ENWAR 2.0: an agentic multimodal wireless LLM framework with reasoning, situation-aware explainability and beam tracking

Abstract

The evolution of next-generation wireless networks demands intelligent, adaptive, and explainable decision-making for robust communication in dynamic environments. This paper presents ENWAR 2.0, the first agentic large language model (LLM) framework integrating adaptive retrieval-augmented generation (RAG) and chain-of-thought (CoT) reasoning into situation-aware and explainable wireless network management. ENWAR 2.0 introduces two specialized agents: a transformerfusion (TransFusion)-based beam prediction agent and an environment perception agent, both of which fuse multi-modal sensory inputs—including camera, LiDAR, radar, and GPS—from the DeepSense6G dataset. The beam prediction agent enables infrastructure-to-vehicle (I2V) target-in-the-loop beam tracking and real-time adaptation based on dynamic environmental conditions. In contrast, the environment perception agent provides situation-aware reasoning and justifications for beam decisions. Unlike its predecessor, ENWAR 1.0, which relied on static knowledge bases (KBs) and text-only LLMs, ENWAR 2.0 is designed for CoT reasoning, leverages LLaMa3.2-3B/LLaMa3.1-8B/LLaMa3.3-70B for text-generation, the multi-modal capabilities of LLaMa 3.2, and employs LlamaIndex for fine-grained, dynamic context retrieval, eliminating retrieval ambiguities and enhancing response relevance. Numerical results show that the beam prediction agent achieves up to 90.0% Top-3 accuracy at t + 3, effectively predicting optimal beam selections three time steps ahead. Overall, ENWAR 2.0 achieves state-of-the-art performance, with up to 89.7%/83.5% interpretation/perception correctness, 81.6%/80.9% faithfulness, and 89.9%/88.2% relevancy. In comparison, the baseline pretrained LLaMa3 models without adaptive RAG achieves up to 80.3%/77.3% correctness, and the baseline without RAG performs significantly worse at 67.1%/64.8%. Additionally, ENWAR 2.0 reduces processing time by over 100% relative to the baseline, while its adaptive RAG improves performance by up to 13.7% compared to static RAG.

More information

Identifiers

Catalogue record

Export record

ASCII CitationAtomBibTeXData Cite XMLDublin CoreDublin CoreEP3 XMLEndNoteHTML CitationHTML CitationHTML ListJSONMETSMODSMPEG-21 DIDLOpenURL ContextObjectOpenURL ContextObject in SpanRDF+N-TriplesRDF+N3RDF+XMLRIOXX2 XMLReferReference ManagerSimple Metadata

Altmetrics