Battery-Sim-Agent: Leveraging LLM-Agent for Inverse Battery Parameter Estimation

2026-05-28

AI Summary

This work addresses the low sample efficiency and neglect of physical mechanisms in inverse parameter estimation for high-fidelity battery digital twins. To overcome these limitations, the task is reframed as a reasoning problem, and the first large language model (LLM) agent capable of closed-loop interaction with a high-fidelity battery simulator is introduced. The agent emulates a scientist’s workflow by interpreting multimodal simulation feedback, generating physically grounded hypotheses, and iteratively refining parameters in a structured manner to enable physics-informed autonomous optimization. Evaluated across diverse battery chemistries and operating conditions, the proposed approach significantly outperforms strong baselines such as Bayesian optimization. It further demonstrates practical efficacy in long-term aging curve fitting and validation against real-world battery data, thereby transcending conventional black-box optimization paradigms.

Abstract

Parameterizing high-fidelity "digital twins" of batteries is a critical yet challenging inverse problem that hinders the pace of battery innovation. Prevailing methods formulate this as a black-box optimization (BBO) task, employing algorithms that are sample-inefficient and blind to the underlying physics. In this work, we introduce a new paradigm that reframes the inverse problem as a reasoning task, and present Battery-Sim-Agent, the first framework to deploy a Large Language Model (LLM) agent in a closed loop with a high-fidelity battery simulator. The agent mimics a human scientist's workflow: it interprets rich, multi-modal feedback from the simulator, forms physically-grounded hypotheses to explain discrepancies, and proposes structured parameter updates. On a systematically constructed benchmark suite spanning diverse battery chemistries, operating conditions, and difficulty levels, our agent significantly outperforms strong BBO baselines like Bayesian optimization in identifying accurate parameters. We further demonstrate the framework's capability in complex long-horizon degradation fitting tasks and validate its practical applicability on real-world battery datasets. Our results highlight the promise of LLM-agents as reasoning-based optimizers for scientific discovery and battery parameter estimation.

Problem

• inverse problem
• battery parameter estimation
• digital twins
• battery modeling
• parameterization

Innovation

• LLM-agent
• inverse parameter estimation
• battery digital twin
• physics-informed reasoning
• closed-loop simulation