# WattCouncil: Context-Aware Household Energy Scenario Generation With Governed LLMs

arXiv: https://arxiv.org/abs/2607.10720 · HTML: https://mlsanity.com/paper/2607.10720/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 43 references that are in the map.
- First posted on arXiv 12 Jul 2026.

## Builds on (most cited first, 8 of 8)

- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Large Language Models for Data Annotation and Synthesis: A Survey](https://mlsanity.com/paper/2402.13446/) (2024)
- [Efficient Dynamic Ensembling for Multiple LLM Experts](https://mlsanity.com/paper/2412.07448/) (2024)
- [A Strategic Coordination Framework of Small LLMs Matches Large LLMs in Data Synthesis](https://mlsanity.com/paper/2504.12322/) (2025)
- [Knowledge Distillation from Large Language Models for Household Energy Modeling](https://mlsanity.com/paper/2502.03034/) (2025)
- [Reshaping Smart Energy Transition: An analysis of human-building interactions in Qatar Using Machine Learning Techniques](https://mlsanity.com/paper/2111.08333/) (2021)
- [Characterizing Residential Load Patterns by Household Demographic and Socioeconomic Factors](https://mlsanity.com/paper/2106.05858/) (2021)
- [Supporting Energy Policy Research with Large Language Models](https://mlsanity.com/paper/2403.12924/) (2024)

## Abstract (arXiv)

The accelerating shift toward low-carbon power systems, together with the widespread adoption of behind-the-meter technologies such as rooftop solar and electric vehicles, is placing new operational and analytical demands on electricity grids. At the same time, smart-grid research increasingly relies on machine learning (ML), yet progress is constrained by limited access to high-resolution household energy data due to privacy concerns, regulatory barriers, and collection costs. This work presents WattCouncil, a data-generation framework in which household electricity demand is generated by a council of Large Language Model (LLM)-based agents operating in specialized roles to generate, audit, and validate structured energy scenarios under explicit cultural, temporal, and physical constraints. Rather than acting as static predictors, these agents serve as adaptive decision-makers within a governed pipeline. Motivated by studies highlighting the importance of contextual factors in energy use, our framework produces context-sensitive daily routines through a guided reasoning process that incorporates household composition, temporal factors, and environmental conditions. We evaluate the generated profiles against the detailed CER dataset, which contains over a year of load measurements for 4232 households together with survey-based socio-economic information. We further assess the consistency of the framework through ablation studies. Source code is available at https://github.com/Singularity-AI-Lab/wattcouncil