{"slug": "apivot-adaptive-planning-with-interleaved-vision-language-thoughts", "title": "APIVOT: Adaptive Planning with Interleaved Vision-Language Thoughts", "summary": "Researchers introduced APIVOT, a VLM-based planner that adaptively interleaves language and visual thoughts for long-horizon robot planning. APIVOT outperforms general-purpose VLMs and prior frameworks on kitchen tasks, especially in spatially constrained settings, by using visual thoughts for geometric feasibility verification.", "body_md": "arXiv:2607.08024v1 Announce Type: new\nAbstract: 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.", "url": "https://wpnews.pro/news/apivot-adaptive-planning-with-interleaved-vision-language-thoughts", "canonical_source": "https://arxiv.org/abs/2607.08024", "published_at": "2026-07-10 04:00:00+00:00", "updated_at": "2026-07-10 04:21:55.388260+00:00", "lang": "en", "topics": ["robotics", "large-language-models", "computer-vision", "artificial-intelligence", "ai-research"], "entities": ["APIVOT"], "alternates": {"html": "https://wpnews.pro/news/apivot-adaptive-planning-with-interleaved-vision-language-thoughts", "markdown": "https://wpnews.pro/news/apivot-adaptive-planning-with-interleaved-vision-language-thoughts.md", "text": "https://wpnews.pro/news/apivot-adaptive-planning-with-interleaved-vision-language-thoughts.txt", "jsonld": "https://wpnews.pro/news/apivot-adaptive-planning-with-interleaved-vision-language-thoughts.jsonld"}}