# KaVa: Latent Reasoning via Compressed KV-Cache Distillation

arXiv: https://arxiv.org/abs/2510.02312 · HTML: https://mlsanity.com/paper/2510.02312/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning.
- Builds on 22 of its 36 references that are in the map.
- First posted on arXiv 2 Oct 2025.

## Placed in

- LLM reasoning / [Test-time compute and efficient thinking](https://mlsanity.com/lr/test-time-compute-and-efficient-thinking/)
- Efficient LLM inference and serving / [Efficient reasoning and agent inference](https://mlsanity.com/inference/efficient-reasoning-and-agent-inference/)

## Builds on (most cited first, 22 of 22)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [Qwen2.5-Coder Technical Report](https://mlsanity.com/paper/2409.12186/) (2024)
- [Training Large Language Models to Reason in a Continuous Latent Space](https://mlsanity.com/paper/2412.06769/) (2024)
- [Humanity's Last Exam](https://mlsanity.com/paper/2501.14249/) (2025)
- [PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling](https://mlsanity.com/paper/2406.02069/) (2024)
- [From Explicit CoT to Implicit CoT: Learning to Internalize CoT Step by Step](https://mlsanity.com/paper/2405.14838/) (2024)
- [CODI: Compressing Chain-of-Thought into Continuous Space via Self-Distillation](https://mlsanity.com/paper/2502.21074/) (2025)
- [Implicit Chain of Thought Reasoning via Knowledge Distillation](https://mlsanity.com/paper/2311.01460/) (2023)
- [Token Assorted: Mixing Latent and Text Tokens for Improved Language Model Reasoning](https://mlsanity.com/paper/2502.03275/) (2025)
- [Stress Testing Deliberative Alignment for Anti-Scheming Training](https://mlsanity.com/paper/2509.15541/) (2025)
- [A Survey on Latent Reasoning](https://mlsanity.com/paper/2507.06203/) (2025)
- [Reasoning Beyond Language: A Comprehensive Survey on Latent Chain-of-Thought Reasoning](https://mlsanity.com/paper/2505.16782/) (2025)
- [R-KV: Redundancy-aware KV Cache Compression for Reasoning Models](https://mlsanity.com/paper/2505.24133/) (2025)
- [KeyDiff: Key Similarity-Based KV Cache Eviction for Long-Context LLM Inference in Resource-Constrained Environments](https://mlsanity.com/paper/2504.15364/) (2025)
- [System-1.5 Reasoning: Traversal in Language and Latent Spaces with Dynamic Shortcuts](https://mlsanity.com/paper/2505.18962/) (2025)
- [Parallel Continuous Chain-of-Thought with Jacobi Iteration](https://mlsanity.com/paper/2506.18582/) (2025)
- [DeepTheorem: Advancing LLM Reasoning for Theorem Proving Through Natural Language and Reinforcement Learning](https://mlsanity.com/paper/2505.23754/) (2025)
- [KV-Distill: Nearly Lossless Learnable Context Compression for LLMs](https://mlsanity.com/paper/2503.10337/) (2025)

## Built on by (most cited first, 8 of 8)

- [The Latent Space: Foundation, Evolution, Mechanism, Ability, and Outlook](https://mlsanity.com/paper/2604.02029/) (2026)
- [What Makes Effective Supervision in Latent Chain-of-Thought: An Information-Theoretic Analysis](https://mlsanity.com/paper/2606.20075/) (2026)
- [LatentDx: Latent Multi-Agent Communication for Cross-Hospital Rare-Disease Diagnosis](https://mlsanity.com/paper/2606.13945/) (2026)
- [Why Struggle with Continuous Latents? Interpretable Discrete Latent Reasoning via Rendered Compression](https://mlsanity.com/paper/2606.29712/) (2026)
- [State commitment learning: training language models to distinguish computation from memory](https://mlsanity.com/paper/2606.05201/) (2026)
- [LoRi: Low-Rank Distillation for Implicit Reasoning](https://mlsanity.com/paper/2606.05315/) (2026)
- [Does Out-of-Sight Equal Out-of-Mind in CoT Monitorability?](https://mlsanity.com/paper/2608.04928/) (2026)
- [INTACT: Inducing Latent Reasoning on a Frozen Backbone](https://mlsanity.com/paper/2610.19568/) (2026)

## Abstract (arXiv)

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. In this work we propose KaVa, the first framework that bridges this gap by distilling knowledge directly from a compressed KV-cache of the teacher into a latent-reasoning student via self-distillation, leveraging the representational flexibility of continuous latent tokens to align stepwise KV trajectories. We show that the abstract, unstructured knowledge within compressed KV-cache, which lacks direct token correspondence, can serve as a rich supervisory signal for a latent reasoning student. Empirically, the approach consistently outperforms strong latent baselines, exhibits markedly smaller degradation from equation-only to natural-language traces, and scales to larger backbones while preserving efficiency. These results establish compressed KV-cache distillation as a scalable supervision signal for latent reasoning, combining the accuracy of CoT-trained teachers with the efficiency and deployability of latent inference.