Newest papers

Reasoning as a Distribution: Generative Plan Latents for Vision-Language-Action Models

Matteo Cercola, Katie Z Luo, Milan Ganai, John Alora, Simone Formentin, Marco Pavone · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.28166 · cited by 0 works (OpenAlex) · open-access PDF

Arabic

في حين أن السياسات الرامية إلى رؤية اللغة الإنجليزية (VLA) تظهر بشكل متزايد قبل العمل، فإن النماذج المنطقية الموجودة تخفيضت هذه القرارات المتوسطة إلى نموذج واحد. عندما تكون الخطة متعددة موثوق بها، فإن هذا التزام يغطي بدائل يمكن اختياره أو تعديلها من ناحية أخرى. نحن نقدم نموذج الخطة الإنجليزية (GPL) الذي يمثل الوضع المنطقي كجزء من توزيع ضوئي منخفض على الخطة، على سبيل المثال، ما هي الوجهة التي يمكن استخدامه، أو الارتقاء بها، أو الطريق إلى استخدامها. هذا يجعل الوضع المنطقي قابلًا للتطبيق: دون إعادة تدريب VLA، يمكن اختياره (الخزانة)، يتم اختي

Machine translation (Meta M2M100); the English original follows.

Abstract

Vision-Language-Action (VLA) policies increasingly reason before acting, but existing reasoning models compress this intermediate decision into a single representation. When several plans are valid, this commitment hides alternatives that could otherwise be selected or revised. We introduce the Generative Plan Latent (GPL), which represents the reasoning state as a low-dimensional conditional distribution over plans, such as which object, grasp, or route to use. This makes the reasoning state addressable: without retraining the VLA, plans can be sampled (coverage), selected on request (steering), and reweighted by deployment outcomes (outcome adaptation). We test all three on SimplerEnv manipulation with $π_0$, and extend the analysis to RoboCasa, LIBERO, and a maze domain. Steering the plan raises the fraction of executions that follow the request from 0.48 to 0.94, while the same guidance on the native action distribution shows no reliable gain. Finally, we show that an explicit plan is most useful when it carries decision information not already determined by the observation.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Artificial intelligence, Plan (archaeology), Generative grammar, Retraining, Machine learning

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.28166, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange