Toward an Unbiased Collective Memory for Efficient LLM-Based Agentic 6G Cross-Domain Management

arXiv:2509.26200 · cs.NI, cs.AI · Submitted 2025-09-30 · Read on arXiv

cs.NI, cs.AI

Submitted: 2025-09-30

Updated: 2026-09-19

Code: https://github.com/HatimChergui/unbiased-collective-memory

License: http://creativecommons.org/licenses/by/4.0/

The gist: Agentic artificial intelligence is a candidate enabler of Level-4 autonomy in sixth-generation (6G) networks, but agents reasoning over a shared memory inherit its distortions.

Terminology

Abstract

Agentic artificial intelligence is a candidate enabler of Level-4 autonomy in sixth-generation (6G) networks, but agents reasoning over a shared memory inherit its distortions. We study cross-domain radio access network (RAN)--edge orchestration in which a RAN agent minimizing energy and an edge agent minimizing latency negotiate, validate proposals against a digital twin (DT), and share a collective memory. Such a memory is a sampling device: what agents retrieve, not what they store, determines what they do. We define the Retrieval Bias Index, a divergence between the induced retrieval law and a representative reference, decomposed along temporal, confirmation and availability axes, and show that additive retrieval scoring is an exponential tilt of the undebiased law, yielding a closed form for the failure-amplification weight and a saturation floor set by the store's own composition; a further result bounds excess service level agreement (SLA) violation additively in retrieval bias and DT mismatch. On a tandem queue for which stochastic network calculus supplies a feasible region, an oracle and a Nash bargaining reference, the operator attains a 12.7 times bias reduction over a recency store and the smallest distance to the bargaining solution among six memory architectures.

Sources

Related papers