# Enhancing LLMs for Power System Simulations: A Feedback-driven Multi-agent Framework arXiv: https://arxiv.org/abs/2411.16707 ยท HTML: https://mlsanity.com/paper/2411.16707/ ## Key facts - Cited by 17 papers in the map (data through 14 Oct 2026). - Placed in Financial trading and forecasting agents, one of 16 directions in LLM agents and tool use. - Builds on 15 of its 34 references that are in the map. - First posted on arXiv 21 Nov 2024. ## 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, 15 of 15) - [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020) - [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022) - [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020) - [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021) - [From News to Forecast: Integrating Event Analysis in LLM-Based Time Series Forecasting with Reflection](https://mlsanity.com/paper/2409.17515/) (2024) - [How Do Large Language Models Acquire Factual Knowledge During Pretraining?](https://mlsanity.com/paper/2406.11813/) (2024) - [Exploring the Capabilities and Limitations of Large Language Models in the Electric Energy Sector](https://mlsanity.com/paper/2403.09125/) (2024) - [Large Language Models Streamline Automated Machine Learning for Clinical Studies](https://mlsanity.com/paper/2308.14120/) (2023) - [Large Foundation Models for Power Systems](https://mlsanity.com/paper/2312.07044/) (2023) - [ChatGPT and Other Large Language Models for Cybersecurity of Smart Grid Applications](https://mlsanity.com/paper/2311.05462/) (2023) - [ElecBench: a Power Dispatch Evaluation Benchmark for Large Language Models](https://mlsanity.com/paper/2407.05365/) (2024) - [Applying Large Language Models to Power Systems: Potential Security Threats](https://mlsanity.com/paper/2311.13361/) (2023) - [Enabling Large Language Models to Perform Power System Simulations with Previously Unseen Tools: A Case of Daline](https://mlsanity.com/paper/2406.17215/) (2024) - [Carbon Footprint Accounting Driven by Large Language Models and Retrieval-augmented Generation](https://mlsanity.com/paper/2408.09713/) (2024) - [Large Language Model Assisted Optimal Bidding of BESS in FCAS Market: An AI-agent based Approach](https://mlsanity.com/paper/2406.00974/) (2024) ## Built on by (most cited first, 17 of 17) - [X-GridAgent: An LLM-Powered Agentic AI System for Assisting Power Grid Analysis](https://mlsanity.com/paper/2512.20789/) (2025) - [Large Language Model Powered Automated Modeling and Optimization of Active Distribution Network Dispatch Problems](https://mlsanity.com/paper/2507.21162/) (2025) - [PowerChain: A Verifiable Agentic AI System for Automating Distribution Grid Analyses](https://mlsanity.com/paper/2508.17094/) (2025) - [Competition and Cooperation of LLM Agents in Games](https://mlsanity.com/paper/2604.00487/) (2026) - [Large Language Model-Empowered Interactive Load Forecasting](https://mlsanity.com/paper/2505.16577/) (2025) - [LLM-Enhanced Multi-Agent Reinforcement Learning with Expert Workflow for Real-Time P2P Energy Trading](https://mlsanity.com/paper/2507.14995/) (2025) - [Two-Stage Active Distribution Network Voltage Control via LLM-RL Collaboration: A Hybrid Knowledge-Data-Driven Approach](https://mlsanity.com/paper/2602.21715/) (2026) - [Foundation-Model-Based Agents in Industrial Automation: Purposes, Capabilities, and Open Challenges](https://mlsanity.com/paper/2605.02592/) (2026) - [Knowledge boundary probing and demand-guided intervention for LLM-based power system code generation](https://mlsanity.com/paper/2605.31478/) (2026) - [Large Language Model as An Operator: An Experience-Driven Solution for Distribution Network Voltage Control](https://mlsanity.com/paper/2507.14800/) (2025) - [One Request, Multiple Experts: LLM Orchestrates Domain Specific Models via Adaptive Task Routing](https://mlsanity.com/paper/2511.12484/) (2025) - [A Few-Shot LLM Framework for Extreme Day Classification in Electricity Markets](https://mlsanity.com/paper/2602.16735/) (2026) - [Grid-Orch: An LLM-Powered Orchestrator for Distribution Grid Simulation and Analytics](https://mlsanity.com/paper/2605.12728/) (2026) - [Agri-SAGE: Simulation-Grounded Multi-Agent LLM for Context-Aware Agricultural Advisory Generation](https://mlsanity.com/paper/2607.00454/) (2026) - [LLMs and Agentic AI Systems for Smart Grids: A Tutorial on Architectures and Applications](https://mlsanity.com/paper/2607.18147/) (2026) - [Engineering Trustworthy Agentic AI for Critical Systems](https://mlsanity.com/paper/2607.18548/) (2026) - [Training Numerical Intelligence via Auto-Diagnosis and Skill Discovery](https://mlsanity.com/paper/2610.03872/) (2026) ## Abstract (arXiv) The integration of experimental technologies with large language models (LLMs) is transforming scientific research. It positions AI as a versatile research assistant rather than a mere problem-solving tool. In the field of power systems, however, managing simulations -- one of the essential experimental technologies -- remains a challenge for LLMs due to their limited domain-specific knowledge, restricted reasoning capabilities, and imprecise handling of simulation parameters. To address these limitations, this paper proposes a feedback-driven, multi-agent framework. It incorporates three proposed modules: an enhanced retrieval-augmented generation (RAG) module, an improved reasoning module, and a dynamic environmental acting module with an error-feedback mechanism. Validated on 69 diverse tasks from Daline and MATPOWER, this framework achieves success rates of 93.13% and 96.85%, respectively. It significantly outperforms ChatGPT 4o, o1-preview, and the fine-tuned GPT-4o, which all achieved a success rate lower than 30% on complex tasks. Additionally, the proposed framework also supports rapid, cost-effective task execution, completing each simulation in approximately 30 seconds at an average cost of 0.014 USD for tokens. Overall, this adaptable framework lays a foundation for developing intelligent LLM-based assistants for human researchers, facilitating power system research and beyond.