{"work":{"id":"bf92a5f5-41a7-4430-8d31-7bb2eadf1097","openalex_id":null,"doi":null,"arxiv_id":"2511.19433","raw_key":null,"title":"Mixture of Horizons in Action Chunking","authors":null,"authors_text":"Dong Jing, Gang Wang, Jiaqi Liu, Weiliang Tang, Zelong Sun, Yunchao Yao, Zhenyu Wei, Yunhui Liu, Zhiwu Lu, and Mingyu Ding","year":2025,"venue":"cs.RO","abstract":"Vision-language-action (VLA) models have shown remarkable capabilities in robotic manipulation, but their performance is sensitive to the $\\textbf{action chunk length}$ used during training, termed $\\textbf{horizon}$. Our empirical study reveals an inherent trade-off: longer horizons provide stronger global foresight but degrade fine-grained accuracy, while shorter ones sharpen local control yet struggle on long-term tasks, implying fixed choice of single horizons being suboptimal. To mitigate the trade-off, we propose a $\\textbf{mixture of horizons (MoH)}$ strategy. MoH rearranges the action chunk into several segments with different horizons, processes them in parallel with a shared action transformer, and fuses outputs with a light linear gate. It has three appealing benefits. 1) MoH exploits long-term foresight and short-term precision jointly within a single model, improving both performance and generalizability to complex tasks. 2) MoH is plug-and-play for full-attention action modules with minimal training or inference overhead. 3) MoH enables dynamic inference with adaptive horizons, which selects stable actions through cross-horizon consensus, achieving 2.5$\\times$ higher throughput than baselines while preserving superior performance. Extensive experiments over flow-based policies $\\pi_0$, $\\pi_{0.5}$, and one-step regression policy $\\pi_{\\text{reg}}$ demonstrate that MoH yields consistent and significant gains on both simulations and real-world tasks. Notably, under mixed-task setting, $\\pi_{0.5}$ with MoH reaches a new state-of-the-art with 99$\\%$ average success rate on LIBERO after only $30k$ training iterations. Project page: https://timsty1.github.io/moh/","external_url":"https://arxiv.org/abs/2511.19433","cited_by_count":null,"metadata_source":"pith","metadata_fetched_at":"2026-07-03T12:28:07.294441+00:00","pith_arxiv_id":"2511.19433","created_at":"2026-05-11T20:21:13.229484+00:00","updated_at":"2026-07-03T12:28:07.294441+00:00","title_quality_ok":true,"display_title":"Mixture of horizons in action chunking","render_title":"Mixture of horizons in action chunking"},"hub":{"state":{"work_id":"bf92a5f5-41a7-4430-8d31-7bb2eadf1097","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":15,"external_cited_by_count":null,"distinct_field_count":4,"first_pith_cited_at":"2026-01-29T17:07:43+00:00","last_pith_cited_at":"2026-07-02T07:18:53+00:00","author_build_status":"not_needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"not_needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-07-04T00:06:10.314011+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":5},{"context_role":"baseline","n":1}],"polarity_counts":[{"context_polarity":"background","n":5},{"context_polarity":"baseline","n":1}],"runs":{},"summary":{},"graph":{},"authors":[]}}