[
    {
        "id": "osp-25519",
        "type": "article-journal",
        "title": "ChunkTrust: Adapting Execution Horizons for Robot Policies with Action-Expert Evidence",
        "author": [
            {
                "family": "Huang",
                "given": "Fanding"
            },
            {
                "family": "Jiang",
                "given": "Jingyan"
            },
            {
                "family": "Bao",
                "given": "Shifeng"
            },
            {
                "family": "Pu",
                "given": "Mingkang"
            },
            {
                "family": "Li",
                "given": "Shiwei"
            },
            {
                "family": "Xu",
                "given": "Jing"
            },
            {
                "family": "Xu",
                "given": "Shijia"
            },
            {
                "family": "Huang",
                "given": "Guanbo"
            },
            {
                "family": "Gu",
                "given": "Chenghao"
            },
            {
                "family": "Huang",
                "given": "Yuzhi"
            },
            {
                "family": "Li",
                "given": "Chenxin"
            },
            {
                "family": "Khan",
                "given": "Faisal Nadeem"
            },
            {
                "family": "Yang",
                "given": "Huan"
            },
            {
                "family": "Wang",
                "given": "Yan"
            },
            {
                "family": "Chi",
                "given": "Cheng"
            },
            {
                "family": "Wang",
                "given": "Zhi"
            }
        ],
        "URL": "https://omanscience.com/ar/articles/chunktrust-adapting-execution-horizons-for-robot-policies-with-action-expert-evidence",
        "language": "en",
        "issued": {
            "date-parts": [
                [
                    2026
                ]
            ]
        },
        "abstract": "Robot foundation policies predict action chunks, but how many actions to execute before replanning depends on the current task phase. We introduce ChunkTrust, which treats the execution horizon as a latent variable inferred from action-expert evidence rather than a fixed hyperparameter. Its training-free Action-aware Horizon Selector (AHS) combines intra-chunk spectral stability of generation traces with inter-chunk continuity between executed history and predicted actions. An online Beta posterior with kernel forgetting tracks horizon preferences across replans. A lightweight Query-based Horizon Adapter (QHA) optionally learns a context-conditioned dense prior from complementary evidence, fused with current evidence and episode-local Beta memory while the base policy remains frozen. Across RoboTwin2.0 and RoboCasa GR1 Tabletop, AHS improves overall task-averaged success for each evaluated base-policy configuration, including gains of +6.80 percentage points on $π_{0.5}$ over all 50 RoboTwin2.0 tasks and +9.67 percentage points on Qwen3GR00T in RoboCasa. AHS+QHA raises the gain over Base to +9.44 percentage points on the eight-task $π_{0.5}$ evaluation. On four real-world household tasks, AHS improves the equal-task mean normalized process score from 50.4% to 57.5%. Ablations examine the contributions of both evidence terms, temporal memory, and the learned prior. Project page is https://hf618.github.io/ChunkTrust.github.io/"
    }
]