mlsanityData to 14 Oct 2026

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

arXiv 2605.27703 ↗First posted 26 May 2026cs.AIcited by 0

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 24 of its 32 references that are in the map. First posted on arXiv 26 May 2026.

Builds on

24 of 32 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025AI Agents and Agentic AI-Navigating a Plethora of Concepts for Future Manufacturing2 Jul

Other references · 23

  1. 2022Training language models to follow instructions with human feedbackcited by 15,971
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  4. 2020Scaling Laws for Neural Language Modelscited by 6,586
  5. 2022Training Compute-Optimal Large Language Modelscited by 3,019
  6. 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,918
  7. 2016Neural Architecture Search with Reinforcement Learningcited by 1,499
  8. 2023MemGPT: Towards LLMs as Operating Systemscited by 1,389
  9. 2020ALFWorld: Aligning Text and Embodied Environments for Interactive Learningcited by 1,205
  10. 2018Regularized Evolution for Image Classifier Architecture Searchcited by 909
  11. 2023Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizescited by 737
  12. 2022Efficiently Scaling Transformer Inferencecited by 539
11 more
  1. 2024A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applicationscited by 431
  2. 2023LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Modelscited by 287
  3. 2024A Survey on Knowledge Distillation of Large Language Modelscited by 284
  4. 2023How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Compositioncited by 223
  5. 2025Reinforcement Learning Meets Large Language Models: A Survey of Advancements and Applications Across the LLM Lifecyclecited by 35
  6. 2026PivotRL: High Accuracy Agentic Post-Training at Low Compute Costcited by 14
  7. 2015Unbounded Bayesian Optimization via Regularizationcited by 13
  8. 2025GraLoRA: Granular Low-Rank Adaptation for Parameter-Efficient Fine-Tuningcited by 10
  9. 2025URSA: The Universal Research and Scientific Agentcited by 6
  10. 2025Schema-Guided Scene-Graph Reasoning based on Multi-Agent Large Language Model Systemcited by 5
  11. 2025Omni-Router: Sharing Routing Decisions in Sparse Mixture-of-Experts for Speech Recognitioncited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025MAPRO: Recasting Multi-Agent Prompt Optimization as Maximum a Posteriori Inference
  2. 2024Active Inference for Self-Organizing Multi-LLM Systems: A Bayesian Thermodynamic Approach to Adaptation
  3. 2025Reasoning-Aware Prompt Orchestration: A Foundation Model for Multi-Agent Language Model Coordination
  4. 2026PACE: Two-Timescale Self-Evolution for Small Language Model Agents
  5. 2026Agent Skills for Large Language Models: Architecture, Acquisition, Security, and the Path Forward
  6. 2026Evolutionary System Prompt Learning for Reinforcement Learning in LLMs
  7. 2025MinionsLLM: a Task-adaptive Framework For The Training and Control of Multi-Agent Systems Through Natural Language
  8. 2026Skill-R1: Agent Skill Evolution via Reinforcement Learning