LATIDIA · Robótica

¿Observar, compartir o predecir? Desenredar la información del socio en la colaboración multiagente incorporada

arXiv:2610.16895v1 Announce Type: cross Resumen: Los LLM se utilizan como controladores de alto nivel para los agentes incorporados, pero no está claro si admiten el razonamiento colaborativo, como anticipar el ac de un colaborador

La noticia

arXiv:2610.16895v1 Announce Type: cross Abstract: LLMs are used as high-level controllers for embodied agents, but it remains unclear whether they support collaborative reasoning, such as anticipating a collaborator's actions in real-time teamwork without dialogue. We ask if observing the partner's state, exchanging object knowledge, and predicting the partner's next action, shape task outcomes and coordination when agents can share percepts but never intentions, plans, or task-level messages, and whether the two agents occupy symmetric roles. Using the Habitat-based PARTNR benchmark, we introduce a Decoupled Partial Observability regime that enforces strictly individual perception, and we augment decentralized zero-shot ReAct planners with Other Agent's State (OAS) observation, object Knowledge Exchange (KE) between