SOURCE-LINKED INTELLIGENCE

STAGE: Diagnosing Semantic Transfer at Grounded Execution in Embodied Agents

arXiv · AI, language, vision and robotics · article · Sep 11, 2026 · UTC

Embodied language grounding requires more than identifying the referent of an instruction: recovered semantics must also control the action an agent exposes. We study this missing link as a semantic-action gap, where instruction semantics are recoverable but weakly expressed in native continuous actions. We introduce SAT-Bench, a fixed-observation counterfactual benchmark that holds the visual scene and agent state fixed while changing only instruction semantics. On LIBERO target-name and pixel-grounded relation swaps, target recovery reaches 100.0% and 95.8%, whereas OpenVLA action sensitivit

Read original source ↗ Open in workspace

recordType

paper

region

Global