Skip to main content

Sources of Inter-Agent Conflicts and Approaches to Conflict Resolution in Network Management
draft-janz-nmrg-inter-agent-conflict-resolution-00

Document Type Active Internet-Draft (individual)
Authors Christopher Janz , Fernando Camacho , Lauri Lovén , Per Kangru
Last updated 2026-06-10
RFC stream (None)
Intended RFC status (None)
Formats
Stream Stream state (No stream defined)
Consensus boilerplate Unknown
RFC Editor Note (None)
IESG IESG state I-D Exists
Telechat date (None)
Responsible AD (None)
Send notices to (None)
draft-janz-nmrg-inter-agent-conflict-resolution-00
Network Management Research Group                                C. Janz
Internet-Draft                                                F. Camacho
Intended status: Informational                                    Huawei
Expires: 12 December 2026                                       L. Lovén
                                                      University of Oulu
                                                               P. Kangru
                                                         Viavi Solutions
                                                            10 June 2026

 Sources of Inter-Agent Conflicts and Approaches to Conflict Resolution
                         in Network Management
           draft-janz-nmrg-inter-agent-conflict-resolution-00

Abstract

   Network management is increasingly carried out by autonomous, AI-
   driven agents that observe and act on the network and service state
   they share.  Where their scopes overlap - the same managed entities,
   resources, or objectives - their independent decisions can prove
   mutually inconsistent, and such inter-agent conflict is, at bottom,
   coordination that has not been put in place; the two are best studied
   together.  This document maps the problem for network management:
   where inter-agent conflict comes from, which families of mechanism
   resolve it, and how those mechanisms are chosen and combined.  It
   then turns that map on a case of current interest in the IETF - the
   AI-based Network Management Agent (NMA) architecture - and offers six
   recommendations for strengthening how that architecture handles
   inter-agent conflict at its Agent-to-Agent interface.

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 12 December 2026.

Janz, et al.            Expires 12 December 2026                [Page 1]
Internet-Draft     Inter-Agent Conflict and Resolution         June 2026

Copyright Notice

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

   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.

Table of Contents

   1.  Introduction  . . . . . . . . . . . . . . . . . . . . . . . .   2
   2.  Conventions and Definitions . . . . . . . . . . . . . . . . .   4
   3.  Sources of Inter-Agent Conflict . . . . . . . . . . . . . . .   5
   4.  Approaches to Conflict Resolution: Coordination Mechanism
           Families  . . . . . . . . . . . . . . . . . . . . . . . .   7
     4.1.  When Decentralised Markets Can Be Trusted . . . . . . . .   9
   5.  Selecting and Composing Mechanisms  . . . . . . . . . . . . .   9
     5.1.  Encapsulation as the Load-Bearing Pattern . . . . . . . .  10
     5.2.  Compose Rather Than Choose  . . . . . . . . . . . . . . .  11
     5.3.  A Worked Example  . . . . . . . . . . . . . . . . . . . .  13
   6.  Application to the Proposed IETF Network Management Agent
           Architecture  . . . . . . . . . . . . . . . . . . . . . .  14
     6.1.  The Conflict Surface at A2A . . . . . . . . . . . . . . .  14
     6.2.  Where Conflict Has to Be Resolved: at Analysis and at the
           Decisions . . . . . . . . . . . . . . . . . . . . . . . .  15
     6.3.  NMA / Management-Domain Partitioning Models . . . . . . .  15
   7.  Recommendations to the IETF NMA Work  . . . . . . . . . . . .  17
   8.  Security Considerations . . . . . . . . . . . . . . . . . . .  18
   9.  IANA Considerations . . . . . . . . . . . . . . . . . . . . .  19
   10. Normative References  . . . . . . . . . . . . . . . . . . . .  19
   11. Informative References  . . . . . . . . . . . . . . . . . . .  19
   Acknowledgments . . . . . . . . . . . . . . . . . . . . . . . . .  21
   Authors' Addresses  . . . . . . . . . . . . . . . . . . . . . . .  21

1.  Introduction

   Software agents have spread across every layer of network management.
   They sit at the cross-domain service tier, within individual
   management domains, next to Software-Defined Networking (SDN)
   controllers, and inside the observe-analyse-decide-act loops that
   drive managed entities, and they take on assurance, optimisation,
   configuration, anomaly response, capacity, and lifecycle work.  No
   two are alike: they differ in how much they reason, in how much they
   are permitted to change, in the objectives they serve, and in the
   resources they touch.  What makes them a system rather than a

Janz, et al.            Expires 12 December 2026                [Page 2]
Internet-Draft     Inter-Agent Conflict and Resolution         June 2026

   collection is that their reach overlaps - in what they watch, what
   they control, and what they would alter - and it is in that overlap
   that conflict arises and coordination becomes necessary.

   Conflict and coordination, in this setting, are two descriptions of
   one thing: a conflict left standing between agents is just a
   coordination gap that nothing in the architecture closes, so
   providing the coordination a system needs and heading off the
   conflicts it would otherwise meet are a single task.  That task
   resolves into three questions - what coordination to install, at
   which point in the architecture, and how the added machinery should
   interlock with whatever is already running.  Behind all of them lies
   one larger question: whether agents, growing in number, in
   capability, and in the scope they are licensed to act on, will go on
   coordinating at all.

   This agent-against-agent dimension is, in the authors' view, the part
   most out of step with where the field is going.  Most attention today
   falls elsewhere - on giving a single agent more capability, and on
   the one interface where an agent hands work to the authoritative
   system that carries it out.  How agents get along with each other,
   across the inter-agent interfaces that autonomous-network
   architectures are only now defining, is comparatively neglected, and
   the neglect grows more costly as autonomy rises, because added
   independence multiplies the ways agents can work at cross purposes.
   This document takes up that neglected dimension for network
   management: where inter-agent conflict originates (Section 3), the
   mechanism families that address it (Section 4), and how those are
   chosen and combined (Section 5).  A substantial further aim,
   developed in the second half, is to bring the framework to bear on
   the AI-based Network Management Agent (NMA) under development in the
   IETF (Section 6), ending with six concrete recommendations to that
   effort (Section 7).

