mlsanityData to 14 Oct 2026

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

arXiv 2610.15095 ↗First posted 10 Oct 2026cs.LGcited by 0

On the map: LLM agents and tool use → Agentic AI for wireless networks

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.

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.

Builds on

23 of 34 references.

References · 23

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2024Gemma 2: Improving Open Language Models at a Practical Sizecited by 1,998
  3. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,988
  4. 2025Gemma 3 Technical Reportcited by 1,824
  5. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Societycited by 1,395
  6. 2024Training Large Language Models to Reason in a Continuous Latent Spacecited by 797
  7. 2023LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusioncited by 564
  8. 2024Mixture-of-Agents Enhances Large Language Model Capabilitiescited by 438
  9. 2025LLMs Get Lost In Multi-Turn Conversationcited by 429
  10. 2023ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMscited by 309
  11. 2025Multiagent Finetuning: Self Improvement with Diverse Reasoning Chainscited by 95
  12. 2023Exchange-of-Thought: Enhancing Large Language Model Capabilities through Cross-Model Communicationcited by 82
11 more
  1. 2025KVLink: Accelerating Large Language Models via Efficient KV Cache Reusecited by 66
  2. 2024LLM Harmony: Multi-Agent Communication for Problem Solvingcited by 35
  3. 2024DroidSpeak: KV Cache Sharing for Cross-LLM Communication and Multi-LLM Servingcited by 35
  4. 2026Latent Space Communication via K-V Cache Alignmentcited by 17
  5. 2026Cross-Model KV Cache Transfer in LLM Families: A Closed-Form Linear Mapping for Prefill Reusecited by 15
  6. 2026ICaRus: Identical Cache Reuse for Efficient Multi Model Inferencecited by 8
  7. 2026Latent Cache Flow: Model-to-Model Communication Without Textcited by 8
  8. 2026See What I See, Know What I Think: Dense Latent Communication Across Heterogeneous Agentscited by 8
  9. 2026CacheBridge: Efficient Cross-Model KV Cache Transfercited by 6
  10. 2025Context Branching for LLM Conversations: A Version Control Approach to Exploratory Programmingcited by 3
  11. 2026Dual-Cache Latent Space Communication between Heterogeneous Language Modelscited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Prefill-Free Cross-Family KV Cache Transfer for Heterogeneous Multi-Agent LLMs
  2. 2025KVCOMM: Online Cross-context KV-cache Communication for Efficient LLM-based Multi-agent Systems
  3. 2026A Token/KV-Cache Communication Media Selection and Resource Allocation Strategy for Multi-Agent Collaboration
  4. 2026Receiver-Conditioned Latent Communication gives 94% CacheBack
  5. 2024Cut the Crap: An Economical Communication Pipeline for LLM-based Multi-Agent Systems
  6. 2026Good Agentic Friends Do Not Just Give Verbal Advice: They Can Update Your Weights
  7. 2026TokenDance: Scaling Multi-Agent LLM Serving via Collective KV Cache Sharing
  8. 2026Agent Memory Below the Prompt: Persistent Q4 KV Cache for Multi-Agent LLM Inference on Edge Devices