arXiv AI October 15, 2026 By Zhiwei Chen, Zhongtao Rao, Waikit Xiu, Yuxiang Zhang, Shuting Cui, Jian Chen, Tianxiang Zhao

LatentRemedy: Efficient Remedy For Non-Prefix KV Cache Reuse in Multi-Agent Systems

Read the original on arXiv AI →

LatentRemedy is a method designed to improve inference efficiency in multi‑agent systems that share non‑prefix KV caches. By inserting a small number of task‑conditioned latent tokens generated via an MLP, the target agent can better interpret reused context without recomputing the shared block. Experiments demonstrate that LatentRemedy consistently outperforms existing reuse baselines on conflicting tasks while keeping TTFT close to direct reuse as cache size grows.

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

Oct 7

KVCMAS: Efficient KV cache Correction for Shared Context in Multi-Agent Systems

arXiv:2609.34060v2 Announce Type: replace Abstract: Prompt-specialized multi-agent systems enable multiple agents to share a model while performing complementary roles to solve complex tasks. However...

By Hyesung Jeon, Hyeongju Ha, Seoyoung Lee, Beomseok Kang, Jae-Joon Kim

agents efficiency multimodal

arXiv AI

Aug 18

Learning Agent Execution for KV-Cache Management in Agentic Serving

arXiv:2608. 14624v1 Announce Type: new Abstract: Multi-agent LLM systems have emerged as an important deployment paradigm for AI services, where each user request is decomposed into a sequence of specialized agents.

By Rui Zhang, Chaeeun Kim, Shaoting Feng, Kuntai Du, Yuhan Liu, Yi Zhong, Cheng-Wei Ching, Junchen Jiang, Liting Hu

llms agents efficiency

arXiv Computation and Language

Aug 21

ReCache: Efficient KV Cache Reuse and Compression for Tool-Augmented LLM Agents

arXiv:2608. 19662v1 Announce Type: new Abstract: Agentic language models repeatedly encode tool and skill schemas that recur across requests in different combinations and orders, preventing standard prefix caching from reusing their key--value (KV) states.

By Yichu Fang, Sitong Wei, Haozhe Hu, Xiaoyu Shen

llms agents nlp efficiency benchmarks

arXiv Computation and Language

Sep 10

KVShareArena: KV-Cache Reuse Across Contexts and Model Checkpoints

arXiv:2609.10266v1 Announce Type: new Abstract: LLM serving systems already reuse KV caches, but only when the reused text sits at the very start of the prompt. Two growing workloads break this condi...

By Xi Shi, Qian Lou

llms rag agents benchmarks

arXiv AI

Jun 2

Leyline: KV Cache Directives for Agentic Inference

arXiv:2606. 01065v1 Announce Type: cross Abstract: Modern KV cache management assumes the chatbot workload: prompts arrive once and the cache grows append-only, so prefix caching and forward-only eviction are correct by construction.

By Bole Ma, Jan Eitzinger, Harald Koestler

llms agents efficiency

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

One email a morning, machine-written

Related stories

KVCMAS: Efficient KV cache Correction for Shared Context in Multi-Agent Systems

Learning Agent Execution for KV-Cache Management in Agentic Serving

ReCache: Efficient KV Cache Reuse and Compression for Tool-Augmented LLM Agents

KVShareArena: KV-Cache Reuse Across Contexts and Model Checkpoints

Leyline: KV Cache Directives for Agentic Inference

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