Metraipolis › archive › dc_7bb85a7822c0

PANDA: A Decentralized Architecture with Flexible Orchestration for Scalable, Fault-Tolerant Multi-Agent Systems — arXiv:2609.38482

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.38482
License (as archived)
CC0-1.0
Archived
2026-10-07T12:39:29.813Z
SHA-256 of the archived text
13bd2c11d19f18a3e049cabd5fb78192965cbb209c9bfd69600c97fa4536d2e9
Stable URL of this page
https://metraipolis.com/documento/dc_7bb85a7822c0

How to cite

PANDA: A Decentralized Architecture with Flexible Orchestration for Scalable, Fault-Tolerant Multi-Agent Systems — arXiv:2609.38482 — arXiv (en), https://arxiv.org/abs/2609.38482 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7bb85a7822c0 (Metraipolis archive dc_7bb85a7822c0, sha256 13bd2c11d19f18a3e049cabd5fb78192965cbb209c9bfd69600c97fa4536d2e9)
BibTeX
@misc{dc7bb85a7822c0,
  title = {PANDA: A Decentralized Architecture with Flexible Orchestration for Scalable, Fault-Tolerant Multi-Agent Systems — arXiv:2609.38482},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.38482},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7bb85a7822c0; sha256 13bd2c11d19f18a3e049cabd5fb78192965cbb209c9bfd69600c97fa4536d2e9},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.38482. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Existing architectures for LLM-based multi-agent systems (MAS) cannot reliably and efficiently solve multi-step tasks at scale: they struggle to support large numbers of agents and concurrent tasks, tolerate failures, govern agent interactions, and accommodate the diverse planning and execution patterns different tasks require. We present PANDA, a decentralized architecture that connects a large collective of heterogeneous, independently administered agents, letting them discover each other's capabilities and self-organize into small specialized teams per task. PANDA scales by decoupling collective communication from team communication, allowing agents to participate in multiple teams simultaneously, load-balancing tasks across the collective, and scheduling concurrent work within each agent. PANDA further separates the underlying architecture from the orchestration strategy, supporting three planning and execution patterns (star, chain, and mesh) that can be selected according to the structure and requirements of each task. PANDA detects infrastructure and orchestration failures and recovers affected tasks by dynamically replanning around failed components. Finally, to provide governance without a centralized service that would limit scalability, PANDA uses a web-of-trust model to constrain agent interactions to established trust relationships. We evaluate PANDA on the HotPotQA benchmark, demonstrating that it scales to thousands of agents, assembles teams in milliseconds, matches state-of-the-art accuracy at up to 8x the efficiency, and sustains 100% task completion under faults where existing systems fail.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-01 in cs.MA).
Categorie arXiv: Multiagent Systems (cs.MA) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.38482 — 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 2026-10-07T12:12:18.618Z dalla pagina https://arxiv.org/catchup/cs.MA/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).