Agentic AI for Intent-Based Networking
draft-cxxx-nmrg-ai4ibn-00

NMRG                                                            A. Clemm
Internet-Draft                                                Individual
Intended status: Informational                                 T. Eckert
Expires: 7 January 2027                       Futurewei Technologies USA
                                                             6 July 2026

                 Agentic AI for Intent-Based Networking
                       draft-cxxx-nmrg-ai4ibn-00

Abstract

   This document specifies how the rise of agentic AI and LLMs can
   impact and and accelerate the transition towards Intent-Based
   Networking.
   Specifically, it revisits functionality and liefecycle in IBN, as
   defined in [RFC9315], and outlines how agentic AI and LLMs can be
   leveraged.

Status of This Memo

   This Internet-Draft is submitted in full conformance with the
   provisions of BCP 78 and BCP 79.

   Internet-Drafts are working documents of the Internet Engineering
   Task Force (IETF).  Note that other groups may also distribute
   working documents as Internet-Drafts.  The list of current Internet-
   Drafts is at https://datatracker.ietf.org/drafts/current/.

   Internet-Drafts are draft documents valid for a maximum of six months
   and may be updated, replaced, or obsoleted by other documents at any
   time.  It is inappropriate to use Internet-Drafts as reference
   material or to cite them other than as "work in progress."

   This Internet-Draft will expire on 7 January 2027.

Copyright Notice

   Copyright (c) 2026 IETF Trust and the persons identified as the
   document authors.  All rights reserved.

Clemm & Eckert           Expires 7 January 2027                 [Page 1]
Internet-Draft                    AI4AN                        July 2026

   This document is subject to BCP 78 and the IETF Trust's Legal
   Provisions Relating to IETF Documents (https://trustee.ietf.org/
   license-info) in effect on the date of publication of this document.
   Please review these documents carefully, as they describe your rights
   and restrictions with respect to this document.  Code Components
   extracted from this document must include Revised BSD License text as
   described in Section 4.e of the Trust Legal Provisions and are
   provided without warranty as described in the Revised BSD License.

Table of Contents

   1.  Introduction: Why revisit IBN in the face of LLMs and agentic
           AI  . . . . . . . . . . . . . . . . . . . . . . . . . . .   2
   2.  Definitions and Terminology . . . . . . . . . . . . . . . . .   3
   3.  IBN Lifecycle Reference Model revisited . . . . . . . . . . .   4
   4.  IBN Functionality revisited . . . . . . . . . . . . . . . . .   5
     4.1.  Intent Fulfillment  . . . . . . . . . . . . . . . . . . .   5
       4.1.1.  Intent Ingestion and Interaction with Users . . . . .   6
       4.1.2.  Intent Translation  . . . . . . . . . . . . . . . . .   6
       4.1.3.  Intent Orchestration  . . . . . . . . . . . . . . . .   6
     4.2.  Intent Assurance  . . . . . . . . . . . . . . . . . . . .   7
       4.2.1.  Monitoring  . . . . . . . . . . . . . . . . . . . . .   7
       4.2.2.  Intent Compliance Assessment  . . . . . . . . . . . .   7
       4.2.3.  Abstraction, Aggregation, Reporting . . . . . . . . .   7
   5.  Related Work  . . . . . . . . . . . . . . . . . . . . . . . .   7
   6.  Acknowledgements  . . . . . . . . . . . . . . . . . . . . . .   8
   7.  Security Considerations . . . . . . . . . . . . . . . . . . .   8
   8.  Informative References  . . . . . . . . . . . . . . . . . . .   8
   Appendix A.  Changelog  . . . . . . . . . . . . . . . . . . . . .   9
   Authors' Addresses  . . . . . . . . . . . . . . . . . . . . . . .   9