   The survey is deliberately not exhaustive on any one technique; the
   goal is a map.  Two bodies of work recur as illustrations.  ETSI's
   Industry Specification Group on Zero-touch network and Service
   Management (ZSM) has produced the most developed treatment of agent
   conflict and coordination of any standards body, and its Management
   Domain construct [ETSI-ZSM-002] furnishes the architectural unit the
   later discussion rests on.  Lovén et al.  [LOVEN2026] offer the
   sharpest current treatment of price-based coordination for agentic
   computing of the kind adjacent to network management.  And a recent
   ETSI study on agents in autonomous networks [ETSI-ZSM-020] speaks
   directly to the case examined here, placing the network-management
   agent inside the Management Domain - the very position this document
   urges on the IETF work.  This document does not update or obsolete
   any existing RFC.

Janz, et al.            Expires 12 December 2026                [Page 3]
Internet-Draft     Inter-Agent Conflict and Resolution         June 2026

   None of this is new to telecommunications, and the framing here
   extends prior work rather than displacing it.  Coordinating self-
   organising functions that contend over shared radio parameters has
   been standardised since 3GPP Release 10, and a broad research
   literature classifies the resulting conflicts and the protective,
   reactive, and proactive remedies for them [SON]; the same concern
   reappears today as the mitigation of clashes among the xApps and
   rApps hosted on the O-RAN near-real-time RIC [ORAN-RIC].  Resolving
   policy conflicts by precedence was studied in distributed-systems
   management long before [LUPU], and the question has resurfaced for
   AI-assisted control loops in early 6G work [PARSAEEFARD].  The
   contribution here is to draw these strands into one frame -
   separating conflicts visible on inspection from those that emerge
   only in joint fulfilment, using encapsulation to connect work in
   markets, control, and learning, and marking the single-epoch /
   repeated-operation divide as the place the hard problems concentrate.

2.  Conventions and Definitions

   The key words "MUST", "MUST NOT", "REQUIRED", "SHALL", "SHALL NOT",
   "SHOULD", "SHOULD NOT", "RECOMMENDED", "NOT RECOMMENDED", "MAY", and
   "OPTIONAL" in this document are to be interpreted as described in BCP
   14 [RFC2119] [RFC8174] when, and only when, they appear in all
   capitals, as shown here.

   Agent:
      an entity to which an owner has delegated operational goals (its
      intents), and which serves them by drawing inferences from what it
      can observe and producing outputs that affect the managed state,
      adjacent components, or its peers.  The term is used inclusively
      for the two kinds below.  An action-bearing agent runs as an
      operational closed loop and so alters network or service state
      directly; an information-producing agent confines itself to
      observing, analysing, and reporting, and never acts on a managed
      entity.

   Closed Loop (CL):
      an operational observe-analyse-decide-act cycle over managed
      entities, in the sense of [ETSI-ZSM-009-1].

   Management Domain (MD):
      the architectural unit of management authority defined in
      [ETSI-ZSM-002]: the entity that holds authoritative network state,
      maps requests onto resources, and enforces its own pre-configured
      policies and decision logic.  An End-to-End Service MD (E2ES MD)
      fronts a complete ZSM framework externally and orchestrates
      delivery across the underlying domain MDs.

Janz, et al.            Expires 12 December 2026                [Page 4]
Internet-Draft     Inter-Agent Conflict and Resolution         June 2026

   Network Management Agent (NMA), Agent-to-Agent (A2A) interface:
      the AI-driven entity for Level 4 (L4) autonomous-network
      operations, and the interface by which NMAs interact with one
      another and with non-AI components, both defined in
      [I-D.zhao-nmop-network-management-agent].

3.  Sources of Inter-Agent Conflict

   Network management hosts two structurally different kinds of agent,
   and which kind is in play determines where conflict can occur.  An
   action-bearing agent alters network or service state; because each of
   its actions might clash with another agent's action, or with standing
   policy and configuration, its exposure is broad.  An information-
   producing agent only senses, analyses, and reports, touching no
   managed entity directly, so it enters conflict only at one remove -
   through the action-bearing agents it informs.  The upshot is that
   exposure to conflict is created by acting, not by reasoning, and the
   taxonomy that follows is anchored at the action layer.  Disagreements
   over state - two agents holding incompatible pictures of the network
   - obey the same logic: they signify only insofar as they push agents
   toward divergent actions, and are otherwise the job of the state-
   synchronisation layer beneath the action layer.  That layer, not the
   mechanisms catalogued here, is where the inconsistent-state case
   raised by the NMA draft [I-D.zhao-nmop-network-management-agent]
   belongs (see Section 6.1).

   When action-bearing agents act independently, two or more can land on
   actions that cannot all be true together: inconsistent logically
   (contradictory demands on one target), structurally (not jointly
   executable on one entity at one time), consequentially (their
   downstream effects interfere), or compositionally (an action runs
   against a policy or configuration set outside the agent layer).  The
   five types below organise these.

   Hard contradictions:
      two demands that cannot both be honoured - no assignment of
      resources, no plan, and no order of execution will satisfy them
      together.  The stock example from intent-driven networking
      [ETSI-ZSM-011] pits one intent's cell-throughput ceiling below 5
      Mbps against another's floor above 8 Mbps on that same cell.  Such
      conflicts usually show under inspection - intent translation tends
      to expose them - and are settled by refusing the request,
      returning it to the intent owner, or applying a priority rule.

   Soft contradictions:
      demands that pull against one another without being flatly
      irreconcilable, and the kind of conflict most common in operation.
      ETSI GS ZSM 016 [ETSI-ZSM-016] sets a floor on bandwidth against a

Janz, et al.            Expires 12 December 2026                [Page 5]
Internet-Draft     Inter-Agent Conflict and Resolution         June 2026

      ceiling on cost: more capacity usually costs more, yet for any
      specific pair of thresholds it is generally unknowable in advance
      whether both can hold.  The remedy is one of degree - balancing
      utilities, negotiating, pricing - rather than refusal.  Two sub-
      cases recur: contention for a bounded resource (link bandwidth,
      compute, inference slots) and trade-offs between competing
      objectives (latency against throughput, energy against coverage,
      cost against reliability).

