# Grounded, Compute-Efficient LLM Policy Agents for Energy-Poverty Equity in Physically-Constrained Peer-to-Peer Energy Markets

arXiv: https://arxiv.org/abs/2609.01918 · HTML: https://mlsanity.com/paper/2609.01918/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Financial trading and forecasting agents, one of 16 directions in LLM agents and tool use.
- Builds on 10 of its 20 references that are in the map.
- First posted on arXiv 1 Sep 2026.

## Placed in

- LLM agents and tool use / [Financial trading and forecasting agents](https://mlsanity.com/agents/financial-trading-and-forecasting-agents/)

## Builds on (most cited first, 10 of 10)

- [EconAgent: Large Language Model-Empowered Agents for Simulating Macroeconomic Activities](https://mlsanity.com/paper/2310.10436/) (2023)
- [How Hungry is AI? Benchmarking Energy, Water, and Carbon Footprint of LLM Inference](https://mlsanity.com/paper/2505.09598/) (2025)
- [LLM Economist: Large Population Models and Mechanism Design in Multi-Agent Generative Simulacra](https://mlsanity.com/paper/2507.15815/) (2025)
- [WeQA: A Benchmark for Retrieval Augmented Generation in Wind Energy Domain](https://mlsanity.com/paper/2408.11800/) (2024)
- [NLP for Social Good: A Survey and Outlook of Challenges, Opportunities, and Responsible Deployment](https://mlsanity.com/paper/2505.22327/) (2025)
- [LLM-Enhanced Multi-Agent Reinforcement Learning with Expert Workflow for Real-Time P2P Energy Trading](https://mlsanity.com/paper/2507.14995/) (2025)
- [Dynamic Operating Envelopes Embedded Peer-to-Peer-to-Grid Energy Trading](https://mlsanity.com/paper/2311.13832/) (2023)
- [An Explainable Equity-Aware P2P Energy Trading Framework for Socio-Economically Diverse Microgrid](https://mlsanity.com/paper/2507.18738/) (2025)
- [Scalable Fairness Shaping with LLM-Guided Multi-Agent Reinforcement Learning for Peer-to-Peer Electricity Markets](https://mlsanity.com/paper/2508.18610/) (2025)
- [Good Intentions Beyond ACL: Who Does NLP for Social Good, and Where?](https://mlsanity.com/paper/2510.04434/) (2025)

## Abstract (arXiv)

Energy poverty is nearly absent from NLP-for-social-good, and the little existing work is either static retrieval/QA or relies on carbon-intensive cloud LLMs, a self-defeating "computational irony" for a humanitarian setting. We present EqGrid, a closed-loop simulation in which a low-frequency, open-weight LLM policy agent sets price and carbon bounds and targeted subsidies over a community of empirically-grounded household personas, while high-frequency multi-agent RL traders clear a continuous double auction constrained by a physical distribution grid (IEEE-33-bus with Dynamic Operating Envelopes). Our contribution is threefold and directly addresses how to measure the social impact of AI: (i) grounded personas (region-matched socio-demographics) whose load curves are checked for shape and level realism against real smart-meter data; (ii) formal energy-poverty equity metrics (Energy Burden, Gini of EB, LIHC) showing the intervention reduces burden inequality without raising net grid cost; and (iii) a compute-efficiency frontier that measures how much equity performance survives compressing the policy agent from a 235B teacher down to a sub-1B model deployable on a laptop, in estimated energy/carbon per decision. A decoupled-safety design (the LLM sets bounds; a validate-and-project grid gate executes) yields zero grid-constraint violations versus 55 under direct LLM control. On energy-poverty equity, the LLM policy lowers the Gini of energy burden to 0.305 (from 0.351) and mean burden by 28% while cutting cost (outperforming a tuned rule baseline), and a 3B-active model retains 95% of the benefit at roughly 9x lower inference energy than the teacher, with even a 0.8B on-device model retaining 92% at roughly 24x lower energy. We will release code and configs.