Cellular image segmentation is essential for quantitative biology yet remains difficult due to heterogeneous modalities, morphological variability, and limited annotations. We present GenCellAgent, a training-free multi-agent framework that orchestrates specialist segmenters and generalist vision-language models via a planner-executor-evaluator loop (choose tool $\rightarrow$ run $\rightarrow$ quality-check) with long-term memory. The system (i) automatically routes images to the best tool, (ii) adapts on the fly using a few reference images when imaging conditions differ from what a tool expects, (iii) supports text-guided segmentation of organelles not covered by existing models, and (iv) commits expert edits to memory, enabling self-evolution and personalized workflows. Across four cell-segmentation benchmarks, this routing yields a 15.7\% mean accuracy gain over state-of-the-art baselines. On endoplasmic reticulum and mitochondria from new datasets, GenCellAgent improves average IoU by 37.6\% over specialist models. It also segments novel objects such as the Golgi apparatus via iterative text-guided refinement, with light human correction further boosting performance. Together, these capabilities provide a practical path to robust, adaptable cellular image segmentation without retraining, while reducing annotation burden and matching user preferences.

翻译：细胞图像分割对于定量生物学至关重要，但由于成像模态异质性、形态多样性以及标注数据有限，该任务仍具挑战性。本文提出GenCellAgent，一种免训练的多智能体框架，通过规划-执行-评估循环（选择工具→运行→质量检查）与长期记忆机制，协同调度专用分割器与通用视觉-语言模型。该系统具备以下功能：（i）自动将图像路由至最优工具；（ii）当成像条件与工具预期不符时，利用少量参考图像进行实时适配；（iii）支持对现有模型未覆盖的细胞器进行文本引导分割；（iv）将专家编辑操作存入记忆，实现自我演进与个性化工作流。在四个细胞分割基准测试中，该路由策略相比最先进的基线方法平均准确率提升15.7%。针对新数据集中的内质网与线粒体，GenCellAgent相较于专用模型将平均交并比提升37.6%。该系统还能通过迭代式文本引导优化分割高尔基体等新型目标，经轻度人工校正后可进一步提升性能。这些能力共同为无需重新训练、鲁棒且自适应的细胞图像分割提供了实用路径，同时减轻标注负担并适应用户偏好。