arXiv AI August 24, 2026 By Jiyao Liu, Qi Zhang, Yaoyi Jia, Ziwen Kan, Song Wang

Dual-Cache Latent Space Communication between Heterogeneous Language Models

The paper introduces XKV, a latent protocol that enables efficient communication between heterogeneous language models by translating a sharer's key‑value cache into a receiver's context. XKV overcomes limitations of prior methods by jointly pooling both caches, reconciling differing layer depths, and allowing each receiver position to retrieve its own residual in native KV geometry. Across 45 dataset‑model pairings, XKV outperforms previous protocols and text communication while using fewer parameters and achieving faster translation times.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv Machine Learning

Jun 9

Latent Cache Flow: Model-to-Model Communication Without Text

arXiv:2605. 22863v2 Announce Type: replace Abstract: 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.

By Maximillian Rossi, Prajwal Raghunath, Eugene Wu

llms agents

arXiv AI

Oct 1

Prefill-Free Cross-Family KV Cache Transfer for Heterogeneous Multi-Agent LLMs

arXiv:2609.32259v2 Announce Type: replace Abstract: Recent multi-agent LLM systems increasingly combine heterogeneous models for specialized agent roles. However, text-based communication requires ea...

By Vincent-Daniel Yun, Woosang Lim, Haneul Yoo, Sungjoo Yoo, Murali Annavaram, Sai Praneeth Karimireddy

llms agents nlp efficiency benchmarks

arXiv AI

Aug 13

XBridge: Entity-Grounded Latent Bridge for Heterogeneous LLM Communication

arXiv:2608. 11676v1 Announce Type: new Abstract: Heterogeneous multi-agent LLM systems, where agents are powered by different model families, can outperform homogeneous configurations by reducing redundant reasoning patterns.

By Wooseong Yang, Wei-Chieh Huang, Weizhi Zhang, Yu Wang, Philip S. Yu, Junhyun Lee

llms agents benchmarks

arXiv AI

Sep 1

A Universal Context-Reuse Layer for Cross-Model KV Sharing

arXiv:2608.30963v1 Announce Type: cross Abstract: Modern large language model (LLM) serving systems increasingly operate over repeated or shared context, yet each model typically performs its own pre...

By Yi Li, Dongming Jiang, Yi Zhao, Bingzhe Li

llms agents nlp

arXiv Machine Learning

Jun 2

LRAgent: Efficient KV Cache Sharing for Multi-LoRA LLM Agents

arXiv:2602. 01053v2 Announce Type: replace Abstract: Role specialization in multi-LLM agent systems is often realized via multi-LoRA, where agents share a pretrained backbone and differ only by lightweight adapters.

By Hyesung Jeon, Hyeongju Ha, Jae-Joon Kim

llms agents fine-tuning efficiency benchmarks

arXiv Machine Learning

Sep 14

Fixed State, Long Reach: What a Constant-Size Cache Buys Block Diffusion at Scale

The paper investigates how block‑diffusion language models can use a constant‑size cache to enable efficient parallel decoding. By employing sequence mixers that summarize completed blocks into a reusable state and a block‑causal training objective, the authors pretrain three 3B block‑diffusion denoisers (attention, Mamba, and hybrid) on 300 B tokens. The resulting state‑space cache remains O(1) in memory and latency regardless of context length, yielding significant speed‑up and memory savings compared to traditional attention‑based caches, especially at very long sequences.

By Vaibhav Singh, Pierre-Andr\'e No\"el, Torsten Scholak, Eugene Belilovsky, Oleksiy Ostapenko

llms diffusion efficiency safety

One email a morning, machine-written

Related stories

Latent Cache Flow: Model-to-Model Communication Without Text

Prefill-Free Cross-Family KV Cache Transfer for Heterogeneous Multi-Agent LLMs

XBridge: Entity-Grounded Latent Bridge for Heterogeneous LLM Communication

A Universal Context-Reuse Layer for Cross-Model KV Sharing

LRAgent: Efficient KV Cache Sharing for Multi-LoRA LLM Agents

Fixed State, Long Reach: What a Constant-Size Cache Buys Block Diffusion at Scale