Skip to main content
AgentNet Observer
Esc

    Library

    A curated index of papers, standards, tools and datasets on agents and the Agent Internet.

    31 / 31

    3GPP FS_6G_APP: Study on 6G Application Enablement (TR 23.xxx, SID in preparation) ↗ 详情

    3GPP SA6

    Standard 2026 2026-08-29 3GPP SA6 Study Item (SID under preparation, work plan Aug-Nov 2026) 3GPP6Gapplication-enablementagent标准

    SA6 study analysing 6G use cases (per SA1 TR 22.870, including third-party AI agent collaboration) to derive application-enabler level requirements and shape 6G application enablement aligned with the IMT-2030 vision and industry initiatives (GSMA Open Gateway, ETSI OpenCAPIF). Work plan: SA6#68 (Aug 25-29) proposals, moderated discussions Sep/Oct, SA6#70 (Nov 17-21), then SID submission to SA plenary. Output TR 23.xxx will form the basis for normative 6G application enablement work. SID draft: S6-255552 (3GPP FTP; accessible via browser, scripted download returns 403).

    3GPP TR 22.870: Study on 6G Use Cases and Service Requirements (FS_6G_REQ) ↗ 详情

    3GPP SA1

    Standard 2026 2026-03-01 3GPP Technical Report (approved at TSG SA#111, March 2026) 3GPP6Gagent需求标准

    Stage-1 6G study approved in March 2026 with 200+ use cases, explicitly including "6G AI agent collaboration with third-party AI" as a use case family and requirements such as exposing services to authorised third-party AI agents. TR 22.870 frames AI agents as automated intelligent entities capable of intent understanding, contextual reasoning, self-learning and collaborative decision-making within the 6G system. Anchor reference for Release 21 normative work together with TR 38.914.

    Contextual Agent Authorization Mesh (CAAM) ↗ 详情

    J. M. Barney, R. Pioli, D. Watson

    Standard 2026 2026-02-25 IETF Internet-Draft (individual) IETFauthorizationa2acontext

    CAAM proposes a contextual authorization mesh for agents: authorization decisions are bound to invocation context rather than long-lived static tokens, limiting over-broad delegation in agentic systems.

    Architectural Requirements for Supporting AI Agents on the Internet ↗ 详情

    S. D. Park

    Standard 2026 2026-08-28 IETF Internet-Draft (individual) IETFarchitectureagent-internetrequirements

    Individual draft enumerating architectural requirements for supporting AI agents on the Internet: how agents are addressed, identified, discovered and how their capabilities are described within existing Internet architecture.

    SAIP: Signed Agent Identity Protocol ↗ 详情

    S. Jovancevic

    Standard 2026 2026-04-09 IETF Internet-Draft (individual) IETFidentitysignatureprotocol

    SAIP defines a signed agent identity protocol that cryptographically attests an agent's identity, answering how a peer can prove it is the agent it claims to be.

    Agent Registration and Discovery Protocol (ARDP) ↗ 详情

    R. Pioli

    Standard 2026 2026-02-24 IETF Internet-Draft (individual) IETFdiscoveryregistrationprotocol

    Defines the Agent Registration and Discovery Protocol: how an agent registers itself, declares its capabilities and endpoints, and how other agents or gateways locate it.

    Agent-to-Agent Trust, Identity, and Verifiable Provenance ↗ 详情

    T. Trujillo

    Standard 2026 2026-07-25 IETF Internet-Draft (individual) IETFa2atrustidentityprovenance

    Specifies trust, identity and verifiable provenance mechanisms for agent-to-agent interaction, enabling participants to authenticate counterparts and audit what an agent actually did.

    Gateway Capability Directory and Synchronization for Internet of Agents ↗ 详情

    Lianhua Zhang, Huiling Yang, Yun Li, Shoufeng Wang

    Standard 2026 2026-04-21 IETF Internet-Draft (individual submission) IETFagent-gatewaycapability-directorydirectory-sync

    Defines a gateway-managed capability-directory framework for the Internet of Agents: a control-plane function maintaining validated capability information beyond transient advertisements, static endpoint bindings or external descriptions, with requirements and a common object model.

