AI软件生态的异常行为源于集体互动，而非单个组件故障。
More Is Different: Toward a Theory of Emergence in AI-Native Software Ecosystems
- 将AI生态视为复杂适应系统，从交互中理解涌现特性。
- 提出可验证的七个命题，挑战传统软件演化理论。
- 适合研究AI系统可靠性与治理的开发者和研究人员。
软件工程面临根本性挑战：多智能体AI系统以传统理论无法解释的方式失效。尽管个体智能体表现正常，其交互却导致整个生态崩溃，暴露出对软件演化的理解缺口。本文主张，必须将AI原生软件生态系统视为复杂适应系统（CAS），其架构熵、级联故障、认知债务等涌现特性并非源自单个组件，而是由交互产生。我们把霍兰德的六项CAS属性映射到可观测的生态动态中，区分此类系统与微服务或开源网络的不同。为测量因果涌现，定义了微观状态变量、粗粒化函数及可行的测量框架。提出七个可证伪命题，将CAS理论与软件演化关联，在智能体层面假设失效时，挑战或扩展莱曼定律。若成立，需彻底转变：以生态级监控作为主要治理机制；若被推翻，现有理论只需渐进更新。无论如何，这项工作迫使我们反思：软件工程的核心假设能否经受自主代理时代的考验？
原文摘要 · Abstract (English)
Software engineering faces a fundamental challenge: multi-agent AI systems fail in ways that defy explanation by traditional theories. While individual agents perform correctly, their interactions degrade entire ecosystems, revealing a gap in our understanding of software evolution. This paper argues that AI-native software ecosystems must be studied as complex adaptive systems (CAS), where emergent properties like architectural entropy, cascade failures, and comprehension debt arise not from individual components, but from their interactions. We map Holland's six CAS properties onto observable ecosystem dynamics, distinguishing these systems from microservices or open-source networks. To measure causal emergence, we define micro-level state variables, coarse-graining functions, and a tractable measurement framework. Seven falsifiable propositions link CAS theory to software evolution, challenging or extending Lehman's laws where agent-level assumptions fail. If confirmed, these findings would demand a radical shift: ecosystem-level monitoring as the primary governance mechanism for AI-native systems. If refuted, existing theories may only need incremental updates. Either way, this work forces us to ask: Can software engineering's core assumptions survive the age of autonomous agents?
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。