AI RESEARCH
KaVa: Latent Reasoning via Compressed KV-Cache Distillation
arXiv CS.LG
•
ArXi:2510.02312v2 Announce Type: replace Large Language Models (LLMs) excel at multi-step reasoning problems with explicit chain-of-thought (CoT), but verbose traces incur significant computational costs and memory overhead, and often carry redundant, stylistic artifacts. Latent reasoning has emerged as an efficient alternative that internalizes the thought process, but it suffers from a critical lack of supervision, limiting its effectiveness on complex, natural-language reasoning traces.