BioProAgent: Neuro-Symbolic Grounding for Constrained Scientific Planning

ACL ARR 2026 January Submission970 Authors

Keywords: Neuro-Symbolic Reasoning; Procedural Language Grounding; Scientific Automation

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 ~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. Our code is available at: https://anonymous.4open.science/r/Bioproagent-C3DC2159 .

Paper Type: Long

Research Area: AI/LLM Agents

Research Area Keywords: Agents, Neuro-symbolic methods, Robotics, Science and Medical applications, Safety

Contribution Types: NLP engineering experiment, Data resources

Languages Studied: English

Submission Number: 970