SOURCE-LINKED INTELLIGENCE

STRETCH the Boundaries: A Unified Self-Taught Framework for Progressive LLM Evolution

arXiv · AI, language, vision and robotics · article · Sep 16, 2026 · UTC

Large language models (LLMs) often suffer from capability stagnation in self-improvement training because fixed difficulty levels fail to adapt to their evolving proficiency. To address this issue, we propose STRETCH (Self-Taught Reasoning Evolution via Targeted CHallenge), a unified framework inspired by cognitive scaffolding theory. STRETCH introduces a dynamic Stretch Zone mechanism that continuously aligns question difficulty with the model's solving capability. Within a single parameter space, the model alternates between a Scaffolder that generates adaptive, boundary-pushing challenges a

Read original source ↗ Open in workspace

recordType

paper

region

Global