Metraipolis › archive › dc_784142dc812c

RoboFL: Federated Expert Assembly for World Action Models — arXiv:2609.34968

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.34968
License (as archived)
CC0-1.0
Archived
2026-10-07T21:03:07.643Z
SHA-256 of the archived text
99b17c95eb9bace88e24e66fcfbaccf567a80669ccab60ad4bd2da3b2d0c2a05
Stable URL of this page
https://metraipolis.com/documento/dc_784142dc812c

How to cite

RoboFL: Federated Expert Assembly for World Action Models — arXiv:2609.34968 — arXiv (en), https://arxiv.org/abs/2609.34968 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_784142dc812c (Metraipolis archive dc_784142dc812c, sha256 99b17c95eb9bace88e24e66fcfbaccf567a80669ccab60ad4bd2da3b2d0c2a05)
BibTeX
@misc{dc784142dc812c,
  title = {RoboFL: Federated Expert Assembly for World Action Models — arXiv:2609.34968},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.34968},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_784142dc812c; sha256 99b17c95eb9bace88e24e66fcfbaccf567a80669ccab60ad4bd2da3b2d0c2a05},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.34968. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Vision-language-action and world-action models are increasingly popular, yet remain bottlenecked by physical interaction data that is scarce, institutionally siloed, and task-heterogeneous. A natural federated solution is to let each client adapt a shared foundation model through parameter-efficient fine-tuning, avoiding the exchange of full-model updates. However, federating these adapters is nontrivial, as naive aggregation can entangle incompatible updates, while incorporating MoE-style routing into federated aggregation may dilute specialization and destabilize expert selection. We present RoboFL, which instantiates MoSAIC (Mixture of Slotted Adapters) for federated world-action learning. MoSAIC directly installs locally trained LoRA adapters as the expert branches of a server MoE. Server-side routers learn token assignments over these prior-informed branches while jointly refining routing and expert parameters. Foresight-to-Action Routing Distillation (FARD) aligns routing across the model's three paths, while Path-Consensus Expert Aggregation (PCEA) converts complete expert updates into a compact global adapter for personalized redistribution. Experiments on RoboTwin 2.0, RLBench, and a real-world Franka robot arm show the superiority of RoboFL with structured expert assembly, as it outperforms centralized PEFT InternVLA-A1 by 12.23% on the Franka arm, while reducing per-round client communication by up to 86.81% relative to MoE-based federated VLA baselines.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI).
Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.34968 — 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 2026-10-07T20:29:03.211Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).