SOURCE-LINKED INTELLIGENCE

Learn Your Own Thoughts: Abstract Token Curriculum

arXiv · AI, language, vision and robotics · article · Sep 17, 2026 · UTC

Large Language Models (LLMs) have achieved remarkable reasoning capabilities by utilizing chain-of-thought (CoT) as a scratchpad for intermediate stages of thinking. However, CoT techniques require explicit supervision on thinking tokens, which requires rich, task-specific data. In this work, we propose Abstract Token Curriculum (ATC), a novel curriculum learning framework that elicits effective continuous intermediate representations without direct supervision or manual scratchpad design. ATC gradually increases problem complexity through a sequence of distributions, training the model to dev

Read original source ↗ Open in workspace

recordType

paper

region

Global