Policy-Aware Edge LLM-RAG Framework for Internet of Battlefield Things Mission Orchestration
2026-04-10 • Networking and Internet Architecture
Networking and Internet Architecture
AI summaryⓘ
The authors developed a system called PA-LLM-RAG to help control battlefield devices safely using AI language models. Their system uses a small retrieval tool to check rules and data, a local language model to plan missions, and another AI judge to verify commands before acting on them. They tested this setup in a simulated battlefield environment and found it detects unsafe commands well while responding quickly. The study also showed that combining strict rule checks with an AI judge makes controlling these devices more reliable.
Large Language ModelsInternet of Battlefield ThingsRetrieval-Augmented GenerationEdge ComputingMission PlanningCommand VerificationPolicy ComplianceRoboDK SimulationAI SafetyLatency
Authors
Om Solanki, Lopamudra Praharaj, Deepti Gupta, Maanak Gupta
Abstract
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.