外观
论文arXiv 2610.0732723 天前
SharedKV-BT：行为树智能体的节点局部类型化决策
原文链接：SharedKV-BT: Node-Local Typed Decisions for Behavior-Tree Agents（arXiv 2610.07327 · 发布日期：2026-10-05）
SharedKV-BT: Node-Local Typed Decisions for Behavior-Tree Agents
SharedKV-BT用行为树节点局部字段与Shared-KV并行评分，缓解互依决策延迟，并在操作、导航和电脑使用任务验证。
核心要点
- 自回归决策接口灵活但逐token生成有延迟，现有共享前缀方法未建模依赖或验证执行。
- 每个活跃BT节点暴露阶段局部字段和候选，Shared-KV并行评分后交给独立执行系统。
- 三类任务中，类型化决策比匹配提示的自回归解码快2.36至4.15倍。
- 操作任务上，联合决策准确率由75%升至94%，闭环成功率由0%升至60%。
验证范围与局限：验证范围为摘要所述的机器人操作、移动导航和计算机使用任务，未说明仿真或真机设置。
英文摘要 (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.
作者：Naoki Wake, Justin Wagle
来源
本页事实对应的公开页面，以原文为准。