SciDER: Scientific Data-centric End-to-end Researcher
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908996674256896 |
|---|---|
| author | Lin, Ke Lu, Yilin Bhat, Shreyas Guo, Xuehang Oliva, Junier Wang, Qingyun |
| author_facet | Lin, Ke Lu, Yilin Bhat, Shreyas Guo, Xuehang Oliva, Junier Wang, Qingyun |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_01421 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | SciDER: Scientific Data-centric End-to-end Researcher Lin, Ke Lu, Yilin Bhat, Shreyas Guo, Xuehang Oliva, Junier Wang, Qingyun Artificial Intelligence Computation and Language 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. |
| title | SciDER: Scientific Data-centric End-to-end Researcher |
| topic | Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2603.01421 |