SCALE: Small-Model-First Concept Abstraction with LLM-Guided Experience Internalization
Overview
This research paper proposes SCALE, a small-model-first framework that integrates selective large language model (LLM) reasoning, experience-driven concept abstraction, and knowledge internalization. The system allows lightweight models to handle routine predictions while using the LLM for reflection on prediction errors and accumulated evidence. Validated concepts are incorporated into hierarchical neural representations, improving held-out accuracy from 87.11% to 98.28% and difficult-case accuracy from 55.33% to 66.47% across ten random seeds, while reducing active experience records from 6,000 to 1,528.
Generated from attributed reports · Updated 3 hours ago
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
Control: reported autonomous
“arXiv:2611.12120v1 Announce Type: cross 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 SCAL”
Exact source · revision 1Source owner not reported
Reported quantity · Reported accuracy: 66.47 percent · Basis not reported · Differing source assertions
“cy 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.”
Exact source · revision 1Source owner not reported
Reported quantity · Reported accuracy: 55.33 percent · Basis not reported · Differing source assertions
“cy 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.”
Exact source · revision 1Source owner not reported
Reported quantity · random seeds count: 10 other · Basis not reported
“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 accura”
Exact source · revision 1Source owner not reported
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsSignalSCALE: Small-Model-First Concept Abstraction with LLM-Guided Experience Internalization
This research paper proposes SCALE, a small-model-first framework that integrates selective large language model (LLM) reasoning, experience-driven concept abstraction, and knowledge internalization. The system allows lightweight models to handle routine predictions while using the LLM for reflection on prediction errors and accumulated evidence. Validated concepts are incorporated into hierarchical neural representations, improving held-out accuracy from 87.11% to 98.28% and difficult-case accuracy from 55.33% to 66.47% across ten random seeds, while reducing active experience records from 6,000 to 1,528.
Event coverage history
There is not enough continuous observation data to show a trend.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).