   Action and ordering conflicts:
      two agents would act on one entity such that the outcome turns on
      whether one goes first, second, or at the same time - network
      management's version of database serialisability.  ETSI GS ZSM
      009-1 [ETSI-ZSM-009-1] handles it as concurrency coordination, and
      the cure is to sequence or serialise the accesses, with closed-
      loop priority or policy deciding the order.

   Impact-level conflicts:
      two actions run at once on different entities, yet one's
      downstream effect cancels or erodes the other's aim - the textbook
      pairing [ETSI-ZSM-011] being a coverage-improving antenna tilt
      undone by a power-saving feature.  This is the most difficult
      class, since the clash happens in the running system rather than
      in any specification.  Catching it needs either a prospective tool
      - virtual actuation on a Network Digital Twin [ETSI-ZSM-018] - or
      a retrospective one, post-execution impact assessment
      [ETSI-ZSM-009-1].

   Intent-versus-non-intent conflicts:
      an intent-driven action meets a constraint that was never
      expressed as an intent at all - a lower-layer policy, a manually
      applied configuration, a built-in rule [ETSI-ZSM-011] - and,
      unlike the intent-versus-intent case, there is no counterpart to
      bargain with; the constraint simply is.  The NMA draft
      [I-D.zhao-nmop-network-management-agent] records essentially this,
      as a clash between an NMA's dynamically generated policy and a
      controller's standing one.  The way out is to raise the non-intent
      constraint to intent level - turning the clash into intent-versus-
      intent - or to apply precedence.

   A further split runs through every one of the five and, for the
   choice of mechanism, tends to matter more than which type a conflict
   is: does it show itself when one inspects specifications, intents,
   and plans, or only when the system attempts to meet all the operative
   intents together?  As the intent-driven closed-loop work notes
   [ETSI-ZSM-016], a conflict's reality and its severity frequently
   surface only while a joint fulfilment is being sought.  The soft and
   impact-level kinds fall disproportionately on this emergent side; an

Janz, et al.            Expires 12 December 2026                [Page 6]
Internet-Draft     Inter-Agent Conflict and Resolution         June 2026

   effective intent - one thrown up by several explicit intents working
   together - can likewise appear only there, betrayed by its own non-
   fulfilment.  The design consequence is sharp: the inspectable kind
   yields to pre-commitment checkers, whereas the emergent kind demands
   exploratory search before commitment plus assessment afterwards, so
   an architecture built only for the first is weakest exactly where it
   can least afford to be.

4.  Approaches to Conflict Resolution: Coordination Mechanism Families

   The catalogue below is ordered by how much central control each
   exerts, the most directive first and the lightest peer- and price-
   based schemes last; these are the options an agent-coordination
   architecture can draw on.  None stands alone in practice, and how
   they combine is the subject of Section 5.

   Imperative arbitration:
      a coordinator settles the matter outright - by priority, override,
      resource partitioning, or serialised access.  ETSI GS ZSM 009-1
      [ETSI-ZSM-009-1] provides exactly such levers in its closed-loop
      priority attribute, action enable/disable, and concurrency
      coordination.  The approach is dependable and transparent but does
      not scale to many agents with conflicting preferences, and it fits
      inspectable conflicts for which a defensible priority or partition
      is available.

   Utility reconciliation:
      a utility is attached to each intent, and a handler chooses the
      joint action that maximises some aggregate of them - commonly a
      weighted sum, as in ETSI GS ZSM 016 [ETSI-ZSM-016].  It fits
      conflicts of degree; its hard parts are putting utilities on one
      scale and an aggregation rule that silently bakes in operational
      choices.

   Markets and micro-economic mechanisms:
      prices do the coordinating - bids go in, a clearing step returns
      allocations.  ETSI GR ZSM 019 [ETSI-ZSM-019] already frames
      resource allocation among Network-as-a-Service consumers as
      something to be run economically via service pricing.  When
      decentralised markets can be relied on is the subject of Lovén et
      al.  [LOVEN2026], summarised in Section 4.1.  The family fits
      resource contention among many agents holding private valuations
      with no single trusted authority; it serves badly where the
      dispute is over ends, not resources.

   Negotiation:
      agents trade offers and concessions toward an outcome all can
      accept, requiring no shared currency and tolerating reservation

Janz, et al.            Expires 12 December 2026                [Page 7]
Internet-Draft     Inter-Agent Conflict and Resolution         June 2026

      values kept private; formalised by the FIPA Agent Communication
      Language [FIPA] and the Contract Net Protocol.  Both ETSI GR ZSM
      011 [ETSI-ZSM-011] and ETSI GR ZSM 019 [ETSI-ZSM-019] already rely
      on it.

   Argumentation:
      every agent argues for and against the options on the table, and
      which argument defeats which is modelled explicitly [DUNG].  This
      is the family to reach for when the reasoning has to stand up -
      when a decision must be explained and defended, not merely shown
      optimal - and for norm clashes that have no shared utility scale.

   Distributed constraint optimization (DCOP):
      the conflict is written as weighted constraints over variables
      owned by different agents, and a least-cost joint assignment is
      computed [DCOP].  It fits any conflict that can be cast as
      constraints across a countable agent set; what ETSI GS ZSM 009-1
      [ETSI-ZSM-009-1] does at its action-plan-selection step is, in
      effect, a small DCOP.

   Normative regulation:
      rules - permissions, prohibitions, obligations - forestall
      conflict by bounding what agents may do, and are already
      everywhere in ZSM as governance state, trust scores, and
      capability profiles.  Since no rule set foresees every situation,
      this family nearly always runs alongside others.

   Social choice and voting:
      preferences of symmetric peers are aggregated by a voting rule; in
      network management this tends to be a building block (consensus
      among redundant analytics agents, say) rather than the main
      mechanism.

   Multi-agent reinforcement learning (MARL):
      coordination is learned from experience instead of prescribed by a
      protocol - adaptable when the shape of the conflict cannot be
      known in advance, but offering weak guarantees, so under firm
      service-level agreements it serves better as an adjunct than as
      the principal layer.

