Ericsson has unveiled AI in RAN, a new software subscription designed to bring telco-grade artificial intelligence directly into radio access network (RAN) infrastructure, enabling communications service providers (CSPs) to improve network performance, operational efficiency, and energy savings without requiring additional hardware investments.
The launch marks a significant step in Ericsson’s strategy to accelerate the transition toward AI-native networks by embedding advanced AI capabilities into basebands and radios across 5G environments.
According to Mårten Lerner, Head of Networks Strategy & Product Management at Ericsson, the new software represents a major milestone in network transformation.
“Ericsson is redefining what’s possible in mobile networks by bringing powerful AI capabilities to service providers. With AI in RAN software, we are taking a major step toward AI-native networks, alongside the AI-ready radios we unveiled in February,” said Mårten Lerner.
AI in RAN Delivers Real-Time Intelligence for 5G Networks
Ericsson’s AI in RAN introduces several advanced capabilities, including:
Telco-grade AI models designed for real-time operation within the RAN
Continuous learning software powered by scalable, high-quality data
Agentic AI support for advanced automation and network operations
The AI models are engineered for ultra-low latency inference at the microsecond level, enabling reliable and robust performance across dynamic radio environments. Developed using Ericsson’s telecommunications expertise and trained on high-quality network datasets, the models are designed to maximize efficiency and network performance.
Nitin Bansal, MD, Ericsson India, highlighted the growing need for AI-driven network infrastructure.
“Service providers need networks that are high-performing, secure and efficient in the AI era. With AI in RAN, Ericsson is bringing AI into networks to elevate operational efficiency, elevate network performance and open new business opportunities,” said Nitin Bansal.
Commercial Deployments Show Strong Performance Gains
Ericsson AI in RAN is compatible with Ericsson 5G Advanced across both purpose-built and Cloud RAN platforms, enabling operators to deploy AI-driven services while improving network intelligence.
The solution uses Ericsson Silicon for energy-efficient AI inference in radios and leverages the latest generation of RAN Compute technology. Cloud RAN portability also allows AI capabilities to run across partner platforms.
The first AI in RAN software features became available in the second quarter of 2026, with additional enhancements scheduled throughout the year. Key capabilities include:
AI-native Scheduler for Link Adaptation
AI-powered Macro Positioning
AI-managed Beamforming
AI-powered Multi-layer Coordination
Performance Management Event Schema Files
Augmented Observability for AI in RAN
Ericsson reported that AI in RAN has already been validated through more than 15 deployments and trials worldwide. Performance results include:
Up to 20% higher downlink throughput
Up to 10% better spectral efficiency
Support for up to 2x more high-traffic users
90–95% coverage prediction accuracy
Up to 5x greater user-positioning precision
Global Operators Back Ericsson’s AI-RAN Vision
Leading telecom operators have endorsed the potential of AI in RAN to enhance network intelligence and support emerging AI-driven applications.
Teruyuki Oya, Senior Vice President & CNO, SoftBank Corp., said the software will help translate AI innovation into practical operational value.
“Ericsson’s AI in RAN software marks an important step in bringing AI deeper into the radio access network. By enabling real-time optimization of radio performance, spectrum efficiency and user experience, it helps us turn AI innovation into practical value on live networks. We also see strong potential in how this foundation can support emerging AI-driven services, including Physical AI scenarios that depend on low-latency, highly reliable connectivity, and intelligent coordination between network and compute resources,” said Teruyuki Oya.
Bruce Dean, Senior Vice President, Network Technology & Operations, Bell, emphasized the importance of intelligent network evolution.
“At Bell, we’re continuously evolving our network to meet growing demand for high-performance, AI-driven services. Integrating AI directly into the RAN is an important step in making networks more intelligent and efficient. Working with partners like Ericsson, we’re bringing these capabilities into our network to enhance performance, improve energy efficiency and deliver a better experience for our customers,” said Bruce Dean.
Yu Takki, Head of Network Technology Office, SK Telecom, highlighted the role of AI-RAN in future network generations.
“Through our collaboration with Ericsson, SK Telecom is advancing AI-RAN to enhance network performance and energy efficiency while supporting more intelligent and automated operations. By combining research, real-world validation and software innovation, we aim to strengthen our leadership in AI-powered network evolution and help lay the foundation for AI-native 6G,” said Yu Takki.
Mark Kennedy, Chief Technology Officer, Rogers, noted the customer and sustainability benefits of the technology.
“As Canada’s best 5G+ network, we’re proud to work with Ericsson and bring the latest 5G technology to Canadians. AI in RAN will help optimize network performance for customers in real-time and reduce energy consumption,” said Mark Kennedy.
Mobile Industry Analysts See Strong ROI Potential
Industry analysts believe AI in RAN could provide operators with one of the strongest returns on investment available in current network infrastructure.
Joe Madden, Principal Analyst at Mobile Experts, described the software as a potentially transformative upgrade for mobile operators.
“This could be the best ROI for mobile operators in years. With a software upgrade, operators can squeeze more capacity, better observability, and more accurate location-based services out of the 5G network they bought years ago,” said Joe Madden.
Ericsson Accelerates the Move Toward AI-Native Networks
Ericsson has steadily expanded AI capabilities across its mobile network portfolio since the 4G era. In 2021, the company introduced AI-ready acceleration within RAN Compute platforms. Earlier in 2026, Ericsson launched Neural Network Accelerators in its Massive MIMO radios, increasing AI inference capability by 10 times.
With AI in RAN now commercially available, Ericsson is positioning itself at the forefront of AI-native networking, helping operators unlock higher network capacity, improved spectral efficiency, enhanced automation, and significant energy savings while preparing for the future of AI-powered 5G and 6G networks.