# Swarm Telepathy: Prefill-Free KV-Cache Transfer Across Families

arXiv: https://arxiv.org/abs/2610.15095 · HTML: https://mlsanity.com/paper/2610.15095/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Agentic AI for wireless networks, one of 16 directions in LLM agents and tool use.
- Builds on 23 of its 34 references that are in the map.
- First posted on arXiv 10 Oct 2026.

## Placed in

- LLM agents and tool use / [Agentic AI for wireless networks](https://mlsanity.com/agents/agentic-ai-for-wireless-networks/)

## Builds on (most cited first, 23 of 23)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Gemma 2: Improving Open Language Models at a Practical Size](https://mlsanity.com/paper/2408.00118/) (2024)
- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [Gemma 3 Technical Report](https://mlsanity.com/paper/2503.19786/) (2025)
- [CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society](https://mlsanity.com/paper/2303.17760/) (2023)
- [Training Large Language Models to Reason in a Continuous Latent Space](https://mlsanity.com/paper/2412.06769/) (2024)
- [LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion](https://mlsanity.com/paper/2306.02561/) (2023)
- [Mixture-of-Agents Enhances Large Language Model Capabilities](https://mlsanity.com/paper/2406.04692/) (2024)
- [LLMs Get Lost In Multi-Turn Conversation](https://mlsanity.com/paper/2505.06120/) (2025)
- [ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMs](https://mlsanity.com/paper/2309.13007/) (2023)
- [Multiagent Finetuning: Self Improvement with Diverse Reasoning Chains](https://mlsanity.com/paper/2501.05707/) (2025)
- [Exchange-of-Thought: Enhancing Large Language Model Capabilities through Cross-Model Communication](https://mlsanity.com/paper/2312.01823/) (2023)
- [KVLink: Accelerating Large Language Models via Efficient KV Cache Reuse](https://mlsanity.com/paper/2502.16002/) (2025)
- [LLM Harmony: Multi-Agent Communication for Problem Solving](https://mlsanity.com/paper/2401.01312/) (2024)
- [DroidSpeak: KV Cache Sharing for Cross-LLM Communication and Multi-LLM Serving](https://mlsanity.com/paper/2411.02820/) (2024)
- [Latent Space Communication via K-V Cache Alignment](https://mlsanity.com/paper/2601.06123/) (2026)
- [Cross-Model KV Cache Transfer in LLM Families: A Closed-Form Linear Mapping for Prefill Reuse](https://mlsanity.com/paper/2608.03893/) (2026)
- [ICaRus: Identical Cache Reuse for Efficient Multi Model Inference](https://mlsanity.com/paper/2603.13281/) (2026)
- [Latent Cache Flow: Model-to-Model Communication Without Text](https://mlsanity.com/paper/2605.22863/) (2026)
- [See What I See, Know What I Think: Dense Latent Communication Across Heterogeneous Agents](https://mlsanity.com/paper/2606.13594/) (2026)
- [CacheBridge: Efficient Cross-Model KV Cache Transfer](https://mlsanity.com/paper/2609.00891/) (2026)
- [Context Branching for LLM Conversations: A Version Control Approach to Exploratory Programming](https://mlsanity.com/paper/2512.13914/) (2025)
- [Dual-Cache Latent Space Communication between Heterogeneous Language Models](https://mlsanity.com/paper/2608.20617/) (2026)

## Abstract (arXiv)

LLM multi-agent systems split work across agents that communicate through text. An agent summarizes its findings, another agent receives the text. This constrains communication to discrete tokens and costs redundant compute, limiting bandwidth and capabilities of multi-agent systems. Recent works demonstrate KV-cache transfer between LLMs but they either require the LLMs to be within the same family or cannot function across context, thus requiring the receiver to prefill text. We present SwaT (Swarm Telepathy), the first cross-family KV-cache transfer method that allows prefill-free communication in multi-family multi-agent systems. In an agent-to-agent communication setting, combining SwaT with recent advances in KV-cache compaction beats text-to-text communication in both accuracy and speed, with a mean of 40% higher accuracy and a mean of 4× faster wall-clock time. Experiments show SwaT achieves high performance on 17 benchmarks across 12 LLMs and 6 families. Additionally, given a sender Vision-Language Model (VLM), SwaT is able to transfer the vision capabilities to a text-only receiver LLM exceeding text-to-text communication despite SwaT being trained on text-only data. SwaT keeps both sender and receiver models frozen without fine-tuning and only requires <50M tokens and <1 GPU-day to train.