Edge devices often lack the DRAM capacity required to store full large-language-model (LLM) weight matrices. This work investigates a radio-broadcast streaming approach---AetherCast-LLM---where each weight row is transmitted as a packet, indexed in a balanced binary search tree, and applied to the input vector without ever materialising the complete matrix. We formalise the state machine that consumes packets, prove that the tree remains height-balanced and key-ordered after each insertion, and derive asymptotic bounds for packet lookup, insertion and output computation. Static analysis of the TypeScript implementation yields a structural complexity of O(log N) per packet and an AST profile of 187 source-lines across 14 functions. The results demonstrate that AetherCast-LLM can guarantee memory-free inference while preserving deterministic computational complexity.
Manuscript Attribution: This manuscript is an empirical research preprint synthesized via agentic autonomous systems engineering pipelines adhering to academic two-column preprint conventions under the direction of Mateus Yonathan.
Hardware & Algorithmic Provenance: Algorithmic complexity bounds, execution profiles, and memory models cite verified static AST analysis and compiler toolchains evaluated by autonomous agent feedback loops.
Limitation of Liability & Scholarly Purpose: Disseminated solely for scholarly inquiry, peer discussion, and reproducible empirical comparison. It does not constitute formal peer-reviewed accreditation. Any reliance upon the mathematical proofs or complexity bounds herein is strictly at the reader's own legal and technical risk.
@article{yonathan2026_2026_10_14_aethercast_broadcasting_ai_weights_ove,
title={Height-Balanced Tree Invariants for TypeScript AetherCast-LLM: Radio-Broadcasted W...},
author={Yonathan, Mateus},
journal={Polyglot Systems Lab Research Preprints},
year={2026},
publisher={Polyglot Systems Lab},
url={https://myonathanlinkedin.github.io/papers/2026-10-14_aethercast_broadcasting_ai_weights_ove/},
howpublished={\url{https://raw.githubusercontent.com/myonathanlinkedin/mini-papers/main/papers/2026-10-14_aethercast_broadcasting_ai_weights_ove/2026-10-14_aethercast_broadcasting_ai_weights_ove.pdf}}
}