{"ID":2825798,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.20275","arxiv_id":"2512.20275","title":"Graph-Symbolic Policy Enforcement and Control (G-SPEC): A Neuro-Symbolic Framework for Safe Agentic AI in 5G Autonomous Networks","abstract":"As networks evolve toward 5G Standalone and 6G, operators face orchestration challenges that exceed the limits of static automation and Deep Reinforcement Learning. Although Large Language Model (LLM) agents offer a path toward intent-based networking, they introduce stochastic risks, including topology hallucinations and policy non-compliance. To mitigate this, we propose Graph-Symbolic Policy Enforcement and Control (G-SPEC), a neuro-symbolic framework that constrains probabilistic planning with deterministic verification. The architecture relies on a Governance Triad - a telecom-adapted agent (TSLAM-4B), a Network Knowledge Graph (NKG), and SHACL constraints. We evaluated G-SPEC on a simulated 450-node 5G Core, achieving zero safety violations and a 94.1% remediation success rate, significantly outperforming the 82.4% baseline. Ablation analysis indicates that NKG validation drives the majority of safety gains (68%), followed by SHACL policies (24%). Scalability tests on topologies ranging from 10K to 100K nodes demonstrate that validation latency scales as $O(k^{1.2})$ where $k$ is subgraph size. With a processing overhead of 142ms, G-SPEC is viable for SMO-layer operations.","short_abstract":"As networks evolve toward 5G Standalone and 6G, operators face orchestration challenges that exceed the limits of static automation and Deep Reinforcement Learning. Although Large Language Model (LLM) agents offer a path toward intent-based networking, they introduce stochastic risks, including topology hallucinations...","url_abs":"https://arxiv.org/abs/2512.20275","url_pdf":"https://arxiv.org/pdf/2512.20275v1","authors":"[\"Divya Vijay\",\"Vignesh Ethiraj\"]","published":"2025-12-23T11:27:17Z","proceeding":"cs.AI","tasks":"[\"cs.AI\",\"cs.NI\"]","methods":"[\"Reinforcement Learning\",\"Large Language Model\",\"Language Model\"]","has_code":false}