One Agent per Zone: Decentralised Active Inference under Partial Observability for Multi-Zone HVAC Control on Edge Hardware

Multi-zone HVAC control is a spatial decision problem in which indoor thermal evolution and control decisions depend not only on outdoor conditions and internal heat gains but also on zone layout, physical adjacency, and delayed thermal interactions across the building. Recent LLM-based HVAC controllers have shown that prompt-based control is feasible. However, these methods typically rely on task descriptions, observation values, short textual feedback, or unstructured retrieval, which limits their ability to reason about zone coupling, thermal response, and building dynamics. This paper presents a thermodynamics-aware LLM control framework for a five-zone EnergyPlus building simulation. The controller is grounded in a physics-informed spatial knowledge graph derived from Brick-style building semantics and linked with recent interaction history. At each control step, the model receives the current building state, graph-structured spatial context, and recent environment-controller history, enabling it to make decisions that reflect both building structure and short-term thermal evolution. We evaluate the framework against standard control baselines and several LLM-based alternatives. Results show that the proposed approach achieves the best overall energy-comfort trade-off and the lowest PMV violation while maintaining energy-efficient operation.

Deploying advanced HVAC (Heating, Ventilation and Air Conditioning) controllers at scale remains difficult because performance often depends on accurate building models or per-site retuning. We propose NOMAD-RL (Neural Online Meta-Adaptation for Dynamics), a general-purpose Reinforcement Learning (RL) controller designed to transfer across heterogeneous thermal zones through a universal, non-invasive thermostat interface. The controller acts on temperature setpoints from zone measurements and forecasts, while a recurrent policy supports online adaptation under partial observability. Our main contribution is an adaptive domain randomization scheme based on physics-informed normalizing flows, which models correlated and multimodal distributions of thermal-zone parameters while maintaining physical plausibility and controllability. This produces a realistic and progressively adaptive training curriculum that improves transfer across buildings. We evaluate NOMAD-RL against a constant-setpoint PID controller, RL without domain randomization, and MPC in single- and multi-zone settings. NOMAD-RL consistently outperforms the PID and non-randomized RL baselines, and approaches the performance of a well-tuned MPC, especially in the more challenging multi-zone case. These results highlight the potential of adaptive, physics-informed domain randomization for robust and transferable HVAC control.

Multi-zone variable-air-volume control must balance thermal comfort, indoor air quality, and electricity use across several continuous actuators. Model predictive control and reinforcement learning are widely studied, but deployment typically requires building-specific modeling or training, limiting scalability. We first test whether a frontier reasoning model (an LLM trained to use additional inference-time computation) can achieve competitive VAV control from text without building-specific training. With that capability established, we then test whether TD3-guided reinforcement fine-tuning (RFT) can transfer control knowledge into a locally deployable open-weight model. Five controllers are evaluated over three summer days in a physics-based four-zone emulator. Relative to a Guideline 36-based baseline, TD3 reduced HVAC electricity by 4.5% while improving temperature and CO$_2$ compliance. Without building-specific training, GPT-5 achieved the largest reduction (6.2%) but reduced the ventilation margin. For RFT, deterministic rollouts restore a saved state, apply one candidate, and follow TD3 to score each action. Auditing a learned critic against these rollouts exposed a failure hidden by its near-perfect across-time correlation ($r=0.9998$): within-state ranking was unreliable; the critic selected the rollout-best candidate in only 5 of 10 states. Even with the rollout verifier, 200 RFT steps produced no sustained improvement in sampled-action return; the open-weight controller used more electricity than the baseline before and after training, and its five-minute predictions remained worse than persistence. GPT-5 predicted transitions far better. Exact rollout scores rank sampled actions but reveal neither next-state effects nor an improvement direction. The unchanged transition errors motivate transition-focused supervised fine-tuning before value-based RFT.