Eco-Bee: A Personalised Multi-Modal Agent for Advancing Student Climate Awareness and Sustainable Behaviour in Campus Ecosystems

• URL: http://arxiv.org/abs/2604.15327v1
• Date: Fri, 06 Mar 2026 11:55:40 GMT
• Title: Eco-Bee: A Personalised Multi-Modal Agent for Advancing Student Climate Awareness and Sustainable Behaviour in Campus Ecosystems
• Abstract summary: Eco-Bee is a conversational agent that connects individual choices to environmental limits.<n> Tailored for students at the cusp of lifelong habits, Eco-Bee delivers actionable insights, peer benchmarking, and gamified challenges.<n>In a pilot tested across multiple campus networks, 96% of the student participants supported a campus-wide rollout and reported a clearer understanding of how daily behaviours collectively impact the planet's limits.
• Score: 2.924756839755417
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Universities are microcosms of urban ecosystems, with concentrated consumption patterns in food, transport, energy, and product usage. These environments not only contribute substantially to sustainability pressures but also provide a unique opportunity to advance sustainability education and behavioural change at scale. As in most sectors, digital sustainability initiatives within universities remain narrowly focused on carbon calculations, typically providing static feedback that limits opportunities for sustained behavioural change. To address this gap, we propose Eco-Bee, integrating large language models, a translation of the Planetary Boundaries framework (as Eco-Score), and a conversational agent that connects individual choices to environmental limits. Tailored for students at the cusp of lifelong habits, Eco-Bee delivers actionable insights, peer benchmarking, and gamified challenges to sustain engagement and drive measurable progress toward boundary-aligned living. In a pilot tested across multiple campus networks (n=52), 96% of the student participants supported a campus-wide rollout and reported a clearer understanding of how daily behaviours collectively impact the planet's limits. By embedding planetary science, behavioural reinforcement, and AI-driven personalisation into a single platform, Eco-Bee establishes a scalable foundation for climate-conscious universities and future AI-mediated sustainability infrastructures.

