提出智能体系统技术债新概念，揭示其治理难题。
Governing Technical Debt in Agentic AI Systems
- 定义智能体技术债：快速拼接提示、记忆、工具等导致的累积风险。
- 提出随机税概念：维持概率性行为在可接受范围内的持续运营成本。
- 提供轻量级看板与管控机制，让治理可见可控。
智能体AI系统正被广泛探索为生产基础设施：它们多步推理、调用工具、执行工作流，并通过记忆和反馈进行自适应。这些系统带来传统软件或预测性机器学习技术债无法涵盖的治理挑战。本文定义了‘智能体技术债’，即当提示、记忆、工具模式、编排图、控制策略和可观测性流程被快速拼接而未充分验证、标准化和治理时产生的累积责任。同时提出‘随机税’概念，指因概率性智能体通过工具和工作流运行而带来的持续运营负担。二者区别在于：技术债是设计与治理的责任存量，而随机税是由此产生的运营成本流量。文章提出通过轻量级仪表盘和治理控制使两者可视化，并给出管理建议。
原文摘要 · Abstract (English)
Agentic AI systems are increasingly being explored as production infrastructure: they reason over multiple steps, call tools, act through workflows, and adapt through memory and feedback. These systems create governance challenges that are not fully captured by traditional software or predictive ML technical debt. We define Agentic Technical Debt as the accumulated liability created when prompts, memory, tool schemas, orchestration graphs, control policies, and observability routines are patched together faster than they can be validated, standardized, and governed. We define Stochastic Tax as the recurring operating burden of keeping probabilistic agent behavior within acceptable bounds. The distinction matters: debt is a stock of design and governance liability, while the tax is a flow of operating cost that arises because stochastic agents act through tools and workflows. We outline how managers can make both visible through lightweight dashboards and governance controls.
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。