SciDER: Scientific Data-centric End-to-end Researcher

Ke Lin, Harry Lu, Shreyas Bhat, Xuehang Guo, Junier Oliva, Qingyun Wang

SciDER: Scientific Data-centric End-to-end Researcher: 5 upvotes on Hugging Face Daily Papers, #21 of 43 papers on 2026-03-04. Day-by-day upvote history.

Automated scientific discovery with large language models is transforming the research lifecycle from ideation to experimentation, yet existing agents struggle to autonomously process raw data collected from scientific experiments. We introduce SciDER, a data-centric end-to-end system that automates the research lifecycle. Unlike traditional frameworks, our specialized agents collaboratively parse and analyze raw scientific data, generate hypotheses and experimental designs grounded in specific data characteristics, and write and execute corresponding code. Evaluation on three benchmarks shows SciDER excels in specialized data-driven scientific discovery and outperforms general-purpose agents and state-of-the-art models through its self-evolving memory and critic-led feedback loop. Distributed as a modular Python package, we also provide easy-to-use PyPI packages with a lightweight web interface to accelerate autonomous, data-driven research and aim to be accessible to all researchers and developers.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.