   Digital-twin-based exploration:
      candidate joint actions are rehearsed on a digital twin and only
      the ones that come through are committed.  ETSI GS ZSM 016
      [ETSI-ZSM-016] spells this out through the Network Digital Twin of
      ETSI GS ZSM 018 [ETSI-ZSM-018] and the virtual-actuation loop of
      ETSI GR ZSM 009-3 [ETSI-ZSM-009-3].  It is the natural answer to
      impact-level and emergent conflicts, provided it fits the
      operational latency budget.  The twin serves twice over: as a gate

Janz, et al.            Expires 12 December 2026                [Page 8]
Internet-Draft     Inter-Agent Conflict and Resolution         June 2026

      that admits or rejects candidates before commitment, and as ground
      on which the other families rank the survivors - utility
      reconciliation scoring them against intent utilities read off the
      twin, or DCOP solved against twin-derived costs.  How far a twin
      can be trusted - whether to use it only to rank and reject
      candidates, or to rely on it for stronger assurances - depends on
      the fidelity of the particular implementation, which varies and
      has to be established case by case.

4.1.  When Decentralised Markets Can Be Trusted

   Whether the market family can be relied on turns on a structural
   property that is simple to state.  Lovén et al.  [LOVEN2026] identify
   the decisive factor as how entangled the dependencies among services
   are.  Where those dependencies stay simple - broadly, tree-shaped,
   free of cross-cutting ties between stages of a service chain - a
   decentralised market provably matches what a fully-informed central
   planner would choose, and nobody profits by misstating what they
   value.  Where they grow entangled, the guarantees collapse: prices
   may fail to settle, the optimal allocation becomes computationally
   hard, and no plain two-sided market can be efficient, fair, and self-
   financing all at once.  The takeaway is that it is the shape of the
   composition, not algorithmic ingenuity, that decides whether a
   decentralised market holds up - and an awkward shape can frequently
   be domesticated by hiding the hard part behind a cleaner interface
   (Section 5.1).  Because this work is a preprint still under review,
   its results warrant reliance only as far as the preprint itself
   proves them; and they are single-epoch, so the cross-epoch
   manipulation noted in Section 5 falls outside their reach.

5.  Selecting and Composing Mechanisms

   Which families fit is largely fixed by the conflict type, and the
   place the decision is taken is fixed by where, relative to a
   Management Domain (MD), the relevant information sits - inside one
   domain's own machinery (intra-MD), across domains via the A2A
   interface or a cross-domain integrator (inter-MD), or at the end-to-
   end (E2E) service layer.  Table 1 sets out both; in practice a
   deployment will draw on several of its rows, at several loci, at
   once.

Janz, et al.            Expires 12 December 2026                [Page 9]
Internet-Draft     Inter-Agent Conflict and Resolution         June 2026

   +================+===========================+======================+
   | Conflict type  | Well-suited families      | Where decided        |
   +================+===========================+======================+
   | Hard           | Imperative arbitration;   | Intra-MD at          |
   | contradictions | refusal and re-           | earliest check;      |
   |                | negotiation; precedence   | inter-MD via A2A     |
   |                |                           | across MDs           |
   +----------------+---------------------------+----------------------+
   | Soft -         | Utility reconciliation;   | Intra-MD; inter-     |
   | objective      | negotiation;              | MD via A2A; E2E      |
   | trade-offs     | argumentation             | for cross-service    |
   +----------------+---------------------------+----------------------+
   | Soft -         | Markets; partitioning;    | Intra-MD resource    |
   | resource       | priority queues; DCOP     | layer; inter-MD      |
   | contention     |                           | at integrator        |
   +----------------+---------------------------+----------------------+
   | Action and     | Pre-execution detection;  | Intra-MD on owned    |
   | ordering       | concurrency coordination; | entities; inter-     |
   |                | priority; DCOP            | MD via A2A on        |
   |                |                           | shared entities      |
   +----------------+---------------------------+----------------------+
   | Impact-level   | Digital-twin exploration; | Intra-MD NDT;        |
   |                | merged analysis-and-      | cross-MD twin at     |
   |                | decision; post-hoc impact | E2E                  |
   |                | assessment                |                      |
   +----------------+---------------------------+----------------------+
   | Intent versus  | Normative regulation;     | Intra-MD intent/     |
   | non-intent     | argumentation; lifting    | policy layer;        |
   |                | into intent; precedence   | supra-MD             |
   |                |                           | governance           |
   +----------------+---------------------------+----------------------+

      Table 1: Conflict type, the families that suit it, and where the
                             decision is taken.

5.1.  Encapsulation as the Load-Bearing Pattern

   A deeper recent finding is that some structural complexity simply
   resists any clean, fully distributed handling; the response is not to
   centralise everything, nor to decentralise harder, but to encapsulate
   - seal the hard sub-problem inside a boundary whose outward face is
   simple, run it centrally within, and let the world outside coordinate
   lightly.  The move shows up in three literatures.  Lovén et al.'s
   cross-domain integrators [LOVEN2026] take an entangled sub-
   composition and offer the market just one composite slice in its
   place - a slice that stays well-behaved outwardly only under stated
   conditions, something the integrator is built to secure rather than
   something it gets for free.  The nested closed loops of ETSI GR ZSM

Janz, et al.            Expires 12 December 2026               [Page 10]
Internet-Draft     Inter-Agent Conflict and Resolution         June 2026

   009-3 [ETSI-ZSM-009-3] make a set of interdependent loops look, from
   outside, like one loop.  And cooperative MARL's centralised-training/
   decentralised-execution is the same trick expressed in rewards.  The
   corollary: for some structural complexity there is no middle road -
   the realistic choice is encapsulation under central control, or
   breakdown.

