arXiv：cs.CL· Naoki Wake, Justin Wagle·· 6 小时前AI 评分41
SharedKV-BT：为行为树智能体提供节点本地类型化决策
SharedKV-BT: Node-Local Typed Decisions for Behavior-Tree Agents
AI 导读
SharedKV-BT 让行为树每个活跃节点暴露阶段局部字段与候选，由 Shared-KV 并行打分选出决策并交给独立执行系统。在机器人操作、移动导航和电脑操作三类任务中，其类型化决策比提示词匹配的自回归解码快 2.36-4.15 倍。机器人操作任务上，节点局部 Shared-KV 将联合决策准确率从 75% 提升至 94%，闭环成功率从 0% 提升至 60%。
正文
Abstract: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.
| Comments: | 8 pages, 5 figures, 1 table. Last updated on October 5th, 2026 |
| Subjects: | Robotics (cs.RO); Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.07327 [cs.RO] |
| (or arXiv:2610.07327v1 [cs.RO] for this version) | |
| https://doi.org/10.48550/arXiv.2610.07327 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Naoki Wake [view email]
[v1]
Mon, 5 Oct 2026 19:59:12 UTC (935 KB)
来源：arXiv：cs.CL · arxiv.org