Metraipolis › archive › dc_a40074bb2587
StateBridge: Training-free Hidden-state Alignment for Latent Communication in LLM Multi-Agent Systems — arXiv:2608.13317
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.13317
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T04:17:38.532Z
- SHA-256 of the archived text
cfa2b0831e367d9112a043c1f9b5e9d0a0f405cd01866e71dfacd033f863e507- Stable URL of this page
https://metraipolis.com/documento/dc_a40074bb2587
How to cite
StateBridge: Training-free Hidden-state Alignment for Latent Communication in LLM Multi-Agent Systems — arXiv:2608.13317 — arXiv (en), https://arxiv.org/abs/2608.13317 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a40074bb2587 (Metraipolis archive dc_a40074bb2587, sha256 cfa2b0831e367d9112a043c1f9b5e9d0a0f405cd01866e71dfacd033f863e507)
BibTeX
@misc{dca40074bb2587,
title = {StateBridge: Training-free Hidden-state Alignment for Latent Communication in LLM Multi-Agent Systems — arXiv:2608.13317},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.13317},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a40074bb2587; sha256 cfa2b0831e367d9112a043c1f9b5e9d0a0f405cd01866e71dfacd033f863e507},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.13317. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large language model based multi-agent systems usually communicate in text, i.e., using discrete tokens. However, text introduces a discrete bottleneck. Converting the sender's continuous hidden states into discrete tokens discards information that token identities alone cannot capture. Recent work proposes latent communication as an alternative, where agents transmit hidden representations directly without converting them to text. However, existing latent methods either inject working memory layer by layer across the transformers, or require trained projectors that limit portability. We propose StateBridge, a training-free latent communication approach that aligns the sender's final-layer hidden states to the receiver's input space via a closed-form orthogonal transformation. Lightweight norm calibration and vocabulary anchoring ensure compatibility with the pretrained input distribution. The aligned states are prepended to the input of the receiver agent as a continuous prefix. We evaluate StateBridge on math reasoning, code generation, and question answering with four models from two families. StateBridge achieves the best or tied-best score on 22 out of 26 model-task pairs, consistently outperforming the strongest baseline. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-14 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.13317 — 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 2026-10-19T04:13:06.604Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).