{"ID":2856817,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.13857","arxiv_id":"2510.13857","title":"From Craft to Constitution: A Governance-First Paradigm for Principled Agent Engineering","abstract":"The advent of powerful Large Language Models (LLMs) has ushered in an ``Age of the Agent,'' enabling autonomous systems to tackle complex goals. However, the transition from prototype to production is hindered by a pervasive ``crisis of craft,'' resulting in agents that are brittle, unpredictable, and ultimately untrustworthy in mission-critical applications. This paper argues this crisis stems from a fundamental paradigm mismatch -- attempting to command inherently probabilistic processors with the deterministic mental models of traditional software engineering. To solve this crisis, we introduce a governance-first paradigm for principled agent engineering, embodied in a formal architecture we call ArbiterOS.","short_abstract":"The advent of powerful Large Language Models (LLMs) has ushered in an ``Age of the Agent,'' enabling autonomous systems to tackle complex goals. However, the transition from prototype to production is hindered by a pervasive ``crisis of craft,'' resulting in agents that are brittle, unpredictable, and ultimately untrus...","url_abs":"https://arxiv.org/abs/2510.13857","url_pdf":"https://arxiv.org/pdf/2510.13857v1","authors":"[\"Qiang Xu\",\"Xiangyu Wen\",\"Changran Xu\",\"Zeju Li\",\"Jianyuan Zhong\"]","published":"2025-10-12T15:42:46Z","proceeding":"cs.SE","tasks":"[\"cs.SE\",\"cs.AI\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}