Related papers

• When LLMs Slow Down: How Environmental Impacts Mediate University Students' LLM Usage [2.519567577955041]
  We design and deploy an interface that visualizes latency-carbon trade-offs during live Large Language Models interactions.<n>We find that the likelihood of choosing the eco-feedback system significantly decreased as perceived response latency increased.<n>Students with stronger eco-mindedness demonstrated higher baseline willingness to adopt lower-carbon modes.
  arXiv  Detail & Related papers  (2026-08-25T01:46:54Z)
• SPADE: Self-Play in Adaptive Synthetic Executable Environments [110.80471334001574]
  We introduce SPADE, a self-play RL framework in which a single LLM plays two roles.<n>The Environment Designer writes complete, long-horizon training environments as executable code with an OpenAI Gym-style reset()/step() interface.<n>We find several components critical to success: grounding the Environment Designer on documents sampled from a large pretraining corpus, and giving it an accumulated environment memory.
  arXiv  Detail & Related papers  (2026-08-19T17:58:56Z)
• Designing Sustainable Federated Learning as a Service using Neural Architecture Search [2.452839095836699]
  We propose a Sustainable Federated Learning as a Service (SFL) framework for heteroge-us sustainable constraints.<n>We introduce a requirement-driven search space that transforms consumer sustainability profiles into a feasible architecture region.<n>We develop a consumer-level carbon feasibility estimation mechanism to evaluate candidate architectures under dynamic carbon conditions.
  arXiv  Detail & Related papers  (2026-08-14T15:00:39Z)
• Learn Weightlessness: Imitate Non-Self-Stabilizing Motions on Humanoid Robot [56.377161933570335]
  Humans naturally exploit a "weightless" state during non-self-stabilizing (NSS) motions.<n>Inspired by this biological mechanism, we propose a weightlessness-state auto-labeling strategy for dataset annotation.<n>Our work bridges the gap between precise trajectory tracking and adaptive environmental interaction, offering a biologically-inspired solution for contact-rich humanoid control.
  arXiv  Detail & Related papers  (2026-04-23T07:10:05Z)
• Autonomous Continual Learning of Computer-Use Agents for Environment Adaptation [57.65688895630163]
  We introduce ACuRL, an Autonomous Curriculum Reinforcement Learning framework that continually adapts agents to specific environments with zero human data.<n>Our method effectively enables both intra-environment and cross-environment continual learning, yielding 4-22% performance gains without forgetting existing environments.
  arXiv  Detail & Related papers  (2026-02-10T23:06:02Z)
• Toward Sustainable Generative AI: A Scoping Review of Carbon Footprint and Environmental Impacts Across Training and Inference Stages [2.2758077237273846]
  Generative AI is spreading rapidly, creating significant social and economic value.<n>The cumulative environmental footprint generated during large-scale service operations has received comparatively less attention.<n>This study conducts a scoping review of methodologies and research trends in AI carbon footprint assessment.
  arXiv  Detail & Related papers  (2025-11-21T11:59:34Z)
• One Life to Learn: Inferring Symbolic World Models for Stochastic Environments from Unguided Exploration [77.8436947454471]
  Symbolic world modeling requires inferring and representing an environment's transitional dynamics as an executable program.<n>OneLife is a framework that models world dynamics through conditionally-activated programmatic laws.<n>OneLife can successfully learn key environment dynamics from minimal, unguided interaction.
  arXiv  Detail & Related papers  (2025-10-14T02:49:32Z)
• Bites of Tomorrow: Personalized Recommendations for a Healthier and Greener Plate [53.11228047172713]
  We introduce Green Recommender Aligned with Personalized Eating (GRAPE), which is designed to prioritize and recommend sustainable food options.<n>We also design two innovative Green Loss functions that cater to green indicators with either uniform or differentiated priorities.
  arXiv  Detail & Related papers  (2025-08-19T14:35:37Z)
• Meltdown: Bridging the Perception Gap in Sustainable Food Behaviors Through Immersive VR [1.335888029640176]
  We developed Meltdown, an immersive virtual reality (VR) escape room that simulates a grocery shopping and food waste management experience.<n>The game emphasizes sustainable food choices and disposal practices, combining interactive elements and narrative feedback to promote behavioral change.<n>We observed statistically significant improvements in participants objective knowledge, perceived confidence, and intention to adopt sustainable behaviors.
  arXiv  Detail & Related papers  (2025-04-19T15:26:48Z)
• EcoVerse: An Annotated Twitter Dataset for Eco-Relevance Classification, Environmental Impact Analysis, and Stance Detection [0.0]
  EcoVerse is an annotated English Twitter dataset of 3,023 tweets spanning a wide spectrum of environmental topics. We propose a three-level annotation scheme designed for Eco-Relevance Classification, Stance Detection, and introducing an original approach for Environmental Impact Analysis.
  arXiv  Detail & Related papers  (2024-04-08T01:21:11Z)
• FREE: The Foundational Semantic Recognition for Modeling Environmental Ecosystems [56.0640340392818]
  We introduce a framework, FREE, that enables the use of varying features and available information to train a universal model.<n>The core idea is to map available environmental data into a text space and then convert the traditional predictive modeling task in environmental science to a semantic recognition problem.<n>Our evaluation on two societally important real-world applications, stream water temperature prediction and crop yield prediction, demonstrates the superiority of FREE over multiple baselines.
  arXiv  Detail & Related papers  (2023-11-17T00:53:09Z)
• Towards Sustainable Development: A Novel Integrated Machine Learning Model for Holistic Environmental Health Monitoring [0.0]
  Urbanization enables economic growth but also harms the environment through degradation. Machine learning has emerged as a promising tool for tracking environmental deterioration by identifying key predictive features. This research aims to assist governments in identifying intervention points, improving planning and conservation efforts, and ultimately contributing to sustainable development.
  arXiv  Detail & Related papers  (2023-08-20T16:35:21Z)
• Ecological Reinforcement Learning [76.9893572776141]
  We study the kinds of environment properties that can make learning under such conditions easier. understanding how properties of the environment impact the performance of reinforcement learning agents can help us to structure our tasks in ways that make learning tractable.
  arXiv  Detail & Related papers  (2020-06-22T17:55:03Z)

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.