"Don't Do That!": Guiding Embodied Systems through Large Language Model-based Constraint Generation

[2506.04500] "Don't Do That!": Guiding Embodied Systems through Large Language Model-based Constraint Generation Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Artificial Intelligence arXiv:2506.04500 (cs) [Submitted on 4 Jun 2025 ( v1 ), last revised 9 Apr 2026 (this version, v3)] Title: "Don't Do That!": Guiding Embodied Systems through Large Language Model-based Constraint Generation Authors: Amin Seffo , Aladin Djuhera , Masataro Asai , Holger Boche View a PDF of the paper titled "Don't Do That!": Guiding Embodied Systems through Large Language Model-based Constraint Generation, by Amin Seffo and 3 other authors View PDF HTML (experimental) Abstract: Recent advancements in large language models (LLMs) have spurred interest in robotic navigation that incorporates complex spatial, mathematical, and conditional constraints from natural language into the planning problem. Such constraints can be informal yet highly complex, making it challenging to translate into a formal description that can be passed on to a planning algorithm. In this paper, we propose STPR, a constraint generation framework that uses LLMs to translate constraints (expressed as instructions on ``what not to do'') into executable Python functions. STPR leverages the LLM's strong coding capabilities to shift the problem description from language into structured and interpretable code, thus circumventing complex reasoning and avoiding potential hallucinations. We show that these LLM-generated functions accurately describe even complex mathematical constraints, and apply them to point cloud representations with traditional search algorithms. Experiments in a simulated Gazebo environment show that STPR ensures full compliance across several constraints and scenarios, while having short runtimes. We also verify that STPR can be used with smaller code LLMs, making it applicable to a wide range of compact models with low inference cost. Comments: ICLR 2026 Workshop -- Agentic AI in the Wild: From Hallucinations to Reliable Autonomy Subjects: Artificial Intelligence (cs.AI) ; Robotics (cs.RO) Cite as: arXiv:2506.04500 [cs.AI] (or arXiv:2506.04500v3 [cs.AI] for this version) https://doi.org/10.48550/arXiv.2506.04500 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Masataro Asai [ view email ] [v1] Wed, 4 Jun 2025 22:47:53 UTC (17,629 KB) [v2] Tue, 24 Feb 2026 14:56:22 UTC (8,835 KB) [v3] Thu, 9 Apr 2026 04:05:58 UTC (8,834 KB) Full-text links: Access Paper: View a PDF of the paper titled "Don't Do That!": Guiding Embodied Systems through Large Language Model-based Constraint Generation, by Amin Seffo and 3 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.AI < prev | next > new | recent | 2025-06 Change to browse by: cs cs.RO References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: 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

Related documents

• Using large language models for embodied planning introduces systematic safety risks#120522
• RECAST: Expanding the Boundaries of LLMs' Complex Instruction Following with Multi-Constraint Data#925783
• Voyager: An Open-Ended Embodied Agent with Large Language Models#16576
• MAGIC: Transition-Aware Generation of Navigable Multi-Scene Game Worlds with Large Language Models#363299
• CoCoBench: A Cooperative Coordination Benchmark for Embodied Multi-Agent Task Planning#792287