Dear All,

 

We will organize a side meeting on Agent Policy-Aware Networks next Wednesday, 
March 18, 09:30-11:00, in Hunan Hall.




This side meeting aims to propose a new paradigm for Agent Policy-Aware 
Networks. MPLS/SRv6 have been widely deployed in backbone networks, providing 
differentiated services for traditional applications. However, the rapid 
development of generative AI and multi-Agent systems imposes unprecedented 
policy-aware service requirements on networks, including ultra-low latency, 
high availability, on-demand scheduling, and fine-grained traffic steering. The 
key challenge is how to utilize existing network advantages to perceive diverse 
policies for AI Agent interactions and support efficient deployment and 
collaboration. To address this gap, the network needs to evolve into an 
intelligent policy-aware service system for AI Agents. We will focus on the 
intent-based interaction between agents and networks, and build a dynamic 
mapping mechanism from agent intents to network policies, so as to realize 
efficient collaboration between agents and networks, end-to-end SLA guarantees 
and secure and trustworthy transmission. We look forward to in-depth 
discussions with all participants to explore the development direction of this 
field.

 

Distinguished experts from George Washington University, Xiangya Hospital, 
Huawei, China Mobile and other institutions will gather here to conduct 
in-depth discussions. If you are interested in the innovative research and 
practice of Agent Policy-Aware Networks, we sincerely invite you to join this 
side meeting. For remote participants, please access the meeting via the link: 
https://ietf.webex.com/meet/sidemeetings1.

 

Welcome to join us!  We look forward to your active participation and valuable 
contributions!





If you have any questions, please feel free to contact us: 
[email protected], [email protected]

 

 

Best Regards,

Xiaoqiu












 
_______________________________________________
rtgwg mailing list -- [email protected]
To unsubscribe send an email to [email protected]

Reply via email to