agent2agent Y. Zhu Internet-Draft China Mobile Intended status: Informational 6 July 2026 Expires: 7 January 2027 Registration and Discovery Extension for Multi-Model Agents draft-zhu-agent-registration-discovery-00 Abstract Existing agent registration and discovery mechanisms assume that each intelligent agent is backed by a single, static inference model. However, in real-world deployments, agents increasingly incorporate internal model routing mechanisms where multiple foundation models are used dynamically within a single agent based on task complexity, latency requirements, system load, and cost constraints. Although such agents are exposed externally as single service endpoints, their execution behavior is not static and may vary due to internal model selection logic that is not visible to external systems. This leads to mismatches between registered metadata and actual service behavior, reducing the effectiveness of discovery and QoS-aware routing. Note The key words "MUST", "MUST NOT", "REQUIRED", "SHALL", "SHALL NOT", "SHOULD", "SHOULD NOT", "RECOMMENDED", "MAY", and "OPTIONAL" in this document are to be interpreted as described in RFC 2119. 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. Zhu Expires 7 January 2027 [Page 1] Internet-Draft Multi-Model Agent Registration July 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. 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 . . . . . . . . . . . . . . . . . . . . . . . . 3 2. Problem Statement . . . . . . . . . . . . . . . . . . . . . . 3 2.1. Emergence of Internal Model Routing in Production Systems . . . . . . . . . . . . . . . . . . . . . . . . . 4 2.2. Hidden Execution Heterogeneity . . . . . . . . . . . . . 4 2.3. Lack of Transparency in Model Selection Behavior . . . . 4 2.4. Impact on Discovery and QoS Matching . . . . . . . . . . 4 2.5. Limitations of Static Agent-Level Representation . . . . 5 2.6. Requirement for Execution-Aware Representation . . . . . 5 3. Design Goals . . . . . . . . . . . . . . . . . . . . . . . . 6 4. Protocol Overview . . . . . . . . . . . . . . . . . . . . . . 6 5. Registration Extension . . . . . . . . . . . . . . . . . . . 6 5.1. Agent Registration Format . . . . . . . . . . . . . . . . 6 5.2. Model Profile . . . . . . . . . . . . . . . . . . . . . . 7 6. Model Update Procedure . . . . . . . . . . . . . . . . . . . 7 7. Discovery Extension . . . . . . . . . . . . . . . . . . . . . 8 7.1. Discovery Request . . . . . . . . . . . . . . . . . . . . 8 7.2. Discovery Response . . . . . . . . . . . . . . . . . . . 8 8. Backward Compatibility . . . . . . . . . . . . . . . . . . . 8 9. Security Considerations . . . . . . . . . . . . . . . . . . . 9 10. IANA Considerations . . . . . . . . . . . . . . . . . . . . . 9 11. Conclusion . . . . . . . . . . . . . . . . . . . . . . . . . 9 12. Normative References . . . . . . . . . . . . . . . . . . . . 9 13. Informative References . . . . . . . . . . . . . . . . . . . 9 Author's Address . . . . . . . . . . . . . . . . . . . . . . . . 10 Zhu Expires 7 January 2027 [Page 2] Internet-Draft Multi-Model Agent Registration July 2026 1. Introduction Intelligent agents built upon large language models (LLMs) have been widely deployed as core service components within AI-native systems. Conventional agent registration and discovery mechanisms expose static metadata, such as agent identifiers, service endpoints, authentication schemes, and supported capability catalogs. These mechanisms operate under an implicit assumption that each agent is backed by only one inference model, and key service metrics including latency and functional capability remain stable and deterministic. This foundational assumption, however, no longer holds true in production deployments. Most modern agents incorporate internal model routing capabilities, which dynamically select distinct foundation models at runtime to achieve balanced tradeoffs among inference latency, invocation cost, and output quality. The broad adoption of intra-agent multi-model routing stems from two primary production scenarios. Tiered Model Scheduling for Latency-Cost Balance: A single business- oriented agent integrates lightweight small-scale models, medium general-purpose models, and high-performance flagship models. Trivial routine queries are handled by low-latency, low-cost small models, while tasks involving sophisticated logical reasoning, long- document parsing, and mathematical computation are automatically routed to high-capacity flagship models. Downstream systems only need to connect to a unified service entry without manual model selection or switching. Load-Adaptive Degradation and Fault Fallback: During traffic surges or GPU resource saturation, the routing module automatically offloads heavy-load requests from flagship models onto lightweight backup models to prevent request timeouts and sustain uninterrupted service. The full degradation and disaster recovery logic is fully transparent to external service discovery modules. From an external perspective, such agents appear as a single logical service entity, yet their internal runtime execution behaviors exhibit substantial heterogeneity. 