GENESIS: Harnessing AI Agents for Autonomous 6G RAN Synthesis, Research, and Testing

2026-05-26

AI Summary

This work addresses the limitations of traditional 6G radio access network (RAN) development, which relies heavily on labor-intensive processes for implementation, testing, adaptation, optimization, exploration, and security validation. Existing large language models often suffer from API hallucinations, misinterpretation of technical specifications, and dependence on unreliable simulations. To overcome these challenges, the authors propose GENESIS—a closed-loop framework integrating AI agents, composable skills with hook primitives, and a domain-specific knowledge base named SYNAPSE. GENESIS enables, for the first time, end-to-end autonomous synthesis and iterative refinement of RAN solutions directly from user intent—such as regulatory clauses or research hypotheses—to over-the-air validated designs. This approach substantially enhances the reliability of large models in wireless communications, reduces development cycles from months to minutes, facilitates autonomous discovery of novel waveforms and functionalities, and ensures interoperability and deployment robustness through real hardware verification.

Abstract

Cellular research and development (R&D) is throttled by six structural processes that each consume months of manual engineering work per iteration: (i) synthesizing new features from standards or research papers into production code; (ii) conformance and interoperability testing; (iii) hardening against field anomalies and diverse deployment environments; (iv) data-driven optimization of network functionalities; (v) discovering and prototyping novel waveforms, functionalities, and capabilities for future standards; and (vi) securing the stack against vulnerabilities. Although Large Language Models (LLMs) have compressed comparable R&D work in general software engineering from days to minutes, their known pitfalls worsen on Radio Access Network (RAN) use cases: they hallucinate Application Programming Interfaces (APIs) and mis-read specifications, which kills interoperability of RAN components at the first mistake, and they heavily rely on simulations for designing algorithms, which is notorious for breaking when transferred to real hardware. To address these challenges, we present GENESIS, an agentic Artificial Intelligence (AI) framework that converts intents (e.g., a specification clause, a telemetry anomaly, or a research hypothesis) into solutions validated with over-the-air experiments, fed back into a persistent knowledge base. GENESIS is built on three composable primitives (agents, skills, hooks) and a knowledge layer (SYNAPSE) that doubles as the source of ground truth and the recipient of every artifact the framework produces, making capabilities compound across runs.

Problem

• 6G RAN
• AI Agents
• Autonomous Synthesis
• Interoperability
• Over-the-Air Validation

Innovation

• AI Agents
• 6G RAN
• Over-the-Air Validation
• Knowledge Base
• Autonomous Synthesis