Policy-Aware Edge LLM-RAG Framework for Internet of Battlefield Things Mission Orchestration
This addresses safety and reliability concerns for LLM-driven orchestration in mission-critical IoBT systems, though it is incremental as it builds on existing RAG and verification methods.
The paper tackled the problem of using Large Language Models (LLMs) for mission control in Internet of Battlefield Things (IoBT) environments by proposing a Policy-Aware LLM-RAG framework that integrates retrieval-augmented reasoning and command verification, resulting in effective detection of policy-violating commands with low latency, such as Gemma-2B achieving 100% success rate and 4.17 sec latency.
Large Language Models (LLMs) offer a promising interface for intent-driven control of autonomous cyber-physical systems, but their direct use in mission-critical Internet of Battlefield Things (IoBT) environments raises significant safety, reliability, and policy-compliance concerns. This paper presents a Policy-Aware Large Language Model Retrieval-Augmented Generation (referred as PA-LLM-RAG), an edge-deployed LLM orchestration framework for IoBT mission control that integrates retrieval-augmented reasoning and independent command verification. The proposed PA-LLM-RAG framework combines a lightweight retrieval module that grounds decisions in operational policies and telemetry with a locally hosted LLM for mission planning and a secondary JudgeLLM for validating user generated commands prior to execution. To evaluate PA-LLM-RAG, we implement a simulated IoBT environment using RoboDK and assess four open-source LLMs across controlled mission scenarios of increasing complexity, including baseline operations, threat detection, coverage recovery, multi-event coordination, and policy-violation requests. Experimental results demonstrate that the framework effectively detects policy-violating commands while maintaining low-latency response suitable for edge deployment. Gemma-2B achieving the highest overall reliability with 4.17 sec latency and 100% success rate. The findings highlight a clear tradeoff between reasoning capacity and responsiveness across models and show that combining deterministic safeguards with JudgeLLM verification significantly improves reliability in LLM-driven IoBT orchestration.