ANX:面向AI代理交互的协议优先设计及其支持的3EX解耦架构
ANX: Protocol-First Design for AI Agent Interaction with a Supporting 3EX Decoupled Architecture
AI总结:
本文提出ANX协议,通过协议创新、架构优化和工具补充,解决AI代理交互中高消耗、碎片化、安全性不足等问题,其核心创新包括代理原生设计、人机交互、轻量应用和可执行SOP。
摘要:
AI代理,即自主数字主体,需要原生协议;现有方法包括GUI自动化和MCP技能,存在高token消耗、交互碎片化、安全性不足等问题,因缺乏统一顶层框架和关键组件。为解决这些问题,本文提出ANX,一个开放、可扩展、可验证的原生协议和顶层框架,整合CLI、Skill、MCP,通过协议创新、架构优化和工具补充解决痛点。其四大核心创新:1)原生设计(ANX配置、标记语言、CLI)具有高信息密度、灵活性和强适应性,减少token消耗并消除不一致性;2)人机交互结合Skill的灵活性,实现双渲染作为代理可执行指令和人可读UI;3)MCP支持的按需轻量应用无需预注册;4)ANX标记语言支持的可执行SOP消除歧义,适用于可靠长期任务和多代理协作。作为系列的第一部分,本文聚焦ANX设计,展示其3EX解耦架构及ANXHub和初步可行性分析和实验验证。ANX确保原生安全性:LLM绕过UI到核心通信保持敏感数据不出代理上下文;人仅确认防止自动化滥用。与Qwen3.5-plus/GPT-4o的表单填写实验显示,ANX相比MCP技能分别减少47.3%和55.6%的token消耗,相比GUI自动化分别减少57.1%和66.3%的token消耗,并将执行时间缩短58.1%和57.7%。
英文摘要:
AI agents, autonomous digital actors, need agent-native protocols; existing methods include GUI automation and MCP-based skills, with defects of high token consumption, fragmented interaction, inadequate security, due to lacking a unified top-level framework and key components, each independent module flawed. To address these issues, we present ANX, an open, extensible, verifiable agent-native protocol and top-level framework integrating CLI, Skill, MCP, resolving pain points via protocol innovation, architectural optimization and tool supplementation. Its four core innovations: 1) Agent-native design (ANX Config, Markup, CLI) with high information density, flexibility and strong adaptability to reduce tokens and eliminate inconsistencies; 2) Human-agent interaction combining Skill's flexibility for dual rendering as agent-executable instructions and human-readable UI; 3) MCP-supported on-demand lightweight apps without pre-registration; 4) ANX Markup-enabled machine-executable SOPs eliminating ambiguity for reliable long-horizon tasks and multi-agent collaboration. As the first in a series, we focus on ANX's design, present its 3EX decoupled architecture with ANXHub and preliminary feasibility analysis and experimental validation. ANX ensures native security: LLM-bypassed UI-to-Core communication keeps sensitive data out of agent context; human-only confirmation prevents automated misuse. Form-filling experiments with Qwen3.5-plus/GPT-4o show ANX reduces tokens by 47.3% (Qwen3.5-plus) and 55.6% (GPT-4o) vs MCP-based skills, 57.1% (Qwen3.5-plus) and 66.3% (GPT-4o) vs GUI automation, and shortens execution time by 58.1% and 57.7% vs MCP-based skills.
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。