arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2605.19035cs.AI
收藏

可信代理网络:在代理网络中,信任必须被内置,而非事后添加

Trustworthy Agent Network: Trust in Agent Networks Must Be Baked In, Not Bolted On

University of Southern California(南加州大学);Carnegie Mellon University(卡内基梅隆大学);University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);Stanford University(斯坦福大学)

Yixiang Yao, Yuhang Yao, Xinyi Fan, Jiechao Gao, Jie Wang, Minjia Zhang, Srivatsan Ravi, Carlee Joe-Wong

AI总结:

本文探讨了在代理网络中信任必须被内置而非事后添加的问题,提出了一个综合的概念框架,通过四个设计支柱来建立代理网络中的信任。

摘要:

大型语言模型的快速发展催生了能够进行复杂推理和执行的自主LLM代理。随着这些代理从孤立操作转向协作生态系统,我们见证了代理到代理(A2A)网络的出现,这是一种异构代理自主协调解决多步骤任务的范式。尽管这些网络可能比单纯使用一个代理完成整个任务表现更好,但它们引入了系统性漏洞,如对抗性组合、语义错位和级联操作失败,现有代理对齐技术无法解决。在本文的愿景论文中,我们主张A2A网络的可信度不能通过在现有协议上进行 retrofitting 来完全保证,这些协议大多为单个代理设计。相反,它必须在A2A协调框架的最初阶段进行架构设计。我们提出一个综合的概念框架,通过四个设计支柱来在A2A系统中建立信任。

英文摘要:

The rapid advancement of Large Language Models has given rise to autonomous LLM-based agents capable of complex reasoning and execution. As these agents transition from isolated operation to collaborative ecosystems, we witness the emergence of the Agent-to-Agent (A2A) network, a paradigm where heterogeneous agents autonomously coordinate to solve multi-step tasks. While these networks may offer better task performance compared to simply using one agent to complete the entire task, they introduce systemic vulnerabilities, such as adversarial composition, semantic misalignment, and cascading operational failures, that existing agent alignment techniques cannot address. In this vision paper, we argue that the trustworthiness of A2A networks cannot be fully guaranteed via retrofitting on existing protocols that are largely designed for individual agents. Rather, it must be architected from the very beginning of the A2A coordination framework. We present a comprehensive conceptual framework that situates trust in A2A systems through four design pillars.

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。

↑