Academic

When OpenClaw Meets Hospital: Toward an Agentic Operating System for Dynamic Clinical Workflows

arXiv:2603.11721v1 Announce Type: new Abstract: Large language model (LLM) agents extend conventional generative models by integrating reasoning, tool invocation, and persistent memory. Recent studies suggest that such agents may significantly improve clinical workflows by automating documentation, coordinating care processes, and assisting medical decision making. However, despite rapid progress, deploying autonomous agents in healthcare environments remains difficult due to reliability limitations, security risks, and insufficient long-term memory mechanisms. This work proposes an architecture that adapts LLM agents for hospital environments. The design introduces four core components: a restricted execution environment inspired by Linux multi-user systems, a document-centric interaction paradigm connecting patient and clinician agents, a page-indexed memory architecture designed for long-term clinical context management, and a curated medical skills library enabling ad-hoc composit

W
Wenxian Yang, Hanzheng Qiu, Bangqun Zhang, Chengquan Li, Zhiyong Huang, Xiaobin Feng, Rongshan Yu, Jiahong Dong · · 1 min read · 178 views
#cs.AI

arXiv:2603.11721v1 Announce Type: new Abstract: Large language model (LLM) agents extend conventional generative models by integrating reasoning, tool invocation, and persistent memory. Recent studies suggest that such agents may significantly improve clinical workflows by automating documentation, coordinating care processes, and assisting medical decision making. However, despite rapid progress, deploying autonomous agents in healthcare environments remains difficult due to reliability limitations, security risks, and insufficient long-term memory mechanisms. This work proposes an architecture that adapts LLM agents for hospital environments. The design introduces four core components: a restricted execution environment inspired by Linux multi-user systems, a document-centric interaction paradigm connecting patient and clinician agents, a page-indexed memory architecture designed for long-term clinical context management, and a curated medical skills library enabling ad-hoc composition of clinical task sequences. Rather than granting agents unrestricted system access, the architecture constrains actions through predefined skill interfaces and resource isolation. We argue that such a system forms the basis of an Agentic Operating System for Hospital, a computing layer capable of coordinating clinical workflows while maintaining safety, transparency, and auditability. This work grounds the design in OpenClaw, an open-source autonomous agent framework that structures agent capabilities as a curated library of discrete skills, and extends it with the infrastructure-level constraints required for safe clinical deployment.

Executive Summary

This article proposes an architecture for an Agentic Operating System for Hospital, integrating large language model agents into clinical workflows while addressing reliability, security, and memory limitations. The design features a restricted execution environment, document-centric interaction, page-indexed memory, and a curated medical skills library. By constraining agent actions through predefined skill interfaces and resource isolation, the system prioritizes safety, transparency, and auditability. Building on the OpenClaw framework, this work extends its capabilities with infrastructure-level constraints for safe clinical deployment.

Key Points

  • ▸ Integration of large language model agents into clinical workflows
  • ▸ Introduction of a restricted execution environment for security and reliability
  • ▸ Design of a document-centric interaction paradigm for patient and clinician agents
  • ▸ Development of a page-indexed memory architecture for long-term clinical context management

Merits

Enhanced Clinical Workflow Efficiency

The proposed system has the potential to significantly improve clinical workflow efficiency by automating documentation and coordinating care processes

Improved Safety and Transparency

The architecture's emphasis on safety, transparency, and auditability through constrained agent actions and resource isolation is a notable strength

Demerits

Complexity of Implementation

The integration of large language model agents into hospital environments may be complex and require significant resources

Potential for Bias in Medical Skills Library

The curated medical skills library may be susceptible to bias if not properly validated and updated

Expert Commentary

The proposed Agentic Operating System for Hospital represents a promising approach to integrating large language model agents into clinical workflows. By prioritizing safety, transparency, and auditability, this system addresses key concerns surrounding the deployment of autonomous agents in healthcare environments. However, the complexity of implementation and potential for bias in the medical skills library must be carefully considered. As the healthcare sector continues to evolve, the development of such systems will play a critical role in shaping the future of patient care and clinical workflows.

Recommendations

  • ✓ Further research is needed to validate the effectiveness and safety of the proposed system in real-world clinical settings
  • ✓ The development of clear policies and regulations governing the use of artificial intelligence in healthcare is essential to ensure the responsible deployment of such systems

Sources

Related Articles