2. Problem Statement Zhu Expires 7 January 2027 [Page 3] Internet-Draft Multi-Model Agent Registration July 2026 2.1. Emergence of Internal Model Routing in Production Systems In modern deployments of LLM-based agents, it is increasingly common for a single agent system to incorporate multiple foundation models internally. These systems typically implement internal routing mechanisms that dynamically select models based on runtime conditions such as request complexity, system load, latency constraints, and cost optimization policies. Although multiple models may be involved in execution, this routing logic is generally not exposed to external registration or discovery systems. As a result, the agent continues to be represented as a single static service entity. 2.2. Hidden Execution Heterogeneity While an agent is registered as a single endpoint, its runtime behavior may vary significantly depending on which internal model is selected for a given request. Service-level characteristics such as latency, response quality, and cost are therefore not fixed attributes of the agent, but emergent properties of internal execution decisions. This leads to a situation where identical requests may receive different service-level outcomes depending on internal routing decisions that are not visible externally. 2.3. Lack of Transparency in Model Selection Behavior Current registration and discovery mechanisms do not provide visibility into: * how internal models are selected for different request types * when fallback or degradation occurs * how latency, cost, and quality trade-offs are enforced internally This lack of transparency prevents external systems from accurately reasoning about expected service behavior. 2.4. Impact on Discovery and QoS Matching The absence of model-level or execution-level visibility leads to inaccurate discovery decisions. In particular: Zhu Expires 7 January 2027 [Page 4] Internet-Draft Multi-Model Agent Registration July 2026 * agents may be selected without awareness of internal fallback behavior * latency expectations may be violated due to hidden model switching * cost-efficient routing decisions cannot be enforced externally * high-complexity requests may be routed to insufficient capability paths under degradation These issues arise because current systems rely on static metadata that does not reflect dynamic execution behavior. 2.5. Limitations of Static Agent-Level Representation Existing registration models assume that an agent can be described using a single, stable capability profile. However, in multi-model routing systems: * capability is not static but context-dependent * execution paths are dynamic and non-deterministic * service-level characteristics vary across requests Therefore, static registration information is insufficient to accurately represent real-world agent behavior. 2.6. Requirement for Execution-Aware Representation There is a requirement for registration and discovery systems to evolve beyond static capability descriptions and support representations that reflect: * dynamic execution behavior within agents * variability in service-level outcomes * internal heterogeneity of model usage Such support is necessary to enable accurate service discovery and QoS-aware routing in environments where multiple models are used within a single agent system. Zhu Expires 7 January 2027 [Page 5] Internet-Draft Multi-Model Agent Registration July 2026 3. Design Goals The following design goals are defined for the extension mechanism: * G1: Support representation of heterogeneous execution behavior within a single agent * G2: Capture dynamic variability of service characteristics * G3: Enable QoS-aware discovery and matching * G4: Preserve single-endpoint abstraction * G5: Maintain backward compatibility with existing systems 4. Protocol Overview The system consists of the following entities: * Agent: service provider with internal execution pipeline * Registration Center: maintains metadata * Service Consumer: performs discovery and invocation Figure 1 illustrates the overall architecture of the extended registration and discovery framework. +----------+ +-------------------+ +----------+ | | | | | | | Agent |<------->| Registration |<------->| Consumer | | | Register| Center | Discover| | +----------+ +-------------------+ +----------+ | | | Invoke | +-------------------------------------------+ Figure 1: System Architecture 5. Registration Extension This section defines the extended registration format for agents with internal multi-model routing capabilities. 