Matteo Cercola, Katie Z Luo, Milan Ganai, John Alora, Simone Formentin, Marco Pavone · 2026 · arXiv
DOI: 10.48550/arXiv.2610.28166 · open-access PDF
Quando vários planos são válidos, este compromisso esconde alternativas que poderiam de outra forma ser selecionadas ou revisadas. Introduzimos o Plano Generativo Latente (GPL), que representa o estado de raciocínio como uma distribuição condicional de baixa dimensão sobre planos, como qual objeto, alcance ou rota usar. Isto torna o estado de raciocínio abordável: sem retrabalhar o VLA, os planos podem ser amostradados (coberta), selecionados a pedido (steerin)
Machine translation (Meta M2M100); the English original follows.
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 (steerin
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
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.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange