Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

BioProAgent: Neuro-Symbolic Grounding for Constrained Scientific Planning

Yuyang Liu, Jingya Wang, Liuzhenghao Lv, Yonghong Tian

TL;DR

A neuro-symbolic framework that anchors probabilistic planning in a deterministic Finite State Machine (FSM), and a State-Augmented Planning mechanism that enforces a rigorous Design-Verify-Rectify workflow, ensuring hardware compliance before execution.

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/}

BioProAgent: Neuro-Symbolic Grounding for Constrained Scientific Planning

TL;DR

A neuro-symbolic framework that anchors probabilistic planning in a deterministic Finite State Machine (FSM), and a State-Augmented Planning mechanism that enforces a rigorous Design-Verify-Rectify workflow, ensuring hardware compliance before execution.

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 6 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/}
Paper Structure (33 sections, 6 equations, 5 figures, 6 tables, 1 algorithm)

This paper contains 33 sections, 6 equations, 5 figures, 6 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Related Works
  3. LLM Agents for Scientific Discovery
  4. Neuro-Symbolic Reasoning & Action
  5. Long-Horizon Context Management
  6. Methodology
  7. Hybrid Cognitive Memory Architecture
  8. Structured Working Memory $\mathcal{M}_{work}$.
  9. Episodic and Long-term Memory.
  10. State-Augmented Neuro-Symbolic Plan
  11. Neuro-Symbolic Control Engine
  12. Neural Reasoning Policy
  13. Hierarchical Verification Framework
  14. Layer 1: Neuro-Scientific Verification ($\mathcal{K}_s$).
  15. Layer 2: Symbolic-Physical Verification ($\mathcal{K}_{p}$).
  16. ...and 18 more sections

Figures (5)

  • Figure 1: Scientific Reasoning vs. Automation Executability. Vanilla LLMs occupy the Theoretical Zone (high logic, weak code), while Neural Agents (like ReAct) often generating better code but failing in scientific reasoning. BioProAgent achieves Trustworthy Autonomy with superior performance in both dimensions.
  • Figure 2: Overview of BioProAgent. (1) Cognitive Memory utilizes Symbolic Grounding $\Phi$ to manage context efficiently; (2) Neural Planner $\pi_\theta$ is grounded in a Design-Verify-Rectify FSM $\Delta(\sigma)$; (3) Hierarchical Verification ($\mathcal{K}_s, \mathcal{K}_p$) acts as a safety interlock, enforcing physical compliance by deterministically triggering rectification.
  • Figure 3: Efficiency and Reliability Analysis. (a) Multidimensional Capabilities: BioProAgent (red) achieves the most expansive capability envelope across five critical dimensions. Note that identical metrics on different axes represent performance in distinct evaluation subsets. (b) Cost-Efficiency: On long-horizon tasks (Subset C), our system reduces token consumption by 82% compared to AutoGPT while maintaining a 100% success rate. (c) Time-Efficiency: BioProAgent demonstrates superior precision with concise execution time.
  • Figure 4: FSM-Driven Self-Correction Trajectories. (a) Physical Correction. (b) Symbol Grounding Repair.
  • Figure 5: Trace Analysis (Subset C). Execution divergence on a long-horizon task. TOP: BioProAgent efficiently transitions to coding via FSM. MIDDLE: ReAct fails early due to context overflow. BOTTOM: AutoGPT wastes resources in a retrieval loop.