Large language models (LLMs) have demonstrated significant reasoning capabilities in scientific discovery but struggle to bridge the gap to physical execution in wet-labs. In these irreversible environments, probabilistic hallucinations are not merely incorrect, but also cause equipment damage or experimental failure. To address this, we propose \textbf{BioProAgent}, a neuro-symbolic framework that anchors probabilistic planning in a deterministic Finite State Machine (FSM). We introduce a State-Augmented Planning mechanism that enforces a rigorous \textit{Design-Verify-Rectify} workflow, ensuring hardware compliance before execution. Furthermore, we address the context bottleneck inherent in complex device schemas by \textit{Semantic Symbol Grounding}, reducing token consumption by $\sim$6$\times$ through symbolic abstraction. In the extended BioProBench benchmark, BioProAgent achieves 95.6\% physical compliance (compared to 21.0\% for ReAct), demonstrating that neuro-symbolic constraints are essential for reliable autonomy in irreversible physical environments. \footnote{Code at https://github.com/YuyangSunshine/bioproagent and project at https://yuyangsunshine.github.io/BioPro-Project/}

翻译：大型语言模型（LLM）在科学发现中展现出显著的推理能力，但在连接湿实验室物理执行层面仍存在困难。在这些不可逆的实验环境中，概率性幻觉不仅会导致错误，还可能引发设备损坏或实验失败。为此，我们提出\textbf{BioProAgent}——一种神经符号框架，通过确定性有限状态机（FSM）对概率性规划进行锚定。我们引入状态增强规划机制，强制执行严格的\textit{设计-验证-修正}工作流程，确保在操作前满足硬件合规性。此外，针对复杂设备架构中固有的上下文瓶颈问题，我们通过\textit{语义符号基础化}方法，借助符号抽象将令牌消耗降低约$6$倍。在扩展的BioProBench基准测试中，BioProAgent实现了95.6\%的物理合规率（相较于ReAct的21.0\%），证明神经符号约束对于不可逆物理环境中的可靠自主操作至关重要。\footnote{代码仓库：https://github.com/YuyangSunshine/bioproagent，项目主页：https://yuyangsunshine.github.io/BioPro-Project/}