5.2.  Compose Rather Than Choose

   In practice no architecture leans on a single family, and that fact
   deserves to be the stated default.  Our suggested default is built
   from three legs.  The first is a normative envelope - permissions,
   prohibitions, priorities, partitions, in today's agentic vocabulary a
   guardrail layer - that fences off the admissible actions, so anything
   unsafe, non-compliant, or beyond an agent's remit never reaches the
   table as a candidate; coordination, seen this way, is as much
   prevention as cure.  The second is one or more decision mechanisms
   working inside that fence, chosen by conflict type per Table 1.  The
   third tries candidates out on a digital twin ahead of committing, and
   stands a diagnostic leg behind that for whatever still slips through
   - in the near term, a fall back to a last-known-good configuration
   and a page to an operator.  The legs back one another up: a decision
   mechanism without exploration is fragile against emergent conflict,
   exploration without a fence is unbounded, and a diagnostic leg
   pressed into front-line service is an expensive net (Figure 1).  ETSI
   GS ZSM 016 [ETSI-ZSM-016] (partitioning, utility reconciliation, twin
   exploration), ETSI GR ZSM 019 [ETSI-ZSM-019] (governance overlay,
   pricing, negotiation), and Lovén et al.  [LOVEN2026] (governance,
   slice market, integrator) each instantiate it; only the middle leg
   changes.

Janz, et al.            Expires 12 December 2026               [Page 11]
Internet-Draft     Inter-Agent Conflict and Resolution         June 2026

      candidate actions from agents
                   |
                   v
      +-------------------------------------------------+
      | 1. Normative envelope (guardrail layer):        |
      |    permissions, prohibitions, priorities,       |
      |    partitions - bounds the admissible actions   |
      +-------------------------------------------------+
                   |
                   v
      +-------------------------------------------------+
      | 2. Decision mechanism(s), chosen by conflict    |
      |    type: utility, market, negotiation, DCOP,    |
      |    argumentation, or imperative arbitration     |
      +-------------------------------------------------+
                   |
                   v
      +-------------------------------------------------+
      | 3a. Exploratory leg (before commit): digital-   |
      |     twin actuation; vet and rank candidates     |
      +-------------------------------------------------+
                   |
                   v   committed action
      +-------------------------------------------------+
      | 3b. Diagnostic leg (after commit): impact       |
      |     assessment; rollback + operator escalation  |
      +-------------------------------------------------+

         Figure 1: The recommended three-leg default.  A normative
         envelope fences the action space; mechanisms selected per
          conflict type run within it; an exploratory leg screens
      candidates before commitment, and a diagnostic leg handles what
                          only appears afterwards.

   Two further points round out the picture.  First, a mechanism built
   on the premise that every conflict can be foreseen will fail
   precisely on the emergent ones that dominate live operation; the
   exploratory and diagnostic legs, then, are not optional trimmings but
   the parts that carry the usual case.  Second, since the cost of
   coordinating is largely the cost of shipping information between
   agents, coordination should sit where that information already is:
   centralise locally within a domain or trust boundary, and use lighter
   machinery between boundaries.  Hard questions stay open - designing
   mechanisms for the emergent case, keeping incentives sound once
   decisions repeat across epochs, conflicts among the composed
   mechanisms themselves, and re-composition as the agent population
   shifts.  On the cross-epoch front there is progress: [LOVEN-TRILEMMA]
   shows that when agents persist and learn, single-epoch guarantees

Janz, et al.            Expires 12 December 2026               [Page 12]
Internet-Draft     Inter-Agent Conflict and Resolution         June 2026

   stop bounding behaviour and even the marketplace operator turns
   strategic, with a flat lesson - watching for cheating does not
   discourage it, and only structural remedies (binding commitment,
   administrative separation, competition among providers) take the
   incentive away.  Treat single-epoch guarantees as though they
   extended to non-stop operation, and the problem has been mis-framed
   from the outset.

5.3.  A Worked Example

   A single end-to-end scenario shows the map at work and leads into the
   agent-and-domain discussion of Section 6.  Take a live ultra-
   reliable, low-latency slice whose capacity is being raised.  Four
   closed-loop management functions act: one drives the slice
   modification; a transport-side function recomputes paths and queue
   weights, converging over seconds to minutes; a radio-side function
   retunes the slice's resource-block share within a fraction of a
   second; and admission control goes on admitting sessions, now to the
   larger quota.  Individually all four are correct; the trouble is the
   spread of their timescales.  Anticipating the change, the radio loop
   has already pared back a neighbouring donor slice's resource-block
   allotment; the transport loop's revised queue weights have not yet
   taken effect; and admission is already letting sessions in at the
   new, higher quota.  Across the convergence window the donor slice
   drops below its latency target and its edge users come up short on
   throughput.  Under the taxonomy of Section 3 the clash is impact-
   level, and it sits well toward the emergent end: inspected request by
   request nothing trips an alarm, because what collides is the timing
   interplay of three loops, not anything in a single specification.

   The prescription follows from Table 1 and Section 5.2.  A normative
   envelope - latency floors and resource-block ceilings, one set per
   slice - bounds the proposals any loop can make; a utility step,
   weighted by each slice's revenue and exposure to penalties, settles
   on one plan covering both the modification and the admissions; a
   digital-twin leg trials each candidate and drops the dangerous ones;
   and a diagnostic leg, falling back to a known-good configuration and
   paging an operator, mops up what the twin gets wrong.  No one family
   does the whole job.  And in NMA terms the place this conflict is
   settled - within one Management Domain or out across the Agent-to-
   Agent interface - depends on whether these functions live as co-
   located services or as separate agents in different domains, which is
   precisely the partitioning question the next section opens.

Janz, et al.            Expires 12 December 2026               [Page 13]
Internet-Draft     Inter-Agent Conflict and Resolution         June 2026

6.  Application to the Proposed IETF Network Management Agent
    Architecture

   The framework above applies directly to a timely case.  The IETF
   Network Management Operations (NMOP) working group is developing
   [I-D.zhao-nmop-network-management-agent], which defines an AI-based
   Network Management Agent for Level 4 (L4) autonomous-network
   operations: internally the four-stage observe-analyse-decide-act loop
   made AI-explicit (perception, reasoning, planning, and action modules
   with knowledge and memory), with an Agent-to-Agent (A2A) interface by
   which NMAs interact with one another and with non-AI components.
   Alongside the ZSM corpus the NMA overlaps the role of the ZSM closed
   loop; the vocabularies differ but the concerns are largely the same.
   The discussion here is constructive: the draft's direction is sound,
   and the aim is to deepen its treatment of agent coordination to match
   the autonomy ambitions of L4.

