Metraipolis › archive › dc_41bbf0f5e5ed

Bayes-Sufficient Compression Is Not Enough: How Does Communication Help Multi-Agent Systems? — arXiv:2610.03769

Source
arXiv
Original
https://arxiv.org/abs/2610.03769
License (as archived)
CC0-1.0
Archived
2026-10-06T05:23:57.322Z
SHA-256 of the archived text
28ff0ea90d207fe5de4eb22f42f3438fee3f207ed47495d3be76685758965d51
Stable URL of this page
https://metraipolis.com/documento/dc_41bbf0f5e5ed

How to cite

Bayes-Sufficient Compression Is Not Enough: How Does Communication Help Multi-Agent Systems? — arXiv:2610.03769 — arXiv, https://arxiv.org/abs/2610.03769 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_41bbf0f5e5ed (Metraipolis archive dc_41bbf0f5e5ed, sha256 28ff0ea90d207fe5de4eb22f42f3438fee3f207ed47495d3be76685758965d51)
BibTeX
@misc{dc41bbf0f5e5ed,
  title = {Bayes-Sufficient Compression Is Not Enough: How Does Communication Help Multi-Agent Systems? — arXiv:2610.03769},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.03769},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_41bbf0f5e5ed; sha256 28ff0ea90d207fe5de4eb22f42f3438fee3f207ed47495d3be76685758965d51},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.03769. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Multi-agent LLM systems pair a sender with broad context and an executor with a limited local view. We study when a short message improves the executor's next decision, when raw context is preferable, and when a stronger sender helps. Our framework, \emph{receiver-relative bounded coordination}, expresses message utility as receiver gain minus protocol tax. Compression beats raw context when tax savings exceed losses from omitted information and decoder mismatch. Even \emph{Bayes-sufficient} compression can fail when a bounded executor cannot use its surface form. A three-stage decomposition separates externalization, absorption, and \emph{action closure}, explaining how errors remain after the correct content reaches the receiver. Under a single-crossing condition, sender upgrades help above a receiver-burden threshold. Across six benchmarks, the same Qwen protocol raises ContextBench joint accuracy from $0.633$ to $0.775$ but lowers ToolSandbox from $0.889$ to $0.653$. Fixed-message replay reveals closure failures despite correct artifact recovery. These results guide an inference-time selector that improves the accuracy-cost frontier on the evaluated communication regimes.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Information Theory (cs.IT); Multiagent Systems (cs.MA).
Pagina del lavoro: https://arxiv.org/abs/2610.03769 — 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 2026-10-06T05:23:50.220Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).