# Cook2LTL: Translating Cooking Recipes to LTL Formulae using Large Language Models

arXiv: https://arxiv.org/abs/2310.00163 · HTML: https://mlsanity.com/paper/2310.00163/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Sep 2023.

## Built on by (most cited first, 12 of 12)

- [Formal Mathematical Reasoning: A New Frontier in AI](https://mlsanity.com/paper/2412.16075/) (2024)
- [Safety Guardrails for LLM-Enabled Robots](https://mlsanity.com/paper/2503.07885/) (2025)
- [Learning Compositional Behaviors from Demonstration and Language](https://mlsanity.com/paper/2505.21981/) (2025)
- [CoT-TL: Low-Resource Temporal Knowledge Representation of Planning Instructions Using Chain-of-Thought Reasoning](https://mlsanity.com/paper/2410.16207/) (2024)
- [The Effectiveness of Large Language Models in Transforming Unstructured Text to Standardized Formats](https://mlsanity.com/paper/2503.02650/) (2025)
- [DREAM: Domain-aware Reasoning for Efficient Autonomous Underwater Monitoring](https://mlsanity.com/paper/2509.13666/) (2025)
- [Integrating Explanations in Learning LTL Specifications from Demonstrations](https://mlsanity.com/paper/2404.02872/) (2024)
- [Integrating Disambiguation and User Preferences into Large Language Models for Robot Motion Planning](https://mlsanity.com/paper/2404.14547/) (2024)
- [Geometric Algebra Meets Large Language Models: Instruction-Based Transformations of Separate Meshes in 3D, Interactive and Controllable Scenes](https://mlsanity.com/paper/2408.02275/) (2024)
- [SEAL: SEmantic-Augmented Imitation Learning via Language Model](https://mlsanity.com/paper/2410.02231/) (2024)
- [Embedding Large Language Models into Flow Controls: An Agentic Framework for Adaptive and Trustworthy Automated Cooking](https://mlsanity.com/paper/2608.04768/) (2026)
- [Do Recipes Have Personas? Characterizing and Generating Creator Style in Attributed Procedural Graphs](https://mlsanity.com/paper/2608.24369/) (2026)

## Abstract (arXiv)

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.