   The draft's repeated invocation of "SDN controller" is best read,
   more durably, as standing in for the entity the NMA hands intent or
   policy to - the thing that holds authoritative network state, maps
   requests onto resources, and has its own pre-configured policies.  In
   a forward-looking architecture that entity is a ZSM Management Domain
   (MD) [ETSI-ZSM-002]: a per-technology or per-administrative domain MD
   where the NMA acts at domain scope, or the E2ES MD where it acts on
   services spanning domains.  The stand-alone SDN controller of the
   2010s is either a legacy artifact within such an MD or a transitional
   shorthand for one.  The substitution sharpens the analysis and
   propagates cleanly to alignment with the ZSM corpus, which already
   speaks the MD language; "MD" is used below where the draft would say
   "SDN controller".

6.1.  The Conflict Surface at A2A

   The draft acknowledges two conflict types, both NMA-versus-MD cases
   under the reading above: configuration-and-policy conflicts (the
   NMA's intent-derived dynamic policy collides with the MD's pre-
   configured policy) and inconsistent network-state synchronisation
   (the NMA's internal model and the MD's authoritative view drift
   apart).  Both are real.  But the MD's side is not a passive component
   to be overridden; it is itself a composition of internal decision
   logic - closed loops, intent translation, resource management, policy
   enforcement - each a decision locus with its own conflict-handling
   responsibilities, so the NMA-versus-MD surface composes against the
   MD's whole apparatus.

   More conspicuously, the NMA-versus-NMA case - two action-bearing
   agents conflicting at A2A - is essentially absent, even though A2A is
   defined precisely as the locus where multiple NMAs interact.  An

Janz, et al.            Expires 12 December 2026               [Page 14]
Internet-Draft     Inter-Agent Conflict and Resolution         June 2026

   architecture that defines an inter-agent interface without defining
   how conflict there is detected and resolved has left the interesting
   work undone.  Under L4 autonomy with multiple NMAs (per-tenant, per-
   service, per-region, or per-layer), every conflict type of Section 3
   becomes available at A2A.  L4 autonomy widens this surface rather
   than narrowing it: more independent decision authority means more
   candidate collisions and less scope for human intervention to catch
   what the architecture missed.  A2A needs to be the locus where this
   surface is detected, characterised, and resolved - not merely an
   interface for state exchange - and it must compose with the conflict-
   handling the MD already performs per ETSI GS ZSM 009-1
   [ETSI-ZSM-009-1], ETSI GR ZSM 011 [ETSI-ZSM-011], and ETSI GS ZSM 016
   [ETSI-ZSM-016].

6.2.  Where Conflict Has to Be Resolved: at Analysis and at the
      Decisions

   Every state-changing action is the output of a decide step somewhere,
   and in any real architecture that step is plural: an MD composes
   several internal decision loci, and an NMA contributes one or more
   inside or outside it.  Handling conflict only at those decide loci is
   too narrow, though.  The analyse stage of the loop can head it off
   earlier: an agent that already knows of other live intents, policies,
   or proposed plans will analyse differently - it may form a different
   plan, reassess an expected impact, or set aside a class of action
   that, considered on its own, looked best.  What the analyse stage
   does not catch falls to three later modes: before any decide locus
   (pre-execution detection of inspection-detectable cases), jointly
   inside a decide locus (utility aggregation, market clearing, DCOP, or
   negotiation, where soft contradictions are usually resolved), and
   after all of them (post-hoc impact assessment and remediation per
   ETSI GS ZSM 009-1 [ETSI-ZSM-009-1]); earlier is cheaper.  Some
   conflicts - notably resource contention - are visible only at the
   locus that sees the resource layer, typically inside the MD, so their
   surfacing there is by design, not a failure of the NMA-level
   decision.  The architectural question is therefore not where "the"
   decide step lives but how authority is distributed across NMAs and
   MDs, what each locus can see, and how conflict feeds back between
   them.

6.3.  NMA / Management-Domain Partitioning Models

   Five models describe how an NMA can compose with an MD.  Real
   deployments mix them, but the pure models clarify the choices, and
   Model C is the cleanest, most ZSM-aligned positioning - and the one
   ETSI's own study on agents in autonomous networks [ETSI-ZSM-020] has
   already adopted, placing the NMA inside the Management Domain.

Janz, et al.            Expires 12 December 2026               [Page 15]
Internet-Draft     Inter-Agent Conflict and Resolution         June 2026

   A - NMA-above-MD:
      the NMA is the cognitive layer, handing requests down to an MD
      whose internal logic remains first-class.  Conflicts arise both at
      A2A above the MD and at the NMA-MD boundary, so coordination needs
      a feedback path, not just a command path.

   B - NMA-and-MD as peers:
      both independently change the same entities.  This is the draft's
      implicit default.  It is usually transitional, an artifact of
      imperfect separation, and most deployments should refactor toward
      C or A.

   C - NMA-inside-MD (recommended default; the ZSM 020 positioning):
      the NMA is a management service within an MD, alongside closed
      loops, intent reasoners, and resource managers.  The MD remains
      the unit of authority; conflict resolution is internal and uses
      the machinery ETSI GS ZSM 009-1, ETSI GR ZSM 011, and ETSI GS ZSM
      016 already specify.  This is the positioning ETSI has adopted for
      the ZSM corpus: ETSI GR ZSM 020 [ETSI-ZSM-020] places the NMA
      inside the Management Domain.  Most of the surface the draft names
      dissolves; what A2A genuinely needs to support is NMAs in
      different MDs or at the E2E layer.

   D - Federated NMAs across MDs:
      NMAs at one level coordinate across several MDs - the natural case
      for cross-domain integrators or per-tenant, per-service, or per-
      region NMAs.  Markets and inter-domain negotiation live here.

