一句话：提出多制品版本化框架，用专用注册表与元数据描述符统一管理 LLM Agent 软件中的模型、数据、提示与行为。
传统版本控制面向源代码更新，难以刻画 LLM、提示、训练数据与 agent 行为持续演化的状态。本文提出多制品方法：将传统代码仓库与模型权重、数据集、提示模板的专用注册表结合，并由富元数据描述符关联。通过类比经典计算层次与真实场景，分析非确定性输出、分层依赖和用户期望变化等挑战。框架支持高风险场景下的严格模式以保障可复现性，也支持流体模式允许低风险迭代改进。目标是统一技术、组织与用户维度的版本策略和工具，促进更稳健、透明且符合伦理的 LLM-agent 系统持续演进。
Large Language Models (LLMs) are redefining software practices by introducing agents that adapt rapidly to new data, tasks, and contexts. Conventional version control, optimized for source code updates, struggles to capture the evolving states of LLMs, prompts, training data, and agent behaviors. This paper proposes a multi-artifact approach that marries traditional code repositories with specialized registries for model weights, datasets, and prompt templates, tied together by metadata-rich descriptors. Through analogies to familiar computing layers and real-world scenarios, we illuminate the challenges of non-deterministic outputs, layered dependencies, and shifting user expectations. Our framework supports both "strict modes" for reproducibility in high-stakes contexts and "fluid modes" allowing iterative improvements with lower risk. By unifying versioning policies and tools across technical, organizational, and user-centric dimensions, we aim to foster more robust, transparent, and ethically informed LLM-agent systems that can reliably evolve alongside their expanding capabilities.