Hierarchical Prompt-Domain Control and Learning for Resource-Constrained Agentic Language Models

Computer Science > Artificial Intelligence [Submitted on 26 May 2026] Hierarchical Prompt-Domain Control and Learning for Resource-Constrained Agentic Language Models Joan Vendrell Gallart, Russell Bent, Michael Grosskopf Large Language Models are increasingly deployed inside agentic systems, where they must follow structured protocols, adapt to evolving states, and operate under memory, latency, and cost constraints. In such regimes, prompt extension is unreliable: growing contexts can push compact models outside their effective prompt domain, while deployment-time fine-tuning remains limited by scarce data and compute. We propose a hierarchical control-and-learning framework in which a compact model is first distilled to learn the required output schema, then supervised online by an oracle-controller loop. The controller monitors protocol validity and semantic performance, projects accumulated histories into a feasible prompt domain, and triggers lightweight oracle-supervised fine-tuning under drift. This separates schema learning for communication compatibility from semantic adaptation for task-level correction. We formalize prompt-domain feasibility and attention-induced saturation, motivating control of the effective prompt state rather than reliance on nominal context length. Using Multi-Fidelity Bayesian Optimization as a controlled sequential testbed, we characterize a core deployment failure mode and show improved reliability and cost-efficiency over non-hierarchical, distillation-only, and non-distilled baselines. Subjects: Artificial Intelligence (cs.AI) Cite as: arXiv:2605.27703 [cs.AI]   (or arXiv:2605.27703v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2605.27703 Focus to learn more Submission history From: Joan Vendrell Gallart [view email] [v1] Tue, 26 May 2026 21:23:30 UTC (13,639 KB) Access Paper: view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-05 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)