AgentCount: An Agentic Workflow for Traceable Colony Counting and Insight Generation from Agar Plate Images
Abstract
Colony counting is commonly used to evaluate microbial populations in food safety testing and microbiological studies. Despite its wide application, manual counting is time-consuming and operator-dependent, and the final count often lacks a record of the objects included in the measurement. To address these limitations, this study presents AgentCount, an open-source agentic workflow for colony counting and result interpretation from agar plate images. Plate photographs and plating metadata are processed through seven agents for image quality control, plate localisation, colony detection, counting, CFU calculation, validation, and reporting. Colony detection is performed using Segment Anything Model 3 (SAM 3) with multiple text prompts and morphology-based filtering. After that, replicate statistics are calculated and a large language model (LLM)-based agent is used to generate a results narrative. Intermediate outputs, including quality scores, segmentation masks, detections, and warnings, are retained to support review of the reported values. The workflow also extends to skill-guided analysis of archived microbial population data. In a retrospective comparison with two previously published studies, we benchmarked 241 published endpoints, including all 216 mean +- SD values of the meat-analogue pathogen tables; on the 168 endpoints with a complete n=6 replicate source, 164 (97.6%) agreed within 0.01 log10 units. Overall, AgentCount demonstrates the promising potential of agentic workflows for applications in applied microbiology.
Related
- From seven combination hypotheses to one testable interaction: a gated agentic AI QSP workflow applied to healthy ageing interventions
- HyARQ: a Snakemake workflow for allele-specific read counting and quality control in F1 hybrids
- The Findings Workflow: An agentic, collaborative, provenance-tracked framework for scientific data analysis with Claude Code
- TRACE: a framework for traceable biomedical resource construction demonstrated through single-cell glaucoma data
- Agentic transcranial functional ultrasound imaging: @fUS
BibTeX
@misc{liu2026agentcount,
title = {{AgentCount: An Agentic Workflow for Traceable Colony Counting and Insight Generation from Agar Plate Images}},
author = {Zhuosheng Liu and Austin E. Weber},
howpublished = {arXiv},
year = {2026},
month = nov,
doi = {10.48550/arxiv.2611.05398},
eprint = {2611.05398},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2611.05398},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - AgentCount: An Agentic Workflow for Traceable Colony Counting and Insight Generation from Agar Plate Images
AU - Zhuosheng Liu
AU - Austin E. Weber
PY - 2026
DA - 2026/11/01
PB - arXiv
DO - 10.48550/arxiv.2611.05398
UR - https://arxiv.org/abs/2611.05398
AB - Colony counting is commonly used to evaluate microbial populations in food safety testing and microbiological studies. Despite its wide application, manual counting is time-consuming and operator-dependent, and the final count often lacks a record of the objects included in the measurement. To address these limitations, this study presents AgentCount, an open-source agentic workflow for colony counting and result interpretation from agar plate images. Plate photographs and plating metadata are processed through seven agents for image quality control, plate localisation, colony detection, counting, CFU calculation, validation, and reporting. Colony detection is performed using Segment Anything Model 3 (SAM 3) with multiple text prompts and morphology-based filtering. After that, replicate statistics are calculated and a large language model (LLM)-based agent is used to generate a results narrative. Intermediate outputs, including quality scores, segmentation masks, detections, and warnings, are retained to support review of the reported values. The workflow also extends to skill-guided analysis of archived microbial population data. In a retrospective comparison with two previously published studies, we benchmarked 241 published endpoints, including all 216 mean +- SD values of the meat-analogue pathogen tables; on the 168 endpoints with a complete n=6 replicate source, 164 (97.6%) agreed within 0.01 log10 units. Overall, AgentCount demonstrates the promising potential of agentic workflows for applications in applied microbiology.
ER -