   E - Layered NMAs across strata:
      an E2E-layer NMA above per-domain MDs, with vertical A2A, mapping
      onto ZSM's E2E service MD above per-technology MDs.  Conflict
      flows both up and down.  D and E combine freely, with A, B, or C
      as the per-NMA choice within them.

   Mechanism families map onto these models predictably.  Imperative
   arbitration and normative regulation are native to the MD, where
   authoritative policy lives.  Markets need peer entities with private
   valuations and a resource layer to clear against, so Model D is their
   home and the ETSI GR ZSM 019 [ETSI-ZSM-019] NaaS picture lives there.
   The intent-reconciliation families can live intra-MD (Model C) or
   across A2A (Models D and E), so their protocol semantics must support
   both; digital-twin exploration belongs at the highest scope at which
   the joint action can be simulated - a domain NDT, or a cross-MD twin
   at the E2E layer.

Janz, et al.            Expires 12 December 2026               [Page 16]
Internet-Draft     Inter-Agent Conflict and Resolution         June 2026

7.  Recommendations to the IETF NMA Work

   Six recommendations follow, constructive in intent: the draft's
   direction is right, and these deepen its agent-coordination dimension
   to match L4.

   R1 - Adopt an explicit conflict taxonomy at A2A:
      the taxonomy of Section 3 (and ETSI GS ZSM 009-1, GR ZSM 011, GS
      ZSM 016) applies to both the NMA-versus-NMA and NMA-versus-MD
      surfaces.  The draft SHOULD adopt it rather than re-derive a
      parallel one, naming hard contradictions, soft contradictions
      (with resource contention and objective trade-offs), action and
      ordering conflicts, impact-level conflicts, and intent-versus-non-
      intent collisions at both surfaces.

   R2 - Treat A2A as the locus for detection, resolution, and
   feedback:
      the draft SHOULD define A2A hooks for pre-execution conflict
      detection (exchange of intents, plans, candidate actions in a
      checkable form), for resolution (exchange of utilities, arguments,
      priced offers), and for feedback from conflicts surfaced at MD-
      internal loci.  The feedback path MUST NOT be assumed to flow only
      top-down.

   R3 - Adopt NMA-inside-MD (Model C) as the default - the ZSM-locked
   positioning:
      Model C is the cleanest positioning, dissolves most of the surface
      the draft names, and aligns with existing ZSM machinery.
      Critically, it is also the positioning ETSI has already committed
      to: ETSI GR ZSM 020 [ETSI-ZSM-020] locks the NMA inside the
      Management Domain.  Adopting Model C as the IETF default is
      therefore not only the cleanest choice but the one that keeps IETF
      NMOP and ETSI ZSM structurally aligned at the locus where AI-
      driven agents meet authoritative network state - a convergence the
      two bodies would otherwise have to engineer after the fact.  The
      draft SHOULD adopt it as default, catalogue A, B, D, and E as
      alternatives, and SHOULD resist defaulting implicitly to Model B
      (peers), the hardest model to coordinate.

   R4 - Layer conflict handling across MD topology:
      four cases need separate treatment - intra-MD coordination among
      services (including the NMA in Model C), intra-MD peer A2A, inter-
      MD A2A, and the NMA-MD boundary (Models A and B).  Each admits
      different families; collapsing them onto one undifferentiated A2A
      definition loses the distinctions.

Janz, et al.            Expires 12 December 2026               [Page 17]
Internet-Draft     Inter-Agent Conflict and Resolution         June 2026

   R5 - Pick a small initial mechanism set, with extension hooks:
      imperative arbitration, utility reconciliation, negotiation, and
      normative regulation are a suitable starter set covering most
      inspection-detectable and joint-decision cases.  Markets,
      argumentation, DCOP, social choice, MARL, and digital-twin
      exploration can follow as extensions, with A2A providing explicit
      hooks rather than one fixed coordination model.

   R6 - Read "SDN controller" as "ZSM Management Domain":
      adopt the ETSI GS ZSM 002 [ETSI-ZSM-002] MD vocabulary, name the
      domain-MD-versus-E2ES-MD distinction where it matters, and frame
      the NMA's interaction with what it now calls an SDN controller as
      an NMA-versus-MD interaction.  This propagates cleanly to
      alignment with the ZSM corpus and avoids parallel re-derivation in
      adjacent bodies.

8.  Security Considerations

   Inter-agent conflict handling introduces considerations beyond
   conventional model-driven management.  Any decision that resolves a
   conflict by changing network or service state - an arbitration
   override, a market allocation, a negotiated concession, an action
   committed after digital-twin exploration - MUST be subject to
   authorisation appropriate to the agent's operational role and MUST be
   auditable after the fact.  Where resolution depends on inputs
   exchanged between agents (utilities, preferences, priced offers,
   arguments, natural-language descriptions), an adversary able to
   influence those inputs could drive the outcome; implementations
   SHOULD attach provenance and confidence to such inputs and apply the
   trust and incentive mechanisms appropriate to the family in use,
   recognising that market incentive guarantees are per-epoch and do not
   preclude cross-epoch manipulation.

   Conflict resolved only after the fact widens the window during which
   an incorrect or adversarially induced action affects the live
   network; implementations SHOULD prefer pre-commitment exploration
   where the latency budget allows.  The A2A interface, as a new locus
   for exchanging intents, plans, and candidate actions, is itself an
   attack surface: it MUST provide authentication of the communicating
   agents, integrity and confidentiality of the exchange, and
   authorisation of the actions an exchange can trigger.  Where
   resolution involves disclosing more granular information than usual,
   policy controls MUST govern what may be disclosed, to whom, and under
   what conditions.  Finally, AI-driven agents inherit the general risks
   of large-language-model-based systems - prompt injection,
   hallucination, miscalibrated confidence - and implementations SHOULD
   apply the usual mitigations and require human review for resolutions
   whose consequences are operationally significant.

Janz, et al.            Expires 12 December 2026               [Page 18]
Internet-Draft     Inter-Agent Conflict and Resolution         June 2026

9.  IANA Considerations

   This document has no IANA actions.

