Hierarchical Prompt-Domain Control and Learning for Resource-Constrained Agentic Language Models
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
CoDa: Constrained Generation based Data Augmentation for Low-Resource NLP
We present CoDa (Constrained Generation based Data Augmentation), a controllable, effective, and training-free data augmentation technique for low-resource (data-scarce) NLP. Our approach is based on prompting off-the-sh…
Data AugmentationInstruction FollowingOptimizing Resource-Constrained Non-Pharmaceutical Interventions for Multi-Cluster Outbreak Control Using Hierarchical Reinforcement Learning
Non-pharmaceutical interventions (NPIs), such as diagnostic testing and quarantine, are crucial for controlling infectious disease outbreaks but are often constrained by limited resources, particularly in early outbreak …
Hierarchical Reinforcement LearningConstrained Hierarchical Monte Carlo Belief-State Planning
Optimal plans in Constrained Partially Observable Markov Decision Processes (CPOMDPs) maximize reward objectives while satisfying hard cost constraints, generalizing safe planning under state and transition uncertainty. …
Prmpt2Adpt: Prompt-Based Zero-Shot Domain Adaptation for Resource-Constrained Environments
Unsupervised Domain Adaptation (UDA) is a critical challenge in real-world vision systems, especially in resource-constrained environments like drones, where memory and computation are limited. Existing prompt-driven UDA…
Domain AdaptationUnsupervised Domain AdaptationCH-MARL: Constrained Hierarchical Multiagent Reinforcement Learning for Sustainable Maritime Logistics
Addressing global challenges such as greenhouse gas emissions and resource inequity demands advanced AI-driven coordination among autonomous agents. We propose CH-MARL (Constrained Hierarchical Multiagent Reinforcement L…
Decision MakingFairnessreinforcement-learningReinforcement Learning