Metraipolis › archive › dc_ac8a8b9cbd7c

Decoupled Multi-Agent Orchestration — arXiv:2610.07556

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.07556
License (as archived)
CC0-1.0
Archived
2026-10-07T11:18:47.155Z
SHA-256 of the archived text
381a4bc53b1605ba2494a2c147db0e5a6a57c5eedd4e2cd8deca8c80674f623a
Stable URL of this page
https://metraipolis.com/documento/dc_ac8a8b9cbd7c

How to cite

Decoupled Multi-Agent Orchestration — arXiv:2610.07556 — arXiv (en), https://arxiv.org/abs/2610.07556 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ac8a8b9cbd7c (Metraipolis archive dc_ac8a8b9cbd7c, sha256 381a4bc53b1605ba2494a2c147db0e5a6a57c5eedd4e2cd8deca8c80674f623a)
BibTeX
@misc{dcac8a8b9cbd7c,
  title = {Decoupled Multi-Agent Orchestration — arXiv:2610.07556},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.07556},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ac8a8b9cbd7c; sha256 381a4bc53b1605ba2494a2c147db0e5a6a57c5eedd4e2cd8deca8c80674f623a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.07556. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Learned orchestration can automatically construct effective language-model multi-agent systems, but existing approaches couple planning to fixed worker pools and train decomposition and collaboration from the same terminal outcome, limiting transfer and obscuring credit assignment. We introduce DeOrch, which separates worker-agnostic planning from concrete worker selection. Its two-stage planner first decomposes the task without worker information, then chooses collaboration operations using compact, worker-identity-free matchability feedback from the pool, enabling conditional credit assignment to decomposition and collaboration decisions. A lightweight matcher estimates worker suitability from behavior on a fixed probe set and adapts online with a contextual bandit, allowing new workers to be incorporated without retraining the planner or matcher. Across diverse in- and out-of-distribution tasks, DeOrch outperforms prior automatic MAS orchestration methods with fewer worker calls than competing learned orchestrators, remains effective when transferred to an entirely unseen worker pool without retraining, and shows consistent gains from both components.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.07556 — 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 2026-10-07T11:15:24.520Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).