5.1. Agent Registration Format The extended registration format includes the following fields: Zhu Expires 7 January 2027 [Page 6] Internet-Draft Multi-Model Agent Registration July 2026 * Agent-ID: unique identifier for the agent * Agent-Type: classification of the agent * Endpoint: service endpoint URI * Authentication: authentication information * Skill-List: list of supported skills * Model-Profile-List: list of internal model profiles (NEW) 5.2. Model Profile Each Model Profile contains the following fields: * Model-ID: unique identifier for the model within the agent * Model-Type: model architecture or family * Model-Version: version identifier * Capability-Level: capability classification * Latency-Class: expected latency classification * Context-Length: maximum supported context length * Cost-Class: cost classification * Availability: availability status * Supported-Skills: skills supported by this model 6. Model Update Procedure Agents SHOULD report internal model lifecycle changes to the Registration Center. The following update types are defined: * MODEL_ADDED: a new model has been added to the agent * MODEL_REMOVED: an existing model has been removed from the agent * MODEL_UPDATED: properties of an existing model have changed * MODEL_DEGRADED: a model has entered a degraded state Zhu Expires 7 January 2027 [Page 7] Internet-Draft Multi-Model Agent Registration July 2026 Upon receiving an update notification, the Registration Center SHOULD update the corresponding Model Profile entries and notify affected consumers if necessary. 7. Discovery Extension This section defines the extended discovery mechanism that enables consumers to perform QoS-aware service selection. 7.1. Discovery Request The extended discovery request includes the following fields: * Required-Skill: the skill required for the request * Maximum-Latency: maximum acceptable latency * Minimum-Capability: minimum required capability level * Minimum-Context-Length: minimum required context length * Cost-Preference: preferred cost classification 7.2. Discovery Response The extended discovery response includes the following fields: * Agent-ID: identifier of the matched agent * Matched-Model: identifier of the model that matches the request * Capability-Level: capability level of the matched model * Expected-Latency: expected latency for the matched model * Endpoint: service endpoint for invocation 8. Backward Compatibility Single-model agents are represented using a single default Model Profile entry. No protocol changes are required for existing implementations. Registration Centers that do not support the extended format MAY ignore the Model-Profile-List field and treat the agent as a traditional single-model agent. Zhu Expires 7 January 2027 [Page 8] Internet-Draft Multi-Model Agent Registration July 2026 Consumers that do not support the extended format MAY continue to use the basic discovery mechanism without the QoS-aware fields. 9. Security Considerations Model-level information MAY reveal sensitive system characteristics. Implementations SHOULD: * protect registration and update messages using appropriate security mechanisms * restrict exposure of internal model identities to authorized consumers * prefer abstract capability representation where possible to avoid revealing sensitive model details Registration Centers SHOULD implement access control policies to limit which consumers can access detailed Model Profile information. 10. IANA Considerations This document does not require any IANA actions. 11. Conclusion This document describes an emerging gap in current agent registration and discovery systems caused by internal multi-model routing within modern agent architectures. It identifies the need for execution- aware representation of agent behavior to enable accurate discovery and QoS-aware service selection in future AI-native networks. The design goals, protocol overview, and extension mechanisms defined in this document provide a foundation for addressing this gap while maintaining backward compatibility with existing systems. 12. 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, . [RFC8174] Leiba, B., "Ambiguity of Uppercase vs Lowercase in RFC 2119 Key Words", BCP 14, RFC 8174, DOI 10.17487/RFC8174, May 2017, . 13. Informative References Zhu Expires 7 January 2027 [Page 9] Internet-Draft Multi-Model Agent Registration July 2026 Author's Address Yidan Zhu China Mobile Beijing China Email: zhuyidan@chinamobile.com Zhu Expires 7 January 2027 [Page 10]