Intent Interpretation at RIC Timescales: Jev Decision Models versus Large Language Models in 6G Open RAN

A study compares Jev-1.13.0 decision models against generative large language models for interpreting intents into A1 policies inside the RAN intelligent controller loop in intent-based 6G Open RAN, noting that Jev-1.13.0 returns typed policy fields while LLMs produce policy token by token. The research asks whether LLMs can match decision models at RIC timescales.

Intent-based Open RAN needs an interpreter that turns intents into A1 policies within the loop of the RAN intelligent controller RIC . Decision models such as Jev-1.13.0 return typed policy fields, whereas generative large language models LLMs produce the policy token by token. We ask whether the