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

arXiv: https://arxiv.org/abs/2604.19827 · HTML: https://mlsanity.com/paper/2604.19827/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 42 references that are in the map.
- First posted on arXiv 20 Apr 2026.

## Builds on (most cited first, 12 of 12)

- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [Why Do Multi-Agent LLM Systems Fail?](https://mlsanity.com/paper/2503.13657/) (2025)
- [Agentless: Demystifying LLM-based Software Engineering Agents](https://mlsanity.com/paper/2407.01489/) (2024)
- [The Impact of AI on Developer Productivity: Evidence from GitHub Copilot](https://mlsanity.com/paper/2302.06590/) (2023)
- [Grounded Copilot: How Programmers Interact with Code-Generating Models](https://mlsanity.com/paper/2206.15000/) (2022)
- [Measuring the Impact of Early-2025 AI on Experienced Open-Source Developer Productivity](https://mlsanity.com/paper/2507.09089/) (2025)
- [SWE-EVO: Benchmarking Coding Agents in Long-Horizon Software Evolution Scenarios](https://mlsanity.com/paper/2512.18470/) (2025)
- [Navigating the Complexity of Generative AI Adoption in Software Engineering](https://mlsanity.com/paper/2307.06081/) (2023)
- [Risk Analysis Techniques for Governed LLM-based Multi-Agent Systems](https://mlsanity.com/paper/2508.05687/) (2025)
- [From Technical Debt to Cognitive and Intent Debt: Rethinking Software Health in the Age of AI](https://mlsanity.com/paper/2603.22106/) (2026)
- [Time Warp: The Gap Between Developers' Ideal vs Actual Workweeks in an AI-Driven Era](https://mlsanity.com/paper/2502.15287/) (2025)

## Built on by (most cited first, 1 of 1)

- [Govern the Repository, Not the Agent: Measuring Ecosystem-Level Risk in AI-Native Software](https://mlsanity.com/paper/2606.28235/) (2026)

## Abstract (arXiv)

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?