aiqbench analysis
The paper pairs a building-grid co-simulation environment (CityLearn V2 with Pandapower and OpenDSS) with an LLM agent that retrieves, composes, executes, verifies, and repairs simulation pipelines from natural-language tasks. The LLM agent and the RL-based building control are central to the work, not incidental. Readers should note that the evidence is limited to experiments on realistic distribution networks, with reliability and executability gains reported but no broader claims about autonomous energy-system operation.
AutoB2G: Agentic Simulation and Reinforcement Learning for Spatio-Temporal Grid-Interactive Building Control
arXiv:2603.26005v3 Announce Type: replace Abstract: Grid-interactive building control can improve demand-side flexibility, but realistic evaluation requires coordinated co-simulation of buildings, reinforcement learning (RL), and distribution grids. Translating user intent into executable co-simulation workflows is labor-intensive, requiring the manual integration and configuration of heterogeneous simulators and interfaces. We introduce AutoB2G, a grid-aware building--grid co-simulation environment integrating CityLearn V2 with Pandapower and OpenDSS. It supports balanced and three-phase unbalanced grid simulation and a broad range of grid-side evaluation metrics. AutoB2G organizes simulation components as a directed acyclic graph (DAG), explicitly encoding module dependencies and execution order for dependency-aware retrieval and composition. Building on this structure, we develop a large language model (LLM)-based agentic framework that automatically retrieves, composes, executes, verifies, and repairs simulation pipelines from natural-language task descriptions. Experiments on realistic distribution networks show improved reliability and executability of complex building--grid workflows, demonstrating the potential of agentic LLMs for scientific simulation orchestration in energy systems.
Abstract:Grid-interactive building control can improve demand-side flexibility, but realistic evaluation requires coordinated co-simulation of buildings, reinforcement learning (RL), and distribution grids. Translating user intent into executable co-simulation workflows is labor-intensive, requiring the manual integration and configuration of heterogeneous simulators and interfaces. We introduce AutoB2G, a grid-aware building--grid co-simulation environment integrating CityLearn V2 with Pandapower and OpenDSS. It supports balanced and three-phase unbalanced grid simulation and a broad range of grid-side evaluation metrics. AutoB2G organizes simulation components as a directed acyclic graph (DAG), explicitly encoding module dependencies and execution order for dependency-aware retrieval and composition. Building on this structure, we develop a large language model (LLM)-based agentic framework that automatically retrieves, composes, executes, verifies, and repairs simulation pipelines from natural-language task descriptions. Experiments on realistic distribution networks show improved reliability and executability of complex building--grid workflows, demonstrating the potential of agentic LLMs for scientific simulation orchestration in energy systems.
Artificial Intelligence (cs.AI)
arXiv:2603.26005 [cs.AI]
(or arXiv:2603.26005v3 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2603.26005 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 240 words