Abstract-CoT lets models reason with short discrete latent token sequences from a reserved vocabulary, using warm-up training and RL to match verbal CoT performance with up to 11.6x fewer tokens.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
LLMs discover latent planning strategies up to five steps during training and execute them up to eight steps at test time, with larger models reaching seven under few-shot prompting, revealing a dissociation between discovery and execution.
citing papers explorer
-
Thinking Without Words: Efficient Latent Reasoning with Abstract Chain-of-Thought
Abstract-CoT lets models reason with short discrete latent token sequences from a reserved vocabulary, using warm-up training and RL to match verbal CoT performance with up to 11.6x fewer tokens.
-
The Depth Ceiling: On the Limits of Large Language Models in Discovering Latent Planning
LLMs discover latent planning strategies up to five steps during training and execute them up to eight steps at test time, with larger models reaching seven under few-shot prompting, revealing a dissociation between discovery and execution.