SYNLAT: Syntax-Aligned Text-Latent Compression for Chain-of-Thought Reasoning

Excerpt

arXiv:2610.03839v1 Announce Type: cross Abstract: Long chain-of-thought (CoT) traces impose substantial output-token costs. Under constrained budgets, compression must preserve answer-critical information, making boundary placement central. Token-level and fixed-length boundaries can fragment coherent spans such as phrases, formulas, and local derivations, whereas step-level boundaries can bind content requiring different compression actions. We introduce SynLat, a text-latent CoT framework that