    ITU-T Y.aias-reqts: AI Agent as a Service (requirements, under study) ↗ 详情

    ITU-T SG13 Q17/13, ETRI

    Standard 2026 2026-06-09 ITU-T SG13 work item (under study) ITU-Tagentagent-as-a-service标准

    SG13 Q17/13 work item on requirements for AI Agent as a Service (Y.aias-reqts), with 2026-06 contributions from ETRI covering proposed revisions of scope/overview of AI agent and text for AI agent as a service in clause 6.2. Related parallel SG13 items: Y.AMLM-reqts (ML model adaptation), Y.MLPaaS-reqts (ML PaaS). Signifies that agent-as-a-service is entering requirements-stage standardization at ITU-T.

    ITU-T YSTR.ACN: AI-agent communication network in IMT-2020 networks and beyond (Draft TR) ↗ 详情

    ITU-T SG13, 中国电信, 中国信通院, 中国移动

    Standard 2026 2026-06-09 ITU-T SG13 WP3 Technical Report (under study) ITU-TagentACN6G标准

    SG13 technical report under study defining the AI-agent communication network (ACN) in IMT-2020 networks and beyond. Presented among SG13 AI-agent achievements alongside YSTR.NAC and Y.IMT2020-DIC; echoes the ACN concept promoted by China Mobile at the 2026 Cloud-Network Intelligence Conference. Note: China Mobile's CN indicator and ITU-T ACN terminology converge on the same problem space — agent-native networking for 6G.

    ITU-T YSTR.NAC-roadmap: Networking for AI agent collaboration — Standardization status and roadmap (TR) ↗ 详情

    ITU-T SG13 Q22/13, 中国电信, 中国信通院, 中国联通 et al.

    Standard 2026 2026-03-16 ITU-T Technical Report (approval targeted 2026-11) ITU-Tagentroadmap标准

    SG13 Q22/13 technical report (target 2026-11) surveying standardization status and roadmap for networking that supports AI agent collaboration across heterogeneous organizations, protocols and data formats; collects related Recommendations and TRs and proposes standardization directions. Companion item: YSTR.NAC (Framework of networking for AI agent collaboration in future networks). Supported by China Telecom, CAICT, China Unicom, BUPT, Zhejiang Lab and NICT; editors include Jingwen LI and Ved P. KAFLE.

    RFC 10038: Distributing the SRv6 Locator Using DHCPv6 ↗ 详情

    W. Cheng, R. Han, C. Lin, D. Voyer et al.

    Standard 2026 2026-08-28 IETF RFC (SPRING WG) 10038 IETFRFCSRv6DHCPv6SPRING

    RFC 10038 specifies distribution of the Segment Routing over IPv6 (SRv6) locator via DHCPv6, automating locator provisioning and removing a major operational friction in large-scale SRv6 deployments.

    T/CCSA 800-2026: Classification method and technical requirements for capability levels of AI agent system ↗ 详情

    CCSA TC1/WG1, 中国移动, 中国信通院, 中国联通 et al.

    Standard 2026 2026-03-02 CCSA 团体标准(已发布) CCSAagentcapability-levelling标准

    Published 2026-03-02, effective 2026-06-01 (project 2025-CCSA-002, TC1/WG1). Defines the capability classification method for AI agent systems and the technical requirements per level; applicable to both agent providers and consumers for grading agent systems. One of 75 group standards approved in the same batch.

    Agent2Agent (A2A) Protocol ↗ 详情

    Google, Linux Foundation

    Standard 2025 2025-03-25 Industry Specification protocolinter-agentinteroperability

    An open protocol for agent-to-agent interoperability: discovery, capability exchange and task delegation across different vendors' agents.

    SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering ↗ 详情

    John Yang, Carlos E. Jimenez, Alexander Wettig, Kilian Lieret et al.

    Paper 2024 2024-05-06 NeurIPS 2024 arXiv:2405.15793 software-engineeringbenchmarktool-use

    Shows that designing the interface through which agents interact with codebases (Agent-Computer Interface) dramatically improves autonomous bug fixing on real GitHub issues.

