Metraipolis › archive › dc_2daa881de284
Prefill-Free Cross-Family KV Cache Transfer for Heterogeneous Multi-Agent LLMs — arXiv:2609.32259
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.32259
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T20:54:03.146Z
- SHA-256 of the archived text
6cd0b1b50078972eb41fde38d25bf463506f2c78cee3505370a3a6b617bd5ec7- Stable URL of this page
https://metraipolis.com/documento/dc_2daa881de284
How to cite
Prefill-Free Cross-Family KV Cache Transfer for Heterogeneous Multi-Agent LLMs — arXiv:2609.32259 — arXiv (en), https://arxiv.org/abs/2609.32259 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2daa881de284 (Metraipolis archive dc_2daa881de284, sha256 6cd0b1b50078972eb41fde38d25bf463506f2c78cee3505370a3a6b617bd5ec7)
BibTeX
@misc{dc2daa881de284,
title = {Prefill-Free Cross-Family KV Cache Transfer for Heterogeneous Multi-Agent LLMs — arXiv:2609.32259},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.32259},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2daa881de284; sha256 6cd0b1b50078972eb41fde38d25bf463506f2c78cee3505370a3a6b617bd5ec7},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.32259. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Recent multi-agent LLM systems increasingly combine heterogeneous models for specialized agent roles. However, text-based communication requires each receiver to prefill shared context already processed by the sender. Reusing the sender's key-value (KV) cache avoids this redundancy, but prefill-free transfer across model families must handle differences in tokenization, model depth, and KV representations. To address these issues, we propose \textit{HeteroFold}, a prefill-free cross-family KV cache transfer method that keeps both the sender and receiver frozen. HeteroFold aligns model structures, maps the sender cache into the receiver space, and calibrates it to preserve receiver behavior. Across six transfer directions, HeteroFold achieves the best cache-transfer performance on all four long-context benchmarks and most short-context settings. It also matches text-based communication on the multi-agent benchmark. At 32K context length, Llama-3.1-8B$\rightarrow$Ministral-3-14B transfer is $10.7\times$ faster than Native Prefill and $1.18$--$1.47\times$ faster than the state-of-the-art prefill-free baselines, Dense Latent and KV Ridge. These results show that HeteroFold enables efficient cross-family KV reuse without receiver prefill.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.MA).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG); Multiagent Systems (cs.MA).
Pagina del lavoro: https://arxiv.org/abs/2609.32259 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T20:24:41.660Z dalla pagina https://arxiv.org/catchup/cs.MA/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).