← Back to all news
arXiv Machine Learning By Adam Deng, Shicheng Liu, Yada Zhu

Augment the Cache, Replace the Activation: A 2x2 Study of Internal-State Sharing

Read the original on arXiv Machine Learning →

The paper investigates how to efficiently share internal states between agents built from frozen language models. It proposes a shared pool approach where each agent publishes its internal state once, allowing peers to read it via a single mechanism, thereby avoiding the need for a dedicated transfer bridge for every agent pair. The study finds that augmenting the key‑value cache and replacing activations—rather than swapping them—yields better accuracy with minimal training, and that a single adapter can generalize across multiple publishers when their internal states are similar to the receiver’s.

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 Machine Learning.

Related stories

arXiv Machine Learning
Oct 16

Close Enough is Nowhere Near: Fidelity-Consumability Decoupling in KV Caches

The paper investigates whether a frozen transformer can use another model’s KV cache as a substitute for its own, finding that this approach fails because the reader only accepts caches within a narrow tolerable set. Experimental results show that none of eight substitution methods improve performance over a baseline, while a different strategy—adding the sender’s cache as extra context and only adapting queries—does outperform the baseline. The authors conclude that pursuing faithful cache substitution is misguided and that augmenting the reader’s own cache is the more promising direction.

By Adam Deng, Shicheng Liu, Yada Zhu
llmsagentsefficiencybenchmarks
More like this →
arXiv AI
Aug 24

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.

By Jiyao Liu, Qi Zhang, Yaoyi Jia, Ziwen Kan, Song Wang
llmsagentsdiffusionnlp
More like this →