1.  Introduction: Why revisit IBN in the face of LLMs and agentic AI

   Intent-Based Networking (IBN) involves the concept of allowing
   networks to be managed using "intent", that is, by allowing network
   operators to specify in a declarative manner sets of operational
   goals (that a network should meet) and outcomes (that a network is
   supposed to deliver) without needing to specify how to actually
   achieve or implement them [RFC9315].  Determining the specific
   actions that would need to be taken would be up to the IBN itself,
   whether those actions involve determining configuration parameters
   and applying them, performing optimizations, monitoring the network
   and assessing whether additional actions need to be taken, and more.
   Intent and IBN in many ways complete the vision articulated as part
   of autonomic networking that involve achieving self-configuration,
   self-optimization, self-healing, and self-protection while minimizing
   dependencies on human administrators who are taken out of the control
   loop.  However, even autonomic networks are not clairvoyant but need

Clemm & Eckert           Expires 7 January 2027                 [Page 2]
Internet-Draft                    AI4AN                        July 2026

   to be given guidance by administrators.  That guidance is
   characterized as intent [RFC7575].

   Since Autonomic Networking and IBN were defined, many commercial
   offerings for intent-based systems have appeared.  In many cases,
   "intent" by those systems has been less abstract in nature but
   instead involves structured APIs that are used to manage services and
   connectivity in a network instead of individual network elements on a
   per-device basis.  While useful, there is still a gap between the
   abstractions provided by those APIs and their underlying system on
   one hand and the vision of an intent as defined in [RFC9315] on the
   other hand.  For example, operators are still very much responsible
   to determine strategies to achieve broad outcomes.

   The recent explosive rise of Large Language Models (LLMs) and agentic
   AI (roughly understood as systems with LLMs at their core, extended
   with additional capabilities that allow them to access additional
   tools, to decompose tasks, to integrate with other applications)
   holds the promise to potentially change that as it opens up
   possibilities for the implementation of capabilities in technical
   systems that until recently did not exist.  For example, agentic AI
   allows for the implementation of chat interfaces that allow users to
   state their intent in their own words, without requiring them to be
   proficient in any particular APIs or command interfaces.
   Importantly, agentic AI may allow to clarify ambiguities, can ask for
   additional information and details, point out constraints, discuss
   alternatives, thus providing means for ingesting intent that systems
   up to this point did not have.  Likewise, agentic control loops hold
   the promise to potentially allow IBNs to intelligently monitor the
   network to assess outcomes as well as the effectiveness of actions
   that are taken.  Coupled with learning capabilities, IBNs can become
   even more effective over time and result in continued network
   optimization and improvement.  While some of this promise yet remains
   to be proven, the potential for it is there and appears to be only a
   matter of time.

   The concept of IBN remains very much valid and appears more relevant
   than ever for the future of networking in light of the new
   possibilities that can help make it a reality.  Given this, it seems
   reasonable to revisit IBNs, specifically, their functional components
   as well as the lifecycle reference architecture, and articulate the
   ways in which agentic AI and LLMs can facilitate and accelerate IBN
   development and adoption.

2.  Definitions and Terminology

Clemm & Eckert           Expires 7 January 2027                 [Page 3]
Internet-Draft                    AI4AN                        July 2026

3.  IBN Lifecycle Reference Model revisited

   IBN is subject to several loops, as depicted in the IBN Lifecycle
   Reference model (Figure 1).

            User Space   :       Translation / IBS       :  Network Ops
                         :            Space              :     Space
                         :                               :
           +----------+  :  +----------+   +-----------+ : +-----------+
   Fulfill |recognize/|---> |translate/|-->|  learn/   |-->| configure/|
           |generate  |     |          |   |  plan/    |   | provision |
           |intent    |<--- |  refine  |   |  render   | : |           |
           +----^-----+  :  +----------+   +-----^-----+ : +-----------+
                |        :                       |       :        |
   .............|................................|................|.....
                |        :                  +----+---+   :        v
                |        :                  |validate|   :  +----------+
                |        :                  +----^---+ <----| monitor/ |
   Assure   +---+---+    :  +---------+    +-----+---+   :  | observe/ |
            |report | <---- |abstract |<---| analyze | <----|          |
            +-------+    :  +---------+    |aggregate|   :  +----------+
                         :                 +---------+   :

      Figure 1: IBN lifecycle and reference architecture per RFC 9315

   The first of these loops occurs between the functions to ingest
   (recognize, generate) intent, and translate it into specific commands
   and operations that will be actionable by the underlying network.
   Agentic AI systems implement similar loops in other areas, for
   example in program development and coding.  Application of Agentic AI
   to IBN in this area appears thus straightforward and it is expected
   that corresponding Agentic AI agents cand implement both of these
   functions.

