CacheFuse：免训练 KV 缓存插值实现异构 LLM 潜空间通信
Think Before You Speak: Enabling Training-Free Latent Communication Between Language Models
让两个不同大小的模型直接共享 KV 缓存、不用再互发文本，免训练就能提准 8.6 个百分点、首 token 快 12 倍，做多智能体的可以看看。
arXiv 论文提出 CacheFuse，一种免训练方法，通过线性插值将上游模型的 KV 缓存注入下游模型，让不同大小的异构模型绕过文本直接潜空间协作。在 4 个推理与知识基准上，准确率比单模型基线最高提升 8.6 个百分点，相比多模型间基于文本的通信，TTFT 最高加速 12.2 倍。此前方案需为每对模型训练融合适配器，CacheFuse 免去了这一部署成本。
Think Before You Speak: Enabling Training-Free Latent Communication Between Language Models
Large language models (LLMs) have demonstrated remarkable capabilities in solving complex tasks in coding, mathematical logic, and iterative reasoning, especially by coordinating effectively within multi-agent systems (MAS). However, language agents traditionally communicate via text exchange, which introduces a bottleneck in information transfer and adds prefill latency for downstream agents. Recent work proposes that directly sharing the key-value (KV) cache between language models can enable efficient latent collaboration, entirely bypassing standard text-based communication. To enable latent communication between heterogeneous models of different sizes, prior work introduces trained fusion adapters for each model pair, which limits practical deployment. We introduce CacheFuse, a training-free method which demonstrates that augmenting a downstream model with an upstream model's KV cache using linear interpolation consistently enables superior performance than the standalone downstream model can achieve. We systematically analyze CacheFuse across four reasoning and knowledge benchmarks and demonstrate up to 8.6 percentage points higher accuracy compared to single-model baselines and up to 12.2x TTFT speedup compared to text-based communication in multi-model inference.
