# Code Models are Zero-shot Precondition Reasoners

arXiv: https://arxiv.org/abs/2311.09601 · HTML: https://mlsanity.com/paper/2311.09601/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 26 references that are in the map.
- First posted on arXiv 16 Nov 2023.

## Builds on (most cited first, 21 of 21)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Do As I Can, Not As I Say: Grounding Language in Robotic Affordances](https://mlsanity.com/paper/2204.01691/) (2022)
- [Code as Policies: Language Model Programs for Embodied Control](https://mlsanity.com/paper/2209.07753/) (2022)
- [ALFWorld: Aligning Text and Embodied Environments for Interactive Learning](https://mlsanity.com/paper/2010.03768/) (2020)
- [Inner Monologue: Embodied Reasoning through Planning with Language Models](https://mlsanity.com/paper/2207.05608/) (2022)
- [Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents](https://mlsanity.com/paper/2201.07207/) (2022)
- [CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis](https://mlsanity.com/paper/2203.13474/) (2022)
- [PAL: Program-aided Language Models](https://mlsanity.com/paper/2211.10435/) (2022)
- [ProgPrompt: Generating Situated Robot Task Plans using Large Language Models](https://mlsanity.com/paper/2209.11302/) (2022)
- [LLM+P: Empowering Large Language Models with Optimal Planning Proficiency](https://mlsanity.com/paper/2304.11477/) (2023)
- [Towards Scalable Multi-domain Conversational Agents: The Schema-Guided Dialogue Dataset](https://mlsanity.com/paper/1909.05855/) (2019)
- [Language Models of Code are Few-Shot Commonsense Learners](https://mlsanity.com/paper/2210.07128/) (2022)
- [Mind's Eye: Grounded Language Model Reasoning through Simulation](https://mlsanity.com/paper/2210.05359/) (2022)
- [Hierarchical Reinforcement Learning for Zero-shot Generalization with Subtask Dependencies](https://mlsanity.com/paper/1807.07665/) (2018)
- [Language Models are Few-Shot Butlers](https://mlsanity.com/paper/2104.07972/) (2021)
- [Meta Reinforcement Learning with Autonomous Inference of Subtask Dependencies](https://mlsanity.com/paper/2001.00248/) (2020)
- [Causal Reasoning of Entities and Events in Procedural Texts](https://mlsanity.com/paper/2301.10896/) (2023)
- [Few-shot Subgoal Planning with Language Models](https://mlsanity.com/paper/2205.14288/) (2022)
- [Multimodal Subtask Graph Generation from Instructional Videos](https://mlsanity.com/paper/2302.08672/) (2023)
- [Unsupervised Task Graph Generation from Instructional Video Transcripts](https://mlsanity.com/paper/2302.09173/) (2023)

## Built on by (most cited first, 3 of 3)

- [On the Prospects of Incorporating Large Language Models (LLMs) in Automated Planning and Scheduling (APS)](https://mlsanity.com/paper/2401.02500/) (2024)
- [Towards Learning Foundation Models for Heuristic Functions to Solve Pathfinding Problems](https://mlsanity.com/paper/2406.02598/) (2024)
- [ADAPT: Benchmarking Commonsense Planning under Unspecified Affordance Constraints](https://mlsanity.com/paper/2604.14902/) (2026)

## Abstract (arXiv)

One of the fundamental skills required for an agent acting in an environment to complete tasks is the ability to understand what actions are plausible at any given point. This work explores a novel use of code representations to reason about action preconditions for sequential decision making tasks. Code representations offer the flexibility to model procedural activities and associated constraints as well as the ability to execute and verify constraint satisfaction. Leveraging code representations, we extract action preconditions from demonstration trajectories in a zero-shot manner using pre-trained code models. Given these extracted preconditions, we propose a precondition-aware action sampling strategy that ensures actions predicted by a policy are consistent with preconditions. We demonstrate that the proposed approach enhances the performance of few-shot policy learning approaches across task-oriented dialog and embodied textworld benchmarks.