AutoB2G: A Large Language Model-Driven Agentic Framework For Automated Building-Grid Co-Simulation

arXiv cs.AI / 3/30/2026

💬 OpinionIdeas & Deep AnalysisModels & Research

共有:

Key Points

AutoB2G is proposed as an LLM-driven agentic framework that automates end-to-end building–grid co-simulation based only on natural-language task descriptions.
The approach extends CityLearn V2 to support Building-to-Grid (B2G) interactions and uses an LLM-based orchestration layer (SOCIA) to generate, run, and iteratively refine simulations.
To address LLMs’ lack of implementation-context knowledge, the paper builds and organizes simulation configuration and functional modules into a directed acyclic graph (DAG) to encode dependencies and execution order.
Experiments reported in the paper indicate AutoB2G can produce executable simulators and coordinate B2G interactions to improve grid-side performance metrics, reducing the need for manual setup and programming.
Overall, the work targets a key gap in prior environments: moving from building-focused evaluation and manual configuration toward systematic grid-impact evaluation with automated simulation workflows.

Abstract

The growing availability of building operational data motivates the use of reinforcement learning (RL), which can learn control policies directly from data and cope with the complexity and uncertainty of large-scale building clusters. However, most existing simulation environments prioritize building-side performance metrics and lack systematic evaluation of grid-level impacts, while their experimental workflows still rely heavily on manual configuration and substantial programming expertise. Therefore, this paper proposes AutoB2G, an automated building-grid co-simulation framework that completes the entire simulation workflow solely based on natural-language task descriptions. The framework extends CityLearn V2 to support Building-to-Grid (B2G) interaction and adopts the large language model (LLM)-based SOCIA (Simulation Orchestration for Computational Intelligence with Agents) framework to automatically generate, execute, and iteratively refine the simulator. As LLMs lack prior knowledge of the implementation context of simulation functions, a codebase covering simulation configurations and functional modules is constructed and organized as a directed acyclic graph (DAG) to explicitly represent module dependencies and execution order, guiding the LLM to retrieve a complete executable path. Experimental results demonstrate that AutoB2G can effectively enable automated simulator implementations, coordinating B2G interactions to improve grid-side performance metrics.