   The second loop concerns the "inner" intent control loop between IBS
   and Network Operations space: learn/plan/render -> configure/
   provision -> monitor/observe -> analyze/aggregate -> validate ->
   learn/plan/render (here the loop closes).  Agentic AI has inherent
   translation capabilities that can play an important role in
   simplifying the implementation of configuration and provisioning
   systems by determining how to map required actions to device
   interfaces, ensuring the right commands and APIs are invoked.  The
   same translation capabilities help smoothen over impedance mismatches
   in the data models exposed by underlying systems.  This simplifies
   many past issues associated with dealing with interface heterogeneity
   and associated sustaining operations.

Clemm & Eckert           Expires 7 January 2027                 [Page 4]
Internet-Draft                    AI4AN                        July 2026

   Agentic AI can also help determine what type of monitoring and
   measurements will be required to observe the effectiveness of actions
   taken and assess compliance with intent, and configuration and
   provisioning functions can be augmented with corresponding
   capabilities to set up those observations as well.  Agentic AI may
   have less of a role to play in analyzing raw monitoring data as the
   data velocity in this space is very high.  This concerns IPFIX
   records, IOAM telemetry data, syslog notifications, YANG-Push
   management data streams.  For a network, the volume of these easily
   reaches into the thousands if not millions of data items per second,
   outpacing LLM token processing capabilities for the foreseeable
   future unless other measures are taken to reduce the amount of data
   by several orders of magnitude.  Anomaly detection and trend analysis
   are areas in which AI-based systems play an important role, but not
   areas in which Agentic AI based on LLMs are expected to make a
   considerable impact.  However, this can change once raw data is
   aggregated, filtered, and preprocessed.  This preprocessed data can
   very well serve as input to Agentic AI systems as part of the
   validation and learning/planning portions of the inner control loop
   and we expect corresponding solution architectures to emerge.

   The third loop concerns the "outer" intent control loop that involves
   abstraction and reporting to keep users informed (and, in a bigger
   sense, "in the loop" to understand what and how their network is in
   fact doing).  There are many applications of Agentic AI systems to
   provide decision support, generate smart reports, and highlight
   relevant information.  IBN should not be expected to be any different
   and Agentic AI is thus a clear candidate to implement the abstraction
   and assurance functions in the IBN lifecyle.

4.  IBN Functionality revisited

   The following sections revisit the corresponding sections in
   [RFC9315] where IBN functionality is described.  For a more detailed
   discussion of what precisely the functionality entails, please refer
   to that document.  In the following, we look specifically at the
   ramifications brought about by LLMs and agentic AI for each of those
   functions.

4.1.  Intent Fulfillment

Clemm & Eckert           Expires 7 January 2027                 [Page 5]
Internet-Draft                    AI4AN                        July 2026

4.1.1.  Intent Ingestion and Interaction with Users

   The first set of functions is concerned with having users convey
   intent to the network respectively to the Intent-Based System (IBS)
   that communicates on the network's behalf.  Using agentic AI
   underpinned by LLMs can allow for conversational interaction between
   the user and the IBS.  Not only can the user convey intent using
   plain language, but ambiguities can be resolved, additional context
   requested, missing information identified, priorities established,
   tradeoffs presented, all with minimal learning curve on the side of
   the user.  To be effective, the AI agent needs to have access to data
   about the network, including but not limited to inventory and
   topology information.

