Metraipolis › archive › dc_3b614cbcda06

SharedKV-BT: Node-Local Typed Decisions for Behavior-Tree Agents — arXiv:2610.07327

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.07327
License (as archived)
CC0-1.0
Archived
2026-10-07T11:23:38.529Z
SHA-256 of the archived text
9321abdedd1d7af4cf9b82e87e158e14af98e960a225f972884afcca35f5b733
Stable URL of this page
https://metraipolis.com/documento/dc_3b614cbcda06

How to cite

SharedKV-BT: Node-Local Typed Decisions for Behavior-Tree Agents — arXiv:2610.07327 — arXiv (en), https://arxiv.org/abs/2610.07327 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3b614cbcda06 (Metraipolis archive dc_3b614cbcda06, sha256 9321abdedd1d7af4cf9b82e87e158e14af98e960a225f972884afcca35f5b733)
BibTeX
@misc{dc3b614cbcda06,
  title = {SharedKV-BT: Node-Local Typed Decisions for Behavior-Tree Agents — arXiv:2610.07327},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.07327},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3b614cbcda06; sha256 9321abdedd1d7af4cf9b82e87e158e14af98e960a225f972884afcca35f5b733},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.07327. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Agent tasks require sequences of interdependent decisions. Autoregressive models support more flexible decision interfaces than conventional classifiers but incur the latency of token-by-token generation. Recent shared-prefix methods reduce this cost by reusing encoded context and scoring multiple decisions in parallel, but do not model decision dependencies or verify execution. We propose SharedKV-BT, where each active node of a behavior tree (BT) exposes stage-local fields and candidates, and Shared-KV scores the candidates in parallel and passes the selected decision to a separate execution system. We tested SharedKV-BT on robot manipulation, mobile navigation, and computer-use tasks. Across three tasks, SharedKV-BT made typed decisions 2.36-4.15 times faster than prompt-matched autoregressive decoding. On the manipulation task, node-local Shared-KV improved joint decision accuracy from 75% to 94% and closed-loop success from 0% to 60%. Fixed-score policy replay showed that stage gating prevented out-of-order actions and external postconditions prevented premature completion.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Robotics (cs.RO) ; Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2610.07327 — 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 2026-10-07T11:15:39.479Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).