The paper discusses a third paradigm shift in software development, termed Software 3.0, where context and reasoning drive behavior. It proposes that Software 3.0 converges to three core components: a generalized database for all persistent state, a large model that performs reasoning and generation, and an agent that orchestrates the interaction between the two. The authors formalize this convergence, present a minimal reference architecture, and analyze its applicability and limits, noting that it applies best to task domains that are expressible, verifiable, externally stateful, and tool-complete.
arXiv:2606. 05608v2 Announce Type: replace-cross Abstract: For over half a century, software engineering has operated on a foundational premise: human engineers decompose problems, encode decision logic into static code, and manually adapt that code as requirements evolve.
By Zhenfeng Cao
arXiv:2606. 00288v1 Announce Type: new Abstract: Large language models are undergoing a transition from model technology to system technology.
By Hai Lin
The paper proposes a shift from AI model storage to AI model management, introducing the concept of "learnware"—a combination of a model and its specification. Learnware specifications are generated without exposing developers’ training data, enabling models from different sources to be identified, reused, and assembled for new tasks. The Learnware Dock System (LDS) offers a framework for managing these learnwares and facilitates collaboration among independently developed models through a shared specification protocol.
By Zhi-Hua Zhou
arXiv:2606. 05608v1 Announce Type: cross Abstract: For over half a century, software engineering has operated on a foundational premise: human engineers decompose problems, encode decision logic into static code, and manually adapt that code as requirements evolve.
By Zhenfeng Cao
arXiv:2603. 14147v2 Announce Type: replace Abstract: The generative artificial intelligence (AI) ecosystem is undergoing rapid transformations that threaten its sustainability.
By Margarita Belova, Yuval Kansal, Yihao Liang, Jiaxin Xiao, Niraj K. Jha
arXiv:2608. 03609v1 Announce Type: new Abstract: Agentic systems driven by large language models (LLMs) are increasingly deployed in real-world workflows where they act on persistent operational data.
By Alejandro J. Mercado, Alessio Lomuscio
The paper proposes a shift from simple AI model storage to comprehensive AI model management, introducing the concept of "learnware"—a model paired with a specification that can be generated without exposing training data. By treating learnware as the basic unit, the Learnware Dock System (LDS) enables identification, reuse, and assembly of independently developed models for new user tasks. The specifications, generated via a data‑preserving machine learning process, also act as a collaboration protocol, allowing models and agents to work together across different objectives.
arXiv:2606. 04025v1 Announce Type: cross Abstract: Dominant programming paradigms inherit an execution model optimised for a bygone era of a single human mind instructing a local machine, leaving contemporary systems burdened with historical path dependencies.
By Philip Sheldrake, Dirk Scheffler
arXiv:2606. 16010v1 Announce Type: cross Abstract: Large language models have achieved impressive performance on reasoning tasks spanning mathematics, science, programming, and commonsense inference.
By Raghu Anantharangachar
The paper argues that while machine-readable models like SysML v2 enable AI participation in systems engineering, the data architecture surrounding these models must also be robust. It introduces the concept of epistemic adequacy, split into read‑side adequacy (ensuring derivations, status, and provenance are answerable) and write‑side admissibility (filtering AI contributions before they enter the record). The authors illustrate their ideas using the public Apollo 11 SysML v2 reconstruction and propose a Governed‑Query Architecture Framework to enforce these principles.
By Jason Gower, Michael J. de C. Henshaw, Siyuan Ji
arXiv:2602. 12430v4 Announce Type: replace-cross Abstract: The transition from monolithic language models to modular, skill-equipped agents marks a defining shift in how large language models (LLMs) are deployed in practice.
By Renjun Xu, Yang Yan