[
    {
        "id": "osp-17527",
        "type": "article-journal",
        "title": "SharedKV-BT: Node-Local Typed Decisions for Behavior-Tree Agents",
        "author": [
            {
                "family": "Wake",
                "given": "Naoki"
            },
            {
                "family": "Wagle",
                "given": "Justin"
            }
        ],
        "URL": "https://omanscience.com/en/articles/sharedkv-bt-node-local-typed-decisions-for-behavior-tree-agents",
        "language": "en",
        "issued": {
            "date-parts": [
                [
                    2026
                ]
            ]
        },
        "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."
    }
]