SOURCE-LINKED INTELLIGENCE

CEDAR: Automata as Verifiable Interfaces for Language-Guided Embodied Action

arXiv · AI, language, vision and robotics · article · Aug 28, 2026 · UTC

Natural-language tasking of embodied agents is rarely just goal specification: users also impose constraints that must persist while the world changes. Code-generating LLM agents can produce plausible behaviors for such instructions, but their free-form programs provide no stable object to verify, compose with new constraints, or repair from a failing trace. We present CEDAR, a counterexample-guided framework that grounds instructions as regular languages over environment event traces. CEDAR uses a language model for semantic judgments and execution traces for correction, then represents both

Read original source ↗ Open in workspace

recordType

paper

region

Global