BioProAgent: Neuro-Symbolic Grounding for Constrained Scientific Planning

2026-02-28

AI Summary

This work addresses the critical risk of hallucination-induced hardware damage or experimental failure when deploying large language models in irreversible physical environments such as wet laboratories. To mitigate this, the authors propose BioProAgent, a neuro-symbolic framework that anchors probabilistic planning with a deterministic finite-state machine, integrating state-augmented planning and semantic symbolic grounding to ensure hardware compliance while substantially reducing context length requirements. The approach employs a design–verify–revise workflow to guarantee execution safety. Evaluated on the BioProBench benchmark, BioProAgent achieves a 95.6% physical compliance rate—significantly outperforming ReAct’s 21.0%—and reduces token consumption by approximately sixfold.

Technology Category

• Natural Language Processing: Safety and Robustness
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Multiagent Systems: Multiagent Planning

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Agentic search
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

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, 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/}

Problem

• scientific planning
• physical execution
• irreversible environments
• probabilistic hallucinations
• wet-lab automation

Innovation

• Neuro-Symbolic AI
• Finite State Machine
• Semantic Symbol Grounding
• Constrained Scientific Planning
• Physical Compliance