Sebastian Barros

Sebastian Barros

As Radio Access Networks (RAN) evolve toward AI-native architectures, intelligent modules such as xApps and rApps are expected to make increasingly autonomous decisions across scheduling, mobility, and resource management domains. However, these agents remain fundamentally stateless, treating each decision as isolated, lacking any persistent memory of prior events or outcomes. This reactive behavior constrains optimization, especially in environments where network dynamics exhibit episodic or recurring patterns. In this work, we propose RAN Cortex, a memory-augmented architecture that enables contextual recall in AI-based RAN decision systems. RAN Cortex introduces a modular layer composed of four elements: a context encoder that transforms network state into high-dimensional embeddings, a vector-based memory store of past network episodes, a recall engine to retrieve semantically similar situations, and a policy interface that supplies historical context to AI agents in real time or near-real time. We formalize the retrieval-augmented decision problem in the RAN, present a system architecture compatible with O-RAN interfaces, and analyze feasible deployments within the Non-RT and Near-RT RIC domains. Through illustrative use cases such as stadium traffic mitigation and mobility management in drone corridors, we demonstrate how contextual memory improves adaptability, continuity, and overall RAN intelligence. This work introduces memory as a missing primitive in AI-native RAN designs and provides a framework to enable "learning agents" without the need for retraining or centralized inference

Sebastian Barros

The rapid proliferation of generative AI has led to an internet increasingly populated with synthetic content-text, images, audio, and video generated without human intervention. As the distinction between human and AI-generated data blurs, the ability to verify content origin becomes critical for applications ranging from social media and journalism to legal and financial systems. In this paper, we propose a conceptual, multi-layer architectural framework that enables telecommunications networks to act as infrastructure level certifiers of human-originated content. By leveraging identity anchoring at the physical layer, metadata propagation at the network and transport layers, and cryptographic attestations at the session and application layers, Telcos can provide an end-to-end Proof of Humanity for data traversing their networks. We outline how each OSI layer can contribute to this trust fabric using technical primitives such as SIM/eSIM identity, digital signatures, behavior-based ML heuristics, and edge-validated APIs. The framework is presented as a foundation for future implementation, highlighting monetization pathways for telcos such as trust-as-a-service APIs, origin-certified traffic tiers, and regulatory compliance tools. The paper does not present implementation or benchmarking results but offers a technically detailed roadmap and strategic rationale for transforming Telcos into validators of digital authenticity in an AI-dominated internet. Security, privacy, and adversarial considerations are discussed as directions for future work.