LabGuard: Grounding Natural-Language Laboratory Rules into Runtime Guards for Embodied Laboratory Agents
Quick Answer
LabGuard introduces a safety suite that translates natural-language laboratory rules into executable specifications, reducing unsafe events from 39.5% to 23.8%.
Quick Take
With a task-scope F1 score of 79.4, it effectively integrates runtime monitors in dynamic lab environments, maintaining intervention rates below 0.5%.
Key Points
- LabGuard consists of LabGuard-IR, LabGuard-Bench, and LabGuard-Grounder.
- The system uses 812 supervised annotations derived from 203 seed laboratory rules.
- LabGuard generalizes to unseen laboratory-rule sources, enhancing safety.
- Runtime monitors are deployed at the controller boundary to ensure compliance.
- Experiments show significant reduction in unsafe events post-monitor compilation.
Paper Resources
📖 Reader Mode
~2 min readAuthors:Jingpu Yang, Fengxian Ji, Zhengzhao Lai, Zhexuan Cui, Guangxian Ouyang, Qian Jiang, Fan Zhang, Min Peng, Qianqian Xie, Preslav Nakov, Zhuohan Xie
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.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2606.31045 [cs.AI] |
| (or arXiv:2606.31045v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2606.31045 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Fengxian Ji [view email]
[v1]
Tue, 30 Jun 2026 02:30:51 UTC (2,213 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →HOBA: Hierarchical On-Policy Bidding Agents for Adaptive Online Advertising
HOBA (Hierarchical On-policy Bidding Agents) is a novel hierarchical reinforcement learning framework that enhances online advertising bidding systems by improving adaptability and reducing hyperparameter tuning costs. It utilizes a for hyperparameter inference, a SARSA agent for expert model selection, and a dynamic expert pool for bid execution, achieving a +3.6% increase in target cost during large-scale deployment and outperforming state-of-the-art baselines on AuctionNet.