arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2606.26211cs.CR
收藏

数据事实:NANDINI多智能体生态系统中结构化数据交换的元数据模式

Data Facts: A Metadata Schema for Structured Data Exchange in the NANDini Multi-Agent Ecosystem

Jin Gao, Maria Gorskikh, Pradyumna Chari, Brittany Box, Mukul Kemla, Pratik Behera, Abhishek Mehta, Ramesh Raskar

AI总结:

提出Data Facts元数据模式,通过轻量JSON和单指针解决多智能体生态中结构化数据交换问题,实现数据集身份、访问控制与完整性验证,实验证明准确率从35.2%提升至100%。

摘要:

NANDINI(网络化智能体自然蒸馏互联节点智能)设想了一个自动化生态系统,其中智能体独立创建、处理并交换数据以驱动大规模决策。实现这一愿景需要超越智能体发现与通信的基础设施:智能体必须能够宣传、评估和验证其持有的数据集。当前协议,包括用于联邦注册的NANDA以及用于智能体间消息传递的A2A和MCP,解决了身份和通信问题,但未提供结构化数据交换的机制。现有的企业数据共享框架,如IDS-RAM、Gaia-X和Ocean Protocol,假设了与自主、实时智能体交互不兼容的人机协同治理。我们引入了Data Facts,一个核心的NANDINI概念:一种轻量级JSON元数据模式,通过单个指针`data_facts_url`(添加到现有Agent Facts注册记录中)桥接智能体发现与数据访问。链接的文档编码了数据集身份、访问层级(公共、半私有或私有)、端点、用于新鲜度验证的生存时间(TTL)以及SHA-256完整性校验和。对于私有和半私有数据,我们实现了一个三层安全管道:JWT认证、能力范围网关授权以及A2A凭证委托协议。在840次决策评估中,数据知情智能体达到100%准确率,而无数据访问时仅为35.2%(p < 0.001);TTL强制执行将过期数据错误从37.6%降至8.8%;校验和验证在所有注入率下实现100%的损坏检测;安全管道阻止了所有46次伪造尝试,且无数据泄露。

英文摘要:

NANDini (Networked Agents Natural Distillation of Interconnected Nodal Intelligence) envisions an automated ecosystem where intelligent agents independently create, process, and exchange data to drive decisions at scale. Realizing this vision requires infrastructure beyond agent discovery and communication: agents must be able to advertise, evaluate, and verify the datasets they hold. Current protocols, including NANDA for federated registry and A2A and MCP for inter-agent messaging, address identity and communication but provide no mechanism for structured data exchange. Existing enterprise data-sharing frameworks, such as IDS-RAM, Gaia-X, and Ocean Protocol, assume human-in-the-loop governance that is incompatible with autonomous, real-time agent interactions. We introduce Data Facts, a core NANDini concept: a lightweight JSON metadata schema that bridges agent discovery and data access through a single pointer, `data_facts_url`, added to an existing Agent Facts registry record. The linked document encodes dataset identity, access tier, whether public, semi-private, or private, endpoint, a time-to-live for freshness validation, and a SHA-256 integrity checksum. For private and semi-private data, we implement a three-layer security pipeline: JWT authentication, capability-scoped gateway authorization, and an A2A credential delegation protocol. Across 840 decision-making evaluations, data-informed agents achieve 100% accuracy versus 35.2% without data access (p < 0.001); TTL enforcement reduces stale-data errors from 37.6% to 8.8%; checksum verification achieves 100% corruption detection at all injection rates; and the security pipeline blocks all 46 forgery attempts with zero data leakage.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