cs.AINov 9, 2026

SCALE: Small-Model-First Concept Abstraction with LLM-Guided Experience Internalization

Authors: Hong Su

Organizations: H. Su is with the School of Computer Science, Chengdu University of Information Technology, Chengdu, China.

Abstract

Autonomous agents must continually acquire reusable knowledge from experience without relying on costly large language model (LLM) reasoning for every decision. However, existing experience-based approaches often struggle to transform accumulated observations and reasoning into compact knowledge that lightweight models can independently apply. This paper proposes SCALE, a small-model-first framework that integrates selective LLM reasoning, experience-driven concept abstraction, and knowledge internalization. A lightweight model handles routine predictions, while prediction errors and accumulated cross-episode evidence selectively trigger LLM reflection. The LLM analyzes relevant historical experiences, generates positive and negative counterfactual examples, and proposes reusable concept hypotheses. Independently validated concepts are progressively incorporated into hierarchical neural representations, enabling lightweight models to exploit increasingly abstract knowledge. Meanwhile, mastered experiences are excluded from active memory while their original records remain available in a complete archive. Experiments across ten random seeds show that historical recall improves held-out accuracy from 87.11% to 98.28%, hierarchical concept knowledge increases difficult-case accuracy from 55.33% to 66.47%, and abstract archiving reduces active experience records from 6,000 to 1,528.

Figures & tables

Explore similar work

CardsList
  1. Principles that Guide, Actions that Inform: Agent Evolution via Knowledge Abstraction

    Oct 3, 2026Bowen Ye, Yongchao Xu, Junkai Ma +2LLM AgentsSelf-Evolving Agents

  2. DELTAMEM: Incremental Experience Memory for LLM Agents via Residual Trees

    Jun 2, 2026Haoran Tan, Zeyu Zhang, Zhicheng Cao +2Continual Learning for LLM AgentsLLM Agent Memory

  3. Retrieval-Augmented LLM Agents: Learning to Learn from Experience

    Mar 18, 2026Thomas Palmeira Ferraz, Romain Deffayet, Vassilina Nikoulina +2Fine-TuningLLM Agent Training