Meta-Ctrl: Guaranteed Plan Generation by Decoupling Syntactic and Semantic Constraints

[2608.22149] Meta-Ctrl: Guaranteed Plan Generation by Decoupling Syntactic and Semantic Constraints Skip to main content Search Submit Donate Log in Computer Science > Robotics arXiv:2608.22149 (cs) [Submitted on 23 Aug 2026 ( v1 ), last revised 28 Aug 2026 (this version, v3)] Title: Meta-Ctrl: Guaranteed Plan Generation by Decoupling Syntactic and Semantic Constraints Authors: Gwen Yidou-Weng , Edward Sun , Tianyi Ma , Metin Alp Dogan , Benjie Wang , Allen Peng , Guy Van den Broeck , Yuchen Cui View PDF HTML (experimental) Abstract: LLMs generate fluent plans for robots but routinely violate the syntactic and se8mantic constraints they must satisfy to execute, and existing remedies trade formal guarantees against plan quality: soft methods (affordance scoring, grounded decoding) give no guarantee, while symbolic planners (LLM+P) discard the LM's commonsense. We propose \textbf{Meta-Ctrl}, a constrained-decoding framework that guarantees the encoded constraints while preserving the base LM's plan quality. Meta-Ctrl introduces \emph{meta-tokens}---a compact vocabulary of grounded actions---enforcing syntax at the token level and semantics (preconditions, goals, ordering) at the action level, an exact factorization that cuts the memory of constrained decoding from over 107TB to under 2GB. With it, a small open-weight LM becomes competitive where it otherwise sits at the bottom of the leaderboard: on WAH-NL under the LoTa-Bench protocol it reaches the highest reported subgoal success rate, exceeding GPT-4's, with consistent gains across the Embodied Agent Interface. We further demonstrate it on a real tabletop robot, where every generated plan satisfies its preconditions and goals by construction. Project website: this https URL Subjects: Robotics (cs.RO) ; Artificial Intelligence (cs.AI) Cite as: arXiv:2608.22149 [cs.RO] (or arXiv:2608.22149v3 [cs.RO] for this version) https://doi.org/10.48550/arXiv.2608.22149 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Gwen Yidou-Weng [ view email ] [v1] Sun, 23 Aug 2026 00:40:19 UTC (2,190 KB) [v2] Tue, 25 Aug 2026 18:39:21 UTC (2,224 KB) [v3] Fri, 28 Aug 2026 00:34:20 UTC (2,224 KB) Full-text links: Access Paper: View PDF HTML (experimental) TeX Source view license Additional Features Audio Summary Current browse context: cs.RO < prev | next > new | recent | 2026-08 Change to browse by: cs cs.AI 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) Major funding support from (opens in new tab) (opens in new tab) (opens in new tab)

Related documents

• Meta-Ctrl: Guaranteed Plan Generation by Decoupling Syntactic and Semantic Constraints#682830
• AstroAgentBench: Evaluating Agentic Planning on Space Mission Planning Tasks#1156256
• CompileRover: Revolutionizing Virtual Machine Compiler Optimization with a Tri-Role LLM-Driven Framework#1013159
• NotDec: WebAssembly Decompilation With Inter-Procedural Type Recovery#429456
• From Treatise’s Geometry to an AI-Driven Procedural Framework for Shape Grammars#355758