分析70个AI代理项目，揭示其架构设计规律与模式。
Architectural Design Decisions in AI Agent Harnesses
- 通过源码与技术文档分析70个开源项目，提炼出五类核心设计维度。
- 发现文件持久化、混合式上下文策略最常见，工具系统以注册表为主导。
- 适合框架设计者、选型者及研究者参考，提供实证指导。
AI代理系统越来越多地依赖可复用的非大模型工程基础设施，涵盖工具调度、上下文管理、任务委派、安全控制和编排等功能。然而，围绕这些基础设施的架构设计决策仍缺乏系统研究。本文通过对70个公开可用的代理系统项目进行协议引导、源码基础的实证研究，回答三个问题：哪些设计维度在项目中反复出现？这些决策之间存在怎样的共现关系？典型的架构模式有哪些？方法上，提出一种透明的异构项目分析流程。实证发现，五类常见设计维度包括子代理架构、上下文管理、工具系统、安全机制与编排方式；数据表明，文件持久化、混合式与分层式上下文策略占主导；注册表导向的工具系统仍主流，而MCP与插件式扩展正逐步兴起；中间隔离普遍，但高保障审计罕见。跨项目共现分析显示，更深层协调伴随更显式的上下文服务，更强执行环境对应更结构化治理，正式化的工具注册边界与更广阔的生态愿景相关。最终归纳出五种典型架构模式：轻量工具型、平衡命令行框架、多代理编排器、企业级系统与场景垂直化项目。研究成果为代理系统工程提供了基于证据的架构规律认知，为框架设计者、选型者与研究者提供实证依据。
原文摘要 · Abstract (English)
AI agent systems increasingly rely on reusable non-LLM engineering infrastructure that packages tool mediation, context handling, delegation, safety control, and orchestration. Yet the architectural design decisions in this surrounding infrastructure remain understudied. This paper presents a protocol-guided, source-grounded empirical study of 70 publicly available agent-system projects, addressing three questions: which design-decision dimensions recur across projects, which co-occurrences structure those decisions, and which typical architectural patterns emerge. Methodologically, we contribute a transparent investigation procedure for analyzing heterogeneous agent-system corpora through source-code and technical-material reading. Empirically, we identify five recurring design dimensions (subagent architecture, context management, tool systems, safety mechanisms, and orchestration) and find that the corpus favors file-persistent, hybrid, and hierarchical context strategies; registry-oriented tool systems remain dominant while MCP- and plugin-oriented extensions are emerging; and intermediate isolation is common but high-assurance audit is rare. Cross-project co-occurrence analysis reveals that deeper coordination pairs with more explicit context services, stronger execution environments with more structured governance, and formalized tool-registration boundaries with broader ecosystem ambitions. We synthesize five recurring architectural patterns spanning lightweight tools, balanced CLI frameworks, multi-agent orchestrators, enterprise systems, and scenario-verticalized projects. The result provides an evidence-based account of architectural regularities in agent-system engineering, with grounded guidance for framework designers, selectors, and researchers.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。