SOURCE-LINKED INTELLIGENCE

Ladders of Thought: A Self-Evolving Curriculum of Progressively Simplified Reasoning Traces

arXiv · AI, language, vision and robotics · article · Sep 22, 2026 · UTC

Large language models (LLMs) excel at reasoning when scaled to hundreds of billions of parameters, but small- and mid-scale models remain brittle reasoners even with knowledge distillation (KD). We present Ladders-of-Thought (LoT), a framework that improves reasoning by combining progressive question rewrites with a self-evolving curriculum. LoT automatically generates semantically faithful but easier variants of reasoning problems, organizes them into difficulty buckets using step-based measures, and employs a self-evolving bandit scheduler to allocate training adaptively. Evaluated on two re

Read original source ↗ Open in workspace

recordType

paper

region

Global