BatteryLake: Agentic, Physics-Grounded Curation of Heterogeneous Battery Aging Data and Benchmarking
Quick Answer
BatteryLake introduces a physics-grounded curation framework for battery aging data, enabling the transformation of raw datasets into benchmark-ready assets.
Quick Take
It features agents for metadata extraction, a human-in-the-loop verification process, and an open benchmark of 41 datasets with standardized tasks from over 25 institutions, enhancing reproducibility and usability in battery health management.
Key Points
- BatteryLake curates battery aging data into benchmark-ready formats using LLM agents.
- Human-in-the-loop verification applies 26 schema and plausibility rules for data admission.
- Open benchmark includes 41 datasets with standardized SOH and RUL tasks.
- Framework addresses inconsistencies in public battery aging datasets for better usability.
- Publicly available resources enhance reproducibility in battery health management research.
Paper Resources
📖 Reader Mode
~2 min readAbstract:Public battery aging datasets are a critical asset for advanced health management, but their practical use is often limited by inconsistent formats, unclear schemas, and metadata scattered across repositories and publications. Current curation remains largely manual and hard to reproduce, while general-purpose data integration tools miss the domain-specific semantics of electrochemical time-series data. We present BatteryLake, a governed data lakehouse that turns raw public battery data into benchmark-ready assets through an agentic, physics-grounded curation framework, with three contributions. First, LLM agents extract metadata and synthesize dataset-specific converters, grounding every output in verbatim evidence and abstaining when none supports a value. Second, a human-in-the-loop mechanism frames verification as selective prediction and gates admitted data through 26 schema, statistical, and physical-plausibility rules. Third, we release an open benchmark of 41 datasets from over 25 institutions, with standardized SOH and RUL tasks, three split protocols, and eight baseline model families. The platform, benchmark, and curation protocol are publicly available at this https URL.
| Comments: | The platform, benchmark, and curation protocol are publicly available at this https URL |
| Subjects: | Artificial Intelligence (cs.AI); Databases (cs.DB) |
| Cite as: | arXiv:2607.09762 [cs.AI] |
| (or arXiv:2607.09762v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2607.09762 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Tianwen Zhu [view email]
[v1]
Mon, 6 Jul 2026 16:49:19 UTC (2,772 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →HOBA: Hierarchical On-Policy Bidding Agents for Adaptive Online Advertising
HOBA (Hierarchical On-policy Bidding Agents) is a novel hierarchical reinforcement learning framework that enhances online advertising bidding systems by improving adaptability and reducing hyperparameter tuning costs. It utilizes a for hyperparameter inference, a SARSA agent for expert model selection, and a dynamic expert pool for bid execution, achieving a +3.6% increase in target cost during large-scale deployment and outperforming state-of-the-art baselines on AuctionNet.