BioProAgent: Neuro-Symbolic Grounding for Constrained Scientific Planning

Yuyang Liu, Jingya Wang, Liuzhenghao Lv, Yonghong Tian

Keywords: Agentic, Neuro-Symbolic, Agent System

Abstract:

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, and cause equipment damage or experimental failure. To address this, we propose **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 *Design-Verify-Rectify* workflow, ensuring hardware compliance before execution. Furthermore, we address the context bottleneck inherent in complex device schemas by Semantic Symbol Grounding, reducing token consumption by ~6X 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{\url{https://anonymous.4open.science/r/Bioproagent-C3DC2159}}

Submission Number: 89