More Is Different: Toward a Theory of Emergence in AI-Native Software Ecosystems

2026-04-20

AI Summary

This study addresses emergent ecosystem-level failures—such as architectural entropy, cascading faults, and comprehension debt—in multi-agent AI systems, which traditional software engineering theories struggle to explain. For the first time, it models AI-native software ecosystems as complex adaptive systems (CAS), leveraging Holland’s six defining CAS properties to construct a testable analytical framework that integrates microstate variables, coarse-graining functions, and measures of causal emergence. The work advances seven falsifiable propositions to challenge or extend Lehman’s laws of software evolution and advocates shifting from component-level governance to ecosystem-level monitoring. This paradigm offers a novel pathway toward enhancing the stability, maintainability, and governance of AI-native systems.

Technology Category

• Multiagent Systems: Agent/AI Theories and Architectures
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Philosophy and Ethics of AI: AI & Epistemology

Application Category

• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

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?

Problem

• emergence
• AI-native software ecosystems
• complex adaptive systems
• software evolution
• multi-agent systems

Innovation

• Complex Adaptive Systems
• Emergence
• AI-Native Software
• Architectural Entropy
• Causal Emergence