Metraipolis › archive › dc_da4da40d4fee

CEDAR: Automata as Verifiable Interfaces for Language-Guided Embodied Action — arXiv:2608.27797

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.27797
License (as archived): CC0-1.0
Archived: 2026-10-17T10:47:12.282Z
SHA-256 of the archived text: 6bad88685c07f5564906823a464ea50b108c39b9f983f926609498ec8ba0857d
Stable URL of this page: https://metraipolis.com/documento/dc_da4da40d4fee

How to cite

CEDAR: Automata as Verifiable Interfaces for Language-Guided Embodied Action — arXiv:2608.27797 — arXiv (en), https://arxiv.org/abs/2608.27797 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_da4da40d4fee (Metraipolis archive dc_da4da40d4fee, sha256 6bad88685c07f5564906823a464ea50b108c39b9f983f926609498ec8ba0857d)

BibTeX

@misc{dcda4da40d4fee,
  title = {CEDAR: Automata as Verifiable Interfaces for Language-Guided Embodied Action — arXiv:2608.27797},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.27797},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_da4da40d4fee; sha256 6bad88685c07f5564906823a464ea50b108c39b9f983f926609498ec8ba0857d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.27797. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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 skills and specifications as deterministic finite automata. This turns constraints into executable finite-state objects: a learned skill can be intersected with a learned sleep at night or stay in this biome specification, yielding a controller that enforces the learned constraint by construction rather than by repeated prompting. In Minecraft, with the same simulator/API observations available to a program-generating baseline, CEDAR maintains temporal and spatial constraints that the baseline fails to preserve and amortizes reuse of learned skills, reducing cumulative LLM queries. These results suggest that regular languages offer a practical verification layer between natural-language instructions and embodied-agent policies.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-31 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL); Formal Languages and Automata Theory (cs.FL).
Pagina del lavoro: https://arxiv.org/abs/2608.27797 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T10:33:42.349Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-31?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).