智能体时代的软件工程：从可信变更到人机软件组织
Software Engineering in the Agent Era From Trustworthy Change to Human Agent Software Organizations
- Faculty of Computing Harbin Institute of Technology（哈尔滨工业大学计算机学院）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文针对智能体时代软件工程中可扩展执行的管控问题，提出含可信变更、责任拓扑、人机单元的框架，明确权威为分类轴并推导相关影响，贡献理论构建与操作化方法。
AI中文摘要：
软件智能体使数字执行具备弹性：代码仓库分析、代码生成、测试、迁移、工具使用及运维可被复制与并行化，且无需按比例增加人力。问题界定、语义承诺、验证、集成、注意力分配及残余风险接受仍受限于人类认知、组织权威与经济能力。应如何管控可扩展的执行，使组织能够接受并维持其变更？本文提出的可测试框架包含两个构建体与一个执行抽象：可信变更（Trustworthy Change, TC）是从意图经委托执行、验证、集成、接受至运维的工程对象；责任拓扑（Responsibility Topology）按独立残余风险接受权威的分布对组织分类——单中心拓扑拥有一个最终基线责任锚点，多锚点拓扑则需经独立治理域联合接受。人机单元（Human-Agent Cell, HAC）生成候选方案、提案与证据，执行环节不赋予接受权威。由于执行与权威的扩展方式不同，分布式HAC会产生上下文一致性与失效压力，而多锚点治理则增添了联合接受与明确的责任闭环。责任、问责、变更管理、规格说明、验证及人类监督早于本研究存在，本文仅主张智能体规模的执行改变了这些要素的组合方式，将权威明确为分类轴并推导其对变更状态、共享工程事实、验证及流控制的影响。渐进式规格说明与容量受限分析仍为待检验的假设而非定律。本文贡献了理论构建与操作化方法，其经验有效性仍有待受控、纵向及实地研究验证。
英文摘要：
Software agents make digital execution elastic: repository analysis, code generation, testing, migration, tool use, and operations can be replicated and parallelized without proportional human headcount. Problem framing, semantic commitment, verification, integration, attention, and residual-risk acceptance remain bounded by human cognition, organizational authority, and economic capacity. How should scalable execution be governed so organizations can accept and sustain its changes? Our testable framework has two constructs and one execution abstraction. Trustworthy Change (TC) is the engineering object moving from intent through delegated execution, verification, integration, acceptance, and operation. Responsibility Topology classifies organizations by the distribution of independent residual-risk acceptance authority. A single-center topology has one final baseline responsibility anchor; a multi-anchor topology requires joint acceptance across independently governed domains. The Human-Agent Cell (HAC) produces candidates, proposals, and evidence; execution grants no acceptance authority. As execution and authority scale differently, distributed HACs create context-coherence and invalidation pressures, while multi-anchor governance adds joint acceptance and explicit responsibility closure. Responsibility, accountability, change management, specification, verification, and human oversight predate this work; our claim is only that agent-scaled execution changes how they fit together. We make that authority an explicit classification axis and derive consequences for change state, shared engineering facts, verification, and flow control. Progressive Specification and bounded-capacity analysis remain hypotheses to test, not laws. We contribute theory construction and operationalization; empirical validity remains open to controlled, longitudinal, and field studies.
