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

[2608.27797] CEDAR: Automata as Verifiable Interfaces for Language-Guided Embodied Action Skip to main content Search Submit Donate Log in Computer Science > Artificial Intelligence arXiv:2608.27797 (cs) [Submitted on 28 Aug 2026] Title: CEDAR: Automata as Verifiable Interfaces for Language-Guided Embodied Action Authors: Lekai Chen , Alvaro Velasquez , Ashutosh Trivedi View PDF HTML (experimental) Abstract: 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. Subjects: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL); Formal Languages and Automata Theory (cs.FL) Cite as: arXiv:2608.27797 [cs.AI] (or arXiv:2608.27797v1 [cs.AI] for this version) https://doi.org/10.48550/arXiv.2608.27797 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Lekai Chen [ view email ] [v1] Fri, 28 Aug 2026 00:25:48 UTC (4,413 KB) Full-text links: Access Paper: View PDF HTML (experimental) TeX Source view license Additional Features Audio Summary Current browse context: cs.AI < prev | next > new | recent | 2026-08 Change to browse by: cs cs.CL cs.FL References & Citations SciX Google Scholar Semantic Scholar export BibTeX citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab)

Related documents

• CEDAR: Automata as Verifiable Interfaces for Language-Guided Embodied Action#779713
• PlanGuard: A Guardrail for Multi-Step Plan Safety in Embodied Agents#1117132
• FluxVLA Engine: A One-Stop VLA Engineering Platform for Embodied Intelligence#1123592
• FluxVLA Engine: A One-Stop VLA Engineering Platform for Embodied Intelligence#919445
• Can Agents Infer Environment from Interaction? Evidence from Agentic Automata Learning#1117470