4.1.2.  Intent Translation

   Intent translation very closely interacts with intent ingestion; in
   an agentic AI environment both functions may very well be integrated,
   not separated.  Agentic AI will be able to translate ingested intent
   into APIs and structured commands, many of which may be device-
   dependent.  In the past, heterogeneity of device interfaces, command
   interfaces, exposed data models were a major contributing factor to
   the complexity it took to develop operations support systems.  One
   major value that Agentic AI and LLM technology can provide involves
   abstracting this heterogeneity and facilitate the application of
   unified "intent" regardless of the particularities of individual
   device interfaces, determining what specific APIs to call and what
   structured commands to apply depending on the specific network
   device.

4.1.3.  Intent Orchestration

   To the extent that agentic AI can help with planning courses of
   actions, orchestration of rolling out intent across a network is
   another function that can benefit from agentic AI, which can offer
   exceptional planning abilities.  One big concern with any
   orchestration system involves dealing with rainy-day scenarios, for
   example failures in the ability to apply a particular configuration
   to a particular device.  Orchestration systems need to be able to
   anticipate, detect, and mitigate such possibilities, including but
   not limited to rolling the overall network back (or forward) into a
   defined state, as well as containing any potential negative impact.
   It will be imperative for any AI agent involved in intent
   orchestration to have corresponding capabilities, even more
   critically so as to not require to be exposed to device intrinsics
   that the IBN is supposed to abstract away from.

Clemm & Eckert           Expires 7 January 2027                 [Page 6]
Internet-Draft                    AI4AN                        July 2026

4.2.  Intent Assurance

4.2.1.  Monitoring

   Monitoring, in the context of intent assurance, involves observing
   the network, conducting measurements, and collecting telemetry data,
   in order to provide visibility into the network that is required to
   ensure that intent is actually complied with and to assess the degree
   to which desired outcomes are achieved.  Some aspects of monitoring
   are resource-intensive operations that need to be used sparingly.
   Examples include configuration of measurement probes and generating
   test traffic (consuming CPU and bandwidth), collecting telemetry data
   (incurring overhead on production traffic), or continuous streaming
   of statistics about flows, interfaces, and device state (at a
   minimum, involving sampling strategies to keep overhead to an
   acceptable level).  Agentic AI can help optimize monitoring
   strategies by having observations directed at those areas where they
   matter the most, such as providing answers as to where measurement
   probes need to be directed at any one point or which aspects are most
   critical to observe closely and adjust where to probe and what to
   sample accordingly.  Similarly, it can collect additional information
   or run tests that will be helpful to validate hypotheses about what
   fine tuning and adjustements maybe needed and facilitate
   corresponding decisions to do so.

4.2.2.  Intent Compliance Assessment

4.2.3.  Abstraction, Aggregation, Reporting

   Agentic AI is a natural fit to many of the functions that involve
   abstracting and summarizing data and statistics reported from the
   network to human users.  Coupled with the ability to relate the
   observations with context and provide analysis to make actionable
   recommendations, agentic AI can be expected to result in very
   powerful systems in that area going forward.  Previously, the
   interpretation of data required operator expert knowledge and
   programming decision support systems to analyze results was a
   formidable task which will be significantly simplified.

5.  Related Work

   Given the rapid rise of Agentic AI, it is not surprising to see a new
   body of work rapidly emerging that attempt to leverage Agentic AI in
   networking and network management.  While to our knowledge this draft
   is the only one that specifically relates Agentic AI to IBN, there
   are a few other drafts worthwhile mentioning:

Clemm & Eckert           Expires 7 January 2027                 [Page 7]
Internet-Draft                    AI4AN                        July 2026

   *  [I-D.jadoon-nmrg-agentic-ai-autonomous-networks] explores
      augmenting protocol stacks with agentic technology.  In addition
      to looking at how different networking layers might related to AI-
      agentic technology, it proposes an architecture to network agentic
      AI systems in an interoperable manner.  The document is not
      concerned with aspects of Intent-Based Networking.

   *  [I-D.cui-nmrg-llm-nm] concerns itself with using Agentic AI
      systems to assist humans in the management control loop.  It
      proposes an LLM-centered network management system architecture
      that is layered above more conventional non-agentic management
      systems, which in turn is used to manage concentional (i.e., non-
      intent based) networks.

