让大模型之间不靠文字直接传信息，更快更准。
Latent Cache Flow: Model-to-Model Communication Without Text
- 用压缩后的隐状态传递信息，适配器仅是原方案的4%
- 在不同上下文场景下，准确率提升7.5%以上，速度提升8.5倍
- 适合需要高效协作的多模型智能体系统
当前大型语言模型（LLM）代理通过文本通信，存在解码延迟和信息损失问题。现有方法如缓存到缓存（C2C；Fu et al., 2026）通过训练适配器转换共享模型的键值（KV）缓存，但适配器体积大、训练成本高，且仅适用于相同上下文。本文提出隐状态缓存流（Latent Cache Flow, LCF），通过联合压缩与转换键值，将适配器大小降至C2C的约4%。针对上下文差异问题，设计适配器仅传输目标模型缺失的新信息摘要。初步实验表明，13 MB的精简版LCF适配器在相同上下文场景下比956 MB的C2C更准确；在不同上下文场景中，F1提升7.5%，精确匹配率提升23%，通信速度提升8.5倍。
原文摘要 · Abstract (English)
LLM agents today communicate via text, which incurs considerable latency and information loss due to the need to autoregressively decode the sharer model's state and encode at the receiver model. Recent work such as Cache-to-Cache (C2C; Fu et al., 2026) seeks to exchange KV caches by learning adapters that translate sharer KV matrices to the receiver model. However, the adapters are large and expensive to train, and translate individual tokens, which requires the target context to be identical. This is unsuitable for agent communication, where the LLMs have differing context. We introduce Latent Cache Flow (LCF). To address efficiency, we observe that keys and values can be jointly translated and compressed, reducing the adapter to about 4% of C2C's size. To address differing context, we design the adapter to transmit a summary of new information that the target model does not have. Our early experiments show that a pruned 13 MB LCF adapter can be more accurate than C2C at 956 MB in shared-context settings; for different contexts, LCF improves F1 by 7.5% and Exact Match by 23% while 8.5 times faster than text-based communication.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。