{"ID":2865748,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.20729","arxiv_id":"2509.20729","title":"Robust, Observable, and Evolvable Agentic Systems Engineering: A Principled Framework Validated via the Fairy GUI Agent","abstract":"The Agentic Paradigm faces a significant Software Engineering Absence, yielding Agentic systems commonly lacking robustness, observability, and evolvability. To address these deficiencies, we propose a principled engineering framework comprising Runtime Goal Refinement (RGR), Observable Cognitive Architecture (OCA), and Evolutionary Memory Architecture (EMA). In this framework, RGR ensures robustness and intent alignment via knowledge-constrained refinement and human-in-the-loop clarification; OCA builds an observable and maintainable white-box architecture using component decoupling, logic layering, and state-control separation; and EMA employs an execution-evolution dual-loop for evolvability. We implemented and empirically validated Fairy, a mobile GUI agent based on this framework. On RealMobile-Eval, our novel benchmark for ambiguous and complex tasks, Fairy outperformed the best SoTA baseline in user requirement completion by 33.7%. Subsequent controlled experiments, human-subject studies, and ablation studies further confirmed that the RGR enhances refinement accuracy and prevents intent deviation; the OCA improves maintainability; and the EMA is crucial for long-term performance. This research provides empirically validated specifications and a practical blueprint for building reliable, observable, and evolvable Agentic AI systems.","short_abstract":"The Agentic Paradigm faces a significant Software Engineering Absence, yielding Agentic systems commonly lacking robustness, observability, and evolvability. To address these deficiencies, we propose a principled engineering framework comprising Runtime Goal Refinement (RGR), Observable Cognitive Architecture (OCA), an...","url_abs":"https://arxiv.org/abs/2509.20729","url_pdf":"https://arxiv.org/pdf/2509.20729v2","authors":"[\"Jiazheng Sun\",\"Ruimeng Yang\",\"Xu Han\",\"Jiayang Niu\",\"Mingxuan Li\",\"Te Yang\",\"Yongyong Lu\",\"Xin Peng\"]","published":"2025-09-25T04:21:31Z","proceeding":"cs.AI","tasks":"[\"cs.AI\",\"cs.HC\",\"cs.MA\"]","methods":"[]","has_code":false}