   *  [I-D.hong-nmrg-agenticai-ps] contains a call for bringing agentic
      AI to networking.  It does describe some opportunities and
      challenges to apply agentic AI to network management problems that
      constitute common ground also for Intent-Based Networking.
      However, it does not discuss how these aspects would be applied to
      IBN nor relate them to any of the concepts specified in [RFC9315].

   *  [I-D.eckert-anima-ai4an] describes the application of agentic AI
      to autonomous networking as per IETF's ANIMA working group.
      [RFC7575] serves as a foundational draft there, in which intent is
      already defined as natural complement to autonomous networking.
      Accordingly our document here is a complement to that other draft
      and applies Agentic AI to IBN in a broader sense, not just
      autonomous networks as defined per the ANIMA suite of RFCs.

6.  Acknowledgements

   TBD

7.  Security Considerations

   TBD

8.  Informative References

   [I-D.cui-nmrg-llm-nm]
              Cui, Y., Xing, M., and L. Zhang, "A Framework for LLM
              Agent-Assisted Network Management with Human-in-the-Loop",
              Work in Progress, Internet-Draft, draft-cui-nmrg-llm-nm-
              02, 1 July 2026, <https://datatracker.ietf.org/doc/html/
              draft-cui-nmrg-llm-nm-02>.

Clemm & Eckert           Expires 7 January 2027                 [Page 8]
Internet-Draft                    AI4AN                        July 2026

   [I-D.eckert-anima-ai4an]
              Eckert, T. T. and A. Clemm, "AI for Autonomous
              Networking", Work in Progress, Internet-Draft, draft-
              eckert-anima-ai4an-00, 5 July 2026,
              <https://datatracker.ietf.org/doc/html/draft-eckert-anima-
              ai4an-00>.

   [I-D.hong-nmrg-agenticai-ps]
              Hong, Y., Youn, J., Wu, Q., and B. Claise, "Motivations
              and Problem Statement of Agentic AI for network
              management", Work in Progress, Internet-Draft, draft-hong-
              nmrg-agenticai-ps-02, 5 July 2026,
              <https://datatracker.ietf.org/doc/html/draft-hong-nmrg-
              agenticai-ps-02>.

   [I-D.jadoon-nmrg-agentic-ai-autonomous-networks]
              Jadoon, M. A., Robitzsch, S., and C. J. Bernardos,
              "Agentic AI Architectural Principles for Autonomous
              Computer Networks", Work in Progress, Internet-Draft,
              draft-jadoon-nmrg-agentic-ai-autonomous-networks-00, 2
              March 2026, <https://datatracker.ietf.org/doc/html/draft-
              jadoon-nmrg-agentic-ai-autonomous-networks-00>.

   [RFC7575]  Behringer, M., Pritikin, M., Bjarnason, S., Clemm, A.,
              Carpenter, B., Jiang, S., and L. Ciavaglia, "Autonomic
              Networking: Definitions and Design Goals", RFC 7575,
              DOI 10.17487/RFC7575, June 2015,
              <https://www.rfc-editor.org/rfc/rfc7575>.

   [RFC9315]  Clemm, A., Ciavaglia, L., Granville, L. Z., and J.
              Tantsura, "Intent-Based Networking - Concepts and
              Definitions", RFC 9315, DOI 10.17487/RFC9315, October
              2022, <https://www.rfc-editor.org/rfc/rfc9315>.

Appendix A.  Changelog

   *  draft-cxxx-nmrg-ai4ibn-00: Initial version

Authors' Addresses

   Alexander Clemm
   Individual
   United States of America
   Email: ludwig@clemm.org

Clemm & Eckert           Expires 7 January 2027                 [Page 9]
Internet-Draft                    AI4AN                        July 2026

   Toerless Eckert
   Futurewei Technologies USA
   United States of America
   Email: tte@cs.fau.de

Clemm & Eckert           Expires 7 January 2027                [Page 10]