Document changes urn:uuid:03c97340-7c3b-5530-884e-c193b1e29c05 2026-08-13T05:16:14.137202+00:00 urn:datatracker-ietf-org:event:1217474 2026-08-07T02:17:31.647564+00:00 2026-08-07T02:17:31.647564+00:00 Linda Dunbar New version available: <b>draft-dunbar-dmsc-gw-scenarios-gap-analysis-03.txt</b> new_revision none active idexists This document examines deployment scenarios for AI agent collaboration and analyzes the circumstances under which AI Agent Gateway functions provide operational or interoperability benefits that cannot be achieved through direct agent-to-agent communication alone. The document considers both single-domain and multi-domain deployments, identifies specific challenges associated with each deployment model, evaluates the limitations of existing agent communication mechanisms (including MCP and A2A) with respect to those challenges, and demonstrates that gateway functions are necessary in deployments involving multiple tenants, multiple vendors, or multiple administrative domains. 03 urn:datatracker-ietf-org:event:1217473 2026-08-07T02:17:31.644492+00:00 2026-08-07T02:17:31.644492+00:00 (System) New version approved new_submission none active idexists urn:datatracker-ietf-org:event:1217472 2026-08-07T02:17:02.493105+00:00 2026-08-07T02:17:02.493105+00:00 (System) Request for posting confirmation emailed to previous authors: Bing Liu <leo.liubing@huawei.com>, Linda Dunbar <ldunbar@futurewei.com>, YiFei Wang <wangyf85@chinatelecom.cn> new_submission none active idexists urn:datatracker-ietf-org:event:1217471 2026-08-07T02:17:02.102517+00:00 2026-08-07T02:17:02.102517+00:00 Linda Dunbar Uploaded new revision new_submission none active idexists urn:datatracker-ietf-org:event:1216864 2026-08-05T01:43:37.148921+00:00 2026-08-05T01:43:37.148921+00:00 Yifei Wang New version available: <b>draft-wang-dmsc-drisac-00.txt</b> new_revision none active idexists The large-scale deployment of autonomous AI Agents introduces challenges to capability description, registration, and discovery. Existing agent communication protocols mainly focus on application- layer interactions and typically rely on centralized registration and discovery mechanisms, which limit scalability, robustness, and semantic extensibility. This document proposes a distributed and hierarchical capability registration and information synchronization mechanism for AI Agents. The mechanism introduces a multi-level capability taxonomy, capability vectors, and globally unique Service Identifiers (Service IDs), and defines two functional entities: Agent Capability Registration Server (ACRS) and Agent Capability Access Server (ACAS). A capability table is constructed and synchronized among ACRSs to enable semantic-based forwarding of capability-related requests. Furthermore, capability registration and discovery procedure are specified, enabling precise selection of agents based on task requirements. The proposed mechanism provides a scalable foundation for capability-aware routing and semantic collaboration in the Internet of Agents (IoA). 00 urn:datatracker-ietf-org:event:1216863 2026-08-05T01:43:37.147101+00:00 2026-08-05T01:43:37.147101+00:00 Yifei Wang New version accepted (logged-in submitter: Yifei Wang) new_submission none active idexists urn:datatracker-ietf-org:event:1216862 2026-08-05T01:29:04.541978+00:00 2026-08-05T01:29:04.541978+00:00 Yifei Wang Uploaded new revision new_submission none active idexists