From Source Reconstruction to Predictive State Preservation: An Information-Theoretic Framework for AI-Native Communication

2026-09-01

AI Summary

论文探讨了在AI原生通信中，为了预测而非源重建，应保留的信息。通过信息论框架，定义了基于预测状态的保真度对象，并分析了通信失真及压缩问题。

Abstract

AI-native communication increasingly aims to support prediction rather than reproduce every detail of the source. This shift raises a basic question left implicit by conventional source coding: what should be preserved when the terminal goal is prediction? We take the source-induced predictive state as the fidelity object. It is the distribution of the specified future conditioned on the source observation and shared context. We show that this state is sufficient and minimal for exact predictive preservation. The terminal prediction loss then defines communication distortion as lost predictive performance rather than source reconstruction error. Under logarithmic loss, this distortion equals the conditional mutual information lost through communication. Using the receiver-side predictive state as a Bayes reference, we separate AI-receiver error into predictive value lost in communication, receiver-available value unusable by the model family, and family capability not realized by the deployed model. The same predictive state also suffices for matched compression. For finite-alphabet memoryless sources, access to the raw source gives no rate-distortion advantage over coding the state directly. Applying the same target-conditioned construction to sequential prediction reveals a dynamic boundary. A state induced by a fixed horizon is minimal for that horizon but may not support recursive updating as the target window shifts. Taking the entire future as the target yields a minimal full-future state that updates recursively and admits a Markov representation. Together, these results shift AI communication from source reconstruction to predictive-state preservation.

Problem

• AI-native communication
• prediction
• source coding
• predictive state
• information-theoretic framework

Innovation

• predictive state
• information-theoretic framework
• communication distortion
• conditional mutual information
• Markov representation