{"ID":2829869,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.11584","arxiv_id":"2512.11584","title":"Atomic Action Slicing: Planner-Aligned Options for Generalist VLA Agents","abstract":"Current vision-language-action (VLA) models generalize poorly, particularly when tasks require new compositions of skills or objects. We introduce Atomic Action Slicing (AAS), a planner-aligned approach that decomposes long-horizon demonstrations into short, typed atomic actions that are easier for planners to use and policies to learn. Using LIBERO demonstrations, AAS produces a validated dataset of 2,124 atomic segments labeled with action type, temporal span, and confidence. A stronger segmenter (Gemini 2.5 Pro) closely matches planner-defined plans and remains robust under keyframe jitter, while smaller models perform worse on multi-object tasks. Fine-tuning CLIP-RT+ on our atomic dataset improves task success from 94.2% to 95.3% on LIBERO-Goal and 83.8% to 88.8% on LIBERO-Long. We publicly release the GATE-VLAP dataset on HuggingFace(https://huggingface.co/datasets/gate-institute/GATE-VLAP-datasets)","short_abstract":"Current vision-language-action (VLA) models generalize poorly, particularly when tasks require new compositions of skills or objects. We introduce Atomic Action Slicing (AAS), a planner-aligned approach that decomposes long-horizon demonstrations into short, typed atomic actions that are easier for planners to use and...","url_abs":"https://arxiv.org/abs/2512.11584","url_pdf":"https://arxiv.org/pdf/2512.11584v1","authors":"[\"Stefan Tabakov\",\"Asen Popov\",\"Dimitar Dimitrov\",\"S. Ensiye Kiyamousavi\",\"Vladimir Hristov\",\"Boris Kraychev\"]","published":"2025-12-12T14:14:27Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.AI\",\"cs.RO\"]","methods":"[]","has_code":false}