Knowing When to Yield: Grounded Arbitration of User Corrections in Text-Based Embodied Agents

cs.AI updates on arXiv.org · 1h ago

arXiv:2610.00282v1 Announce Type: new Abstract: How should an embodied agent respond when a person's correction may be wrong? We formulate grounded correction arbitration as a choice among accepting, rejecting, inspecting the world, and asking the speaker. GAVA implements this interface with observation-bounded evidence, legal probes, and a one-step expected-loss rule. In text-only ALFWorld, 162…

Read original article on cs.AI updates on arXiv.org →