Managing Uncertainty in LLM-Generated Procedural Knowledge for Virtual Laboratory Planning

2026-05-25

AI Summary

This work addresses the challenge that experimental protocols generated by large language models (LLMs) often suffer from missing steps, incorrect sequencing, or logical inconsistencies, rendering them unsuitable for direct execution in virtual laboratories. To bridge this gap, the paper proposes a novel framework that systematically transforms the inherently uncertain procedural knowledge produced by LLMs into explicit, verifiable, and repairable constraints. The approach leverages structured domain representations and state-transition sampling to extract candidate procedural rules, which are then refined through constraint-based reasoning to correct unreliable steps. Evaluated in a virtual experimental environment involving instruments, containers, and material transfer operations, the method substantially reduces procedural uncertainty and yields more accurate, executable, and interpretable experimental plans.

Abstract

Educational virtual laboratories can make experimental training more scala-ble, adaptive, and accessible, especially when students have limited access to physical laboratory facilities. However, authoring new simulated laboratory procedures remains costly: educators must describe new equipment, define how instruments and materials interact, and specify valid procedural flows that can be executed or assessed inside the virtual environment. Large lan-guage models can assist in this authoring process by generating detailed ex-perimental procedures, but their output should not be treated as directly exe-cutable plans. They may omit necessary actions, arrange steps in the wrong order, or produce instructions that are logically incorrect or incompatible with the laboratory equipment. This paper presents a prototype framework for managing uncertainty in LLM-generated procedural knowledge for virtu-al laboratory planning. The framework aims to reduce procedural uncertainty by using structured domain representations and uncertain LLM-generated state-transition samples to extract candidate procedural rules, transform them into explicit and inspectable constraints, and use them to repair uncertain procedural steps. Although the motivating domain refers to educational vir-tual laboratories, the underlying problem is more general: managing uncer-tain procedural knowledge for action planning in structured interactive envi-ronments. We illustrate the approach in a virtual laboratory domain involving laboratory instruments, containers, tools, and material-transfer actions.

Problem

• uncertainty management
• procedural knowledge
• large language models
• virtual laboratories
• action planning

Innovation

• procedural knowledge
• uncertainty management
• large language models
• virtual laboratories
• constraint-based planning