10.  Normative References

   [RFC2119]  Bradner, S., "Key words for use in RFCs to Indicate
              Requirement Levels", BCP 14, RFC 2119,
              DOI 10.17487/RFC2119, March 1997,
              <https://www.rfc-editor.org/info/rfc2119>.

   [RFC8174]  Leiba, B., "Ambiguity of Uppercase vs Lowercase in RFC
              2119 Key Words", BCP 14, RFC 8174, DOI 10.17487/RFC8174,
              May 2017, <https://www.rfc-editor.org/info/rfc8174>.

11.  Informative References

   [I-D.zhao-nmop-network-management-agent]
              Zhao, C., "AI based Network Management Agent (NMA):
              Concepts and Architecture", Work in Progress, Internet-
              Draft, draft-zhao-nmop-network-management-agent, February
              2026, <https://datatracker.ietf.org/doc/html/draft-zhao-
              nmop-network-management-agent>.

   [ETSI-ZSM-002]
              ETSI ISG ZSM, "Zero-touch network and Service Management
              (ZSM); Reference Architecture", ETSI GS ZSM 002 V1.1.1,
              August 2019.

   [ETSI-ZSM-009-1]
              ETSI ISG ZSM, "Zero-touch network and Service Management
              (ZSM); Closed-Loop Automation; Part 1: Enablers", ETSI GS
              ZSM 009-1 V1.1.1, June 2021.

   [ETSI-ZSM-009-3]
              ETSI ISG ZSM, "Zero-touch network and Service Management
              (ZSM); Closed-Loop Automation; Part 3: Advanced Topics",
              ETSI GR ZSM 009-3 V1.1.1, 2023.

   [ETSI-ZSM-011]
              ETSI ISG ZSM, "Zero-touch network and Service Management
              (ZSM); Intent-driven Autonomous Networks; Generic
              Aspects", ETSI GR ZSM 011 V2.1.1, September 2024.

   [ETSI-ZSM-016]
              ETSI ISG ZSM, "Zero-touch network and Service Management
              (ZSM); Intent-driven Closed Loops", ETSI GS ZSM 016
              V1.1.1, October 2024.

Janz, et al.            Expires 12 December 2026               [Page 19]
Internet-Draft     Inter-Agent Conflict and Resolution         June 2026

   [ETSI-ZSM-018]
              ETSI ISG ZSM, "Zero-touch network and Service Management
              (ZSM); Network Digital Twin", ETSI GS ZSM 018, 2025.

   [ETSI-ZSM-019]
              ETSI ISG ZSM, "Zero-touch network and Service Management
              (ZSM); ZSM Framework for Network-as-a-Service (NaaS)",
              ETSI GR ZSM 019 V1.1.1, January 2026.

   [ETSI-ZSM-020]
              ETSI ISG ZSM, "Zero-touch network and Service Management
              (ZSM); Study on the Utilization of Agents in Autonomous
              Networks", ETSI GR ZSM 020 V1.1.1, January 2026.

   [LOVEN2026]
              Lovén, L., Saleh, A., Farahani, R., Murturi, I., Bordallo
              Lopez, M., Donta, P. K., and S. Dustdar, "Real-Time AI
              Service Economy: A Framework for Agentic Computing Across
              the Continuum", arXiv preprint arXiv:2603.05614v1, 2026
              (under review, IEEE Trans. Services Computing), 2026,
              <https://arxiv.org/abs/2603.05614>.

   [LOVEN-TRILEMMA]
              Lovén, L., Gujar, S., Timperi, K., Mehmood, H., Donta, P.
              K., Tarkoma, S., and S. Dustdar, "Credibility Trilemma in
              Polymatroidal Service Markets", arXiv preprint
              arXiv:2605.26604, 2026,
              <https://arxiv.org/abs/2605.26604>.

   [DUNG]     Dung, P. M., "On the acceptability of arguments and its
              fundamental role in nonmonotonic reasoning, logic
              programming and n-person games", Artificial Intelligence,
              Vol. 77, No. 2, pp. 321-357, 1995.

   [DCOP]     Fioretto, F., Pontelli, E., and W. Yeoh, "Distributed
              Constraint Optimization Problems and Applications: A
              Survey", Journal of Artificial Intelligence Research, Vol.
              61, 2018.

   [FIPA]     Foundation for Intelligent Physical Agents (FIPA), "FIPA
              ACL Message Structure Specification", 2002.

   [SON]      Bayazeed, A., Khorzom, K., and M. Aljnidi, "A survey of
              self-coordination in self-organizing network", Computer
              Networks, Vol. 196, p. 108222, 2021.

Janz, et al.            Expires 12 December 2026               [Page 20]
Internet-Draft     Inter-Agent Conflict and Resolution         June 2026

   [ORAN-RIC] O-RAN Alliance, "O-RAN Working Group 3: Near-Real-Time RAN
              Intelligent Controller Architecture", O-RAN Alliance
              Technical Report, 2024.

   [LUPU]     Lupu, E. C. and M. Sloman, "Conflicts in Policy-Based
              Distributed Systems Management", IEEE Transactions on
              Software Engineering, Vol. 25, No. 6, pp. 852-869, 1999.

   [PARSAEEFARD]
              Parsaeefard, S., "Interaction and Conflict Management in
              AI-Assisted Operational Control Loops in 6G", arXiv
              preprint arXiv:2110.12025, 2021,
              <https://arxiv.org/abs/2110.12025>.

Acknowledgments

   Much of this thinking developed in tandem with the authors' ETSI ISG
   ZSM contributions on agent coordination.  We thank colleagues there,
   along with the NMRG and NMOP communities, for many useful
   conversations on how agentic AI should figure in network operations.

Authors' Addresses

   Chris Janz
   Huawei
   Email: christopher.janz@huawei.com

   Fernando Camacho
   Huawei
   Email: fernando.camacho1@huawei.com

   Lauri Lovén
   University of Oulu
   Email: lauri.loven@oulu.fi

   Per Kangru
   Viavi Solutions
   Email: per.kangru@viavisolutions.com

Janz, et al.            Expires 12 December 2026               [Page 21]