English

Entropic-Time Inference: Self-Organizing Large Language Model Decoding Beyond Attention

Computation and Language 2026-03-05 v1 Machine Learning

Abstract

Modern large language model (LLM) inference engines optimize throughput and latency under fixed decoding rules, treating generation as a linear progression in token time. We propose a fundamentally different paradigm: entropic\-time inference, where decoding is governed by the flow of uncertainty rather than token index. We introduce a self\-organizing inference architecture that jointly couples scheduling, attention sparsification, and sampling temperature under a unified entropy control objective. Our method extends vLLM with entropy-aware scheduling, entropic pruning of paged attention blocks, and adaptive temperature control that stabilizes generation near a target entropy regime. This transforms inference into a resource\-intelligent thermodynamic process that allocates computation where uncertainty reduction is maximized. We present a concrete systems design, pseudocode, and integration plan, demonstrating how entropy can serve as a first\-class control signal for scalable LLM inference.

Keywords

Cite

@article{arxiv.2603.03310,
  title  = {Entropic-Time Inference: Self-Organizing Large Language Model Decoding Beyond Attention},
  author = {Andrew Kiruluta},
  journal= {arXiv preprint arXiv:2603.03310},
  year   = {2026}
}
R2 v1 2026-07-01T11:01:46.586Z