发表机构
University of Birmingham; Bournemouth University; Brunel University London; HBKU; University of Hawaii（伯明翰大学; 伯恩茅斯大学; 伦敦布鲁内尔大学; 哈迈德·本·哈利法大学; 夏威夷大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文针对智能体AI系统引入智能体技术债务（AgTD）概念，通过转换方法建立AITD到智能体表现的系统映射，明确其影响并提出管理框架与研究议程。
AI 中文摘要
以自主推理、多智能体协作、工具编排、自适应决策和持久记忆为特征的智能体AI系统的出现，标志着从传统AI流水线向动态软件生态系统的根本性转变。尽管AI技术债务（AITD）已在机器学习和软件工程领域得到广泛研究，但现有模型假设架构是静态的、组件级的，无法捕捉智能体环境的动态性和涌现行为。为解决这一缺口，本文引入智能体技术债务（AgTD），定义为因智能体AI系统的自主性和协作性而产生、积累、传播和放大的技术债务。基于我们先前对7个根本原因类别中31种AITD的系统范围审查，本文采用基于理论的转换方法，通过直接转换、情境转换和表现形式扩展，在智能体AI中重新解释这些债务。本文呈现了首个将已确立的AITD映射到其智能体表现形式的系统映射，展示了传统债务如何演变为系统级负债，包括记忆不一致、编排脆弱性、级联故障和不安全的自主决策。研究结果表明，技术债务不仅限于软件制品，还涵盖智能体行为、协调机制以及智能体、工具和执行环境之间的交互。本文进一步研究了其对AI信任、风险与安全管理（AI TRiSM）的影响，强调了对可信赖性、治理、安全、运营弹性和可持续性技术债务的影响。总体而言，这项工作将AgTD确立为基础软件工程构造，并为管理自主多智能体AI系统中的技术债务提供了转换框架、分类法和研究议程。
英文摘要
The emergence of Agentic AI systems, characterized by autonomous reasoning, multi-agent collaboration, tool orchestration, adaptive decision-making, and persistent memory, represents a fundamental shift from traditional AI pipelines to dynamic software ecosystems. While AI Technical Debt (AITD) has been widely studied in machine learning and software engineering, existing models assume static, component-level architectures and fail to capture the dynamic and emergent behaviors of agentic environments. To address this gap, this paper introduces Agentic Technical Debt (AgTD), defined as technical debt that emerges, accumulates, propagates, and amplifies due to the autonomous and collaborative nature of Agentic AI systems. Building on our prior systematic scoping review of 31 AITDs across seven root-cause categories, we employ a theory-informed transformation methodology to reinterpret these debts in Agentic AI through direct transformation, contextual transformation, and manifestation expansion. We present the first systematic mapping of established AITDs to their agentic manifestations, showing how conventional debts evolve into system-level liabilities, including memory inconsistencies, orchestration fragility, cascading failures, and unsafe autonomous decision-making. Our findings show that technical debt extends beyond software artifacts to encompass agent behaviors, coordination mechanisms, and interactions among agents, tools, and execution environments. We further examine its implications for AI Trust, Risk, and Security Management (AI TRiSM), highlighting impacts on trustworthiness, governance, security, operational resilience, and Sustainability Technical Debt. Overall, this work establishes AgTD as a foundational software engineering construct and provides a transformation framework, taxonomy, and research agenda for managing technical debt in autonomous multi-agent AI systems.
Comments32 pages, 7 figures, 7 tables, submitted to IEEE Transactions on Software Engineering
