LabGuard: Grounding Natural-Language Laboratory Rules into Runtime Guards for Embodied Laboratory Agents

• URL: http://arxiv.org/abs/2606.31045v1
• Date: Tue, 30 Jun 2026 02:30:51 GMT
• Title: LabGuard: Grounding Natural-Language Laboratory Rules into Runtime Guards for Embodied Laboratory Agents
• Abstract summary: LabGuard is a language-to-execution safety suite that grounds natural-language laboratory rules into executable specifications and deploys them as runtime guards.<n>LabGuard includes three core components: LabGuard-IR, which defines a typed executable representation; LabGuard-Bench, which provides 812 supervised annotations expanded from 203 seed laboratory rules; and LabGuard-Grounder, which maps natural-language laboratory rules into LabGuard-IR.<n>Experiments show that LabGuard generalizes to unseen laboratory-rule sources, achieves 79.4 task-scope F1, and reduces unsafe events from 39.5% to 23.8% after monitor
• Score: 48.775530122251844
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Scientific embodied agents are increasingly capable of carrying out laboratory procedures, but executing these procedures safely in dynamic laboratory environments remains challenging. Current safety approaches often overlook the intermediate step of transforming laboratory natural language, including safety rules, manuals, protocols, and standard operating procedures, into machine-checkable runtime constraints. We introduce LabGuard (Laboratory Guard), a language-to-execution safety suite that grounds natural-language laboratory rules into executable specifications and deploys them as runtime guards. LabGuard includes three core components: LabGuard-IR, which defines a typed executable representation; LabGuard-Bench, which provides 812 supervised annotations expanded from 203 seed laboratory rules; and LabGuard-Grounder, which maps natural-language laboratory rules into LabGuard-IR. The resulting IR instances are handled by the LabGuard Pipeline, which compiles them into runtime monitors and applies them at the controller boundary. Experiments show that LabGuard generalizes to unseen laboratory-rule sources, achieves 79.4 task-scope F1, and reduces unsafe events from 39.5% to 23.8% after monitor compilation. In LabUtopia, its runtime monitors integrate with ACT, keeping interventions below 0.5% while preserving task success.

Related papers

• LabRobFail: A Benchmark for Robotic Failure Analysis in Chemical Self-driving Laboratory [52.26893354670174]
  We introduce LabRobFail, a failure-centric framework for learning and evaluating robotic failure analysis in chemical laboratories.<n>LabRobFail-Sim injects controllable failures at the control, physics, and semantic levels.<n>LabRobFail-Bench evaluates six capabilities spanning task understanding, failure detection, temporal localization, severity assessment, failure classification, and actionable correction.
  arXiv  Detail & Related papers  (2026-07-26T14:56:04Z)
• LabVLA: Grounding Vision-Language-Action Models in Scientific Laboratories [95.20367571157679]
  Vision-Language-Action (VLA) models provide one possible interface between written protocols and robot execution.<n>Existing policies are trained mostly on household and tabletop demonstrations and rarely encounter the instruments, transparent liquids, or fixed protocol found in scientific laboratories.<n>We present LabVLA, trained with a two-stage recipe: FAST action token pretraining first makes the Qwen3-VL-4B-Instruct backbone action aware before any continuous control is learned, and flow matching posttraining then attaches a DiT action expert under knowledge insulation.
  arXiv  Detail & Related papers  (2026-06-11T17:03:53Z)
• Managing Uncertainty in LLM-Generated Procedural Knowledge for Virtual Laboratory Planning [0.0]
  This paper presents a prototype framework for managing uncertainty in LLM-generated procedural knowledge for virtu-al laboratory planning.<n>The framework aims to reduce procedural uncertainty by using structured domain representations and uncertain LLM-generated state-transition samples.<n>We illustrate the approach in a virtual laboratory domain involving laboratory instruments, containers, tools, and material-transfer actions.
  arXiv  Detail & Related papers  (2026-05-25T21:12:47Z)
• LabBuilder: Protocol-Grounded 3D Layout Generation for Interactable and Safe Laboratory [93.63620478256063]
  We present LabBuilder, an end-to-end system that generates and verifies 3D laboratory layouts from concise textual specifications.<n>LabBuilder significantly outperforms existing state-of-the-art methods.
  arXiv  Detail & Related papers  (2026-05-04T07:24:56Z)
• Pre-Execution Safety Gate & Task Safety Contracts for LLM-Controlled Robot Systems [14.419994656981002]
  We introduce SafeGate, a neurosymbolic safety architecture that prevents unsafe natural language task commands from reaching robot execution.<n>In addition, we introduce Task Safety Contracts, which decomposes commands that pass through the gate into invariants, guards, and abort conditions.<n>Results show that SafeGate significantly reduces the acceptance of defective commands while maintaining a high acceptance of benign tasks.
  arXiv  Detail & Related papers  (2026-04-07T04:46:06Z)
• LabUtopia: High-Fidelity Simulation and Hierarchical Benchmark for Scientific Embodied Agents [103.65422553044816]
  LabUtopia is a comprehensive simulation and benchmarking suite designed to facilitate the development of generalizable, reasoning-capable embodied agents.<n>It supports 30 distinct tasks and includes more than 200 scene and instrument assets.<n>We demonstrate that LabUtopia offers a powerful platform for advancing the integration of perception, planning, and control in scientific-purpose agents.
  arXiv  Detail & Related papers  (2025-05-28T17:50:53Z)
• LabSafety Bench: Benchmarking LLMs on Safety Issues in Scientific Labs [78.99703366417661]
  Large language models (LLMs) increasingly assist in tasks ranging from procedural guidance to autonomous experiment orchestration.<n>Such overreliance is particularly dangerous in high-stakes laboratory settings, where failures in hazard identification or risk assessment can result in severe accidents.<n>We propose the Laboratory Safety Benchmark (LabSafety Bench) to evaluate models on their ability to identify potential hazards, assess risks, and predict the consequences of unsafe actions in lab environments.
  arXiv  Detail & Related papers  (2024-10-18T05:21:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.