicated metrics for energy consumption and sustainability.

Related papers

• An Illusion of Progress? Assessing the Current State of Web Agents [49.76769323750729]
  We conduct a comprehensive and rigorous assessment of the current state of web agents. Results depict a very different picture of the competency of current agents, suggesting over-optimism in previously reported results. We introduce Online-Mind2Web, an online evaluation benchmark consisting of 300 diverse and realistic tasks spanning 136 websites.
  arXiv  Detail & Related papers  (2025-04-02T05:51:29Z)
• Green MLOps to Green GenOps: An Empirical Study of Energy Consumption in Discriminative and Generative AI Operations [2.2765705959685234]
  This study investigates the energy consumption of Discriminative and Generative AI models within real-world MLOps pipelines. We employ software-based power measurements to ensure ease of replication across diverse configurations, models, and datasets.
  arXiv  Detail & Related papers  (2025-03-31T10:28:04Z)
• A Survey of WebAgents: Towards Next-Generation AI Agents for Web Automation with Large Foundation Models [45.12763718252896]
  In the context of the web, leveraging AI Agents -- WebAgents -- to automatically assist people in handling tedious daily tasks can dramatically enhance productivity and efficiency. To fully explore the potential of LFMs, extensive research has emerged on WebAgents designed to complete daily web tasks according to user instructions.
  arXiv  Detail & Related papers  (2025-03-30T08:15:44Z)
• Proposer-Agent-Evaluator(PAE): Autonomous Skill Discovery For Foundation Model Internet Agents [64.75036903373712]
  Proposer-Agent-Evaluator is a learning system that enables foundation model agents to autonomously discover and practice skills in the wild. At the heart of PAE is a context-aware task proposer that autonomously proposes tasks for the agent to practice with context information. The success evaluation serves as the reward signal for the agent to refine its policies through RL.
  arXiv  Detail & Related papers  (2024-12-17T18:59:50Z)
• Double-Exponential Increases in Inference Energy: The Cost of the Race for Accuracy [3.6731536660959985]
  Deep learning models in computer vision pose increasing concerns about energy consumption and sustainability.<n>We conduct a comprehensive analysis of the inference energy consumption of 1,200 ImageNet classification models.<n>We identify key factors contributing to energy consumption and demonstrate methods to improve energy efficiency.
  arXiv  Detail & Related papers  (2024-12-12T21:44:08Z)
• BiTSA: Leveraging Time Series Foundation Model for Building Energy Analytics [15.525789412274587]
  This paper presents the design of an interactive visualization tool, BiTSA.<n>The tool enables building managers to interpret complex energy data quickly and take immediate, data-driven actions based on real-time insights.
  arXiv  Detail & Related papers  (2024-11-20T23:49:06Z)
• OpenWebVoyager: Building Multimodal Web Agents via Iterative Real-World Exploration, Feedback and Optimization [66.22117723598872]
  We introduce an open-source framework designed to facilitate the development of multimodal web agent. We first train the base model with imitation learning to gain the basic abilities. We then let the agent explore the open web and collect feedback on its trajectories.
  arXiv  Detail & Related papers  (2024-10-25T15:01:27Z)
• WorkArena: How Capable Are Web Agents at Solving Common Knowledge Work Tasks? [83.19032025950986]
  We study the use of large language model-based agents for interacting with software via web browsers. WorkArena is a benchmark of 33 tasks based on the widely-used ServiceNow platform. BrowserGym is an environment for the design and evaluation of such agents.
  arXiv  Detail & Related papers  (2024-03-12T14:58:45Z)
• Continually learning out-of-distribution spatiotemporal data for robust energy forecasting [10.47725405370935]
  Building energy usage is essential for promoting sustainability and reducing waste. Forecasting energy usage during anomalous periods is difficult due to changes in occupancy patterns and energy usage behavior. Online learning has emerged as a promising solution to this challenge. We have conducted experiments using data from six buildings to test the efficacy of these approaches.
  arXiv  Detail & Related papers  (2023-06-10T09:12:10Z)
• $E^3$: Visual Exploration of Spatiotemporal Energy Demand [11.3457742898176]
  We identify the key elements of the energy demand problem. No previous research has investigated the shifts in demand. A potential flow based approach was formalized to model shifts in energy demand. Experts then evaluated and affirmed the usefulness of this approach through case studies of server real-world electricity data.
  arXiv  Detail & Related papers  (2020-06-16T19:59:28Z)
• Multi-Agent Meta-Reinforcement Learning for Self-Powered and Sustainable Edge Computing Systems [87.4519172058185]
  An effective energy dispatch mechanism for self-powered wireless networks with edge computing capabilities is studied. A novel multi-agent meta-reinforcement learning (MAMRL) framework is proposed to solve the formulated problem. Experimental results show that the proposed MAMRL model can reduce up to 11% non-renewable energy usage and by 22.4% the energy cost.
  arXiv  Detail & Related papers  (2020-02-20T04:58:07Z)

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.