    Model Context Protocol (MCP) Specification ↗ 详情

    Anthropic

    Standard 2024 2024-09-24 Industry Specification protocoltool-useinteroperability

    An open protocol standardizing how LLM applications connect to external tools and data sources; widely adopted as the "USB-C of AI".

    Browser Use ↗ 详情

    Browser Use Team

    Tool 2024 2024-10-31 Open Source web-agentbrowser-automationtool-use

    A library enabling LLM agents to control web browsers naturally — a key building block for web-operating agents.

    OpenHands (formerly OpenDevin) ↗ 详情

    All Hands AI

    Tool 2024 2024-03-13 Open Source software-engineeringautonomous-agentopen-source

    An open platform for AI software engineers: sandboxed code execution, browser use and task planning, aiming at autonomous development workflows.

    AgentBench: Evaluating LLMs as Agents ↗ 详情

    Xiao Liu, Botian Yu, Haotian Du, Zhiheng Zheng et al.

    Dataset 2023 2023-08-07 ICLR 2024 arXiv:2308.03688 benchmarkevaluation

    A systematic multi-dimensional benchmark evaluating LLMs as agents across 8 distinct environments (OS, DB, knowledge graph, digital card game, etc.).

    GAIA: A Benchmark for General AI Assistants ↗ 详情

    Grégoire Mialon, Clémentine Fourrier, Craig Swift, Thomas Wolf et al.

    Dataset 2023 2023-11-21 NeurIPS 2023 (Datasets & Benchmarks) arXiv:2311.12983 benchmarkgeneral-assistantevaluation

    A benchmark of 466 questions requiring reasoning, multimodal handling, web browsing and tool use — questions simple for humans yet hard for state-of-the-art AI.

    Generative Agents: Interactive Simulacra of Human Behavior ↗ 详情

    Joon Sung Park, Joseph C. O'Brien, Carrie J. Cai, Meredith Ringel Morris et al.

    Paper 2023 2023-04-07 UIST 2023 arXiv:2304.03442 multi-agentsimulationmemory

    The Stanford "Smallville" experiment: 25 LLM agents with memory, reflection and planning living in a simulated town, a landmark in agent society research.

    MetaGPT: Meta Programming for a Multi-Agent Collaborative Framework ↗ 详情

    Sirui Hong, Mingchen Zhuge, Jonathan Chen, Xiawu Zheng et al.

    Paper 2023 2023-08-01 ICLR 2024 (Oral) arXiv:2308.00352 multi-agentSOPsoftware-engineering

    Encodes Standardized Operating Procedures into LLM agent roles, assembling a software company simulation that turns one-line requirements into working programs.

    Voyager: An Open-Ended Embodied Agent with Large Language Models ↗ 详情

    Guanzhi Wang, Yuqi Xie, Yunfan Jiang, Ajay Mandlekar et al.

    Paper 2023 2023-05-25 TMLR 2024 arXiv:2305.16291 embodiedlifelong-learningminecraft

    An LLM-powered agent with automatic curriculum, skill library and iterative prompting that explores Minecraft open-endedly without human intervention.

    CrewAI ↗ 详情

    CrewAI Inc.

    Tool 2023 2023-10-27 Open Source frameworkmulti-agentpython

    A role-playing multi-agent orchestration framework: define agents with roles, goals and tools, then assemble them into crews for collaborative tasks.

    ReAct: Synergizing Reasoning and Acting in Language Models ↗ 详情

    Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du et al.

    Paper 2022 2022-10-06 ICLR 2023 arXiv:2210.03629 reasoningtool-usefoundation

    Introduces ReAct, prompting LLMs to interleave chain-of-thought reasoning with actions, becoming the paradigm backbone of most agent frameworks.

    LangChain ↗ 详情

    LangChain Inc.

    Tool 2022 2022-10-17 Open Source frameworkpythontool-use

    The most widely used LLM application framework: chains, tool calling, memory and integrations; LangGraph extends it to stateful agent workflows.