{"ID":6267821,"CreatedAt":"2026-07-10T01:11:38.759438437Z","UpdatedAt":"2026-07-12T01:02:22.86131488Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.08024","arxiv_id":"2607.08024","title":"APIVOT: Adaptive Planning with Interleaved Vision-Language Thoughts","abstract":"Long-horizon robot planning requires jointly reasoning over semantic task structure and geometric feasibility. To successfully execute a task, a robot must decompose goals, select task-relevant objects, and sequence actions, while ensuring that plans satisfy spatial constraints such as limited free space and object collisions. In this work, we propose APIVOT, a VLM-based planner that adaptively interleaves language and visual thoughts for long-horizon planning. APIVOT learns to leverage language for semantic reasoning, while using visual thoughts as imagined future states for internal verification of geometric feasibility. On long-horizon kitchen tasks, APIVOT outperforms general-purpose VLMs and prior planning frameworks, achieving the largest gains in spatially constrained settings. We find that APIVOT learns meaningful modality selection behavior, demonstrating that adaptive interleaving of vision-language thoughts improves both planning success and reasoning efficiency.","short_abstract":"Long-horizon robot planning requires jointly reasoning over semantic task structure and geometric feasibility. To successfully execute a task, a robot must decompose goals, select task-relevant objects, and sequence actions, while ensuring that plans satisfy spatial constraints such as limited free space and object col...","url_abs":"https://arxiv.org/abs/2607.08024","url_pdf":"https://arxiv.org/pdf/2607.08024v1","authors":"[\"Emily Jin\",\"Joy Hsu\",\"Yiqing Xu\",\"Weiyu Liu\",\"Nick Haber\",\"Jiajun Wu\"]","published":"2026-07-09T01:02:35Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\",\"cs.LG\",\"cs.RO\"]","methods":"[]","has_code":false}