LabWeaver: reliable agentic data analysis grounded in laboratory knowled
- 1Division of Biostatistics, Department of Population Health Sciences, University of Utah
Abstract
Agentic systems powered by large language models are rapidly automating biological data analysis. However, their reliability remains questionable because they often overlook experimental context, such as disease domain and experimental protocol. Existing agentic systems organize context around individual users and projects, whereas research is organized around laboratories whose projects share experimental context. As a result, experimental context learned in one project remains unavailable to related projects. We introduce LabWeaver, an agentic data analysis framework with a laboratory-organized architecture of three tiers: laboratory, user and project. Further, LabWeaver distills experimental context into laboratory memory and skills, which are shared across users and projects after human-gated review. To isolate the contribution of experimental context, we analyzed a synovial sarcoma single-cell RNA-seq dataset in two sessions that differed only in whether laboratory memory and skills were available. The context-free session lost the fusion reporter at read alignment and misannotated the tumor cells. In contrast, the context-enabled session recovered reporter expression and resolved five fusion-anchored tumor cell states.
Related
- TIAgent: From Natural Language to Grounded Agentic Workflows for Computational Pathology
- TRACEDD: A Tool-grounded Reasoning and Agentic Coordination for Explainable Drug Design
- Determining Reliable Neural Targets for enhancing Motor Sequence Learning: A preparatory study for focal tDCS
- Integrating Narrow-Window DIA with AI-Powered Search Enables Deep and Reliable Functional Proteomics
- Physics-Grounded Simulation Enables Zero-Shot Molecular and Reaction Analysis in Scanning Tunneling Microscopy
BibTeX
@misc{li2026labweaver,
title = {{LabWeaver: reliable agentic data analysis grounded in laboratory knowled}},
author = {L. Li and G. Fort and J. Xu and A. C. Tan and B. Guo},
howpublished = {bioRxiv},
year = {2026},
month = oct,
doi = {10.64898/2026.10.28.762601},
url = {https://www.biorxiv.org/content/10.64898/2026.10.28.762601v1},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - LabWeaver: reliable agentic data analysis grounded in laboratory knowled
AU - L. Li
AU - G. Fort
AU - J. Xu
AU - A. C. Tan
AU - B. Guo
PY - 2026
DA - 2026/10/28
PB - bioRxiv
DO - 10.64898/2026.10.28.762601
UR - https://www.biorxiv.org/content/10.64898/2026.10.28.762601v1
AB - Agentic systems powered by large language models are rapidly automating biological data analysis. However, their reliability remains questionable because they often overlook experimental context, such as disease domain and experimental protocol. Existing agentic systems organize context around individual users and projects, whereas research is organized around laboratories whose projects share experimental context. As a result, experimental context learned in one project remains unavailable to related projects. We introduce LabWeaver, an agentic data analysis framework with a laboratory-organized architecture of three tiers: laboratory, user and project. Further, LabWeaver distills experimental context into laboratory memory and skills, which are shared across users and projects after human-gated review. To isolate the contribution of experimental context, we analyzed a synovial sarcoma single-cell RNA-seq dataset in two sessions that differed only in whether laboratory memory and skills were available. The context-free session lost the fusion reporter at read alignment and misannotated the tumor cells. In contrast, the context-enabled session recovered reporter expression and resolved five fusion-anchored tumor cell states.
ER -