{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/cook2ltl-translating-cooking-recipes-to-ltl","title":"Cook2LTL: Translating Cooking Recipes to LTL Formulae using Large Language Models","arxiv_id":"2310.00163","date":"2023-09-29","proceeding":null,"authors":["Angelos Mavrogiannis","Christoforos Mavrogiannis","Yiannis Aloimonos"],"abstract":"Cooking recipes are challenging to translate to robot plans as they feature rich linguistic complexity, temporally-extended interconnected tasks, and an almost infinite space of possible actions. Our key insight is that combining a source of cooking domain knowledge with a formalism that captures the temporal richness of cooking recipes could enable the extraction of unambiguous, robot-executable plans. In this work, we use Linear Temporal Logic (LTL) as a formal language expressive enough to model the temporal nature of cooking recipes. Leveraging a pretrained Large Language Model (LLM), we present Cook2LTL, a system that translates instruction steps from an arbitrary cooking recipe found on the internet to a set of LTL formulae, grounding high-level cooking actions to a set of primitive actions that are executable by a manipulator in a kitchen environment. Cook2LTL makes use of a caching scheme that dynamically builds a queryable action library at runtime. We instantiate Cook2LTL in a realistic simulation environment (AI2-THOR), and evaluate its performance across a series of cooking recipes. We demonstrate that our system significantly decreases LLM API calls (-51%), latency (-59%), and cost (-42%) compared to a baseline that queries the LLM for every newly encountered action at runtime.","url_abs":"https://arxiv.org/abs/2310.00163v2","url_pdf":"https://arxiv.org/pdf/2310.00163v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"links_only","authors_date_abstract":"arXiv metadata, CC0 1.0 (https://info.arxiv.org/help/license), from the Kaggle arXiv metadata snapshot of 2026-09-12"},"code_links":[{"paper_slug":"cook2ltl-translating-cooking-recipes-to-ltl","repo_url":"https://github.com/angmavrogiannis/cook2ltl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"cook2ltl-translating-cooking-recipes-to-ltl","repo_url":"https://github.com/angmavrogiannis/cook2ltl-translating-cooking-recipes-to-primitive-ltl-action-formulae","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2310.00163","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}