# CAPE: Corrective Actions from Precondition Errors using Large Language Models

arXiv: https://arxiv.org/abs/2211.09935 · HTML: https://mlsanity.com/paper/2211.09935/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 47 references that are in the map.
- First posted on arXiv 17 Nov 2022.

## Builds on (most cited first, 16 of 16)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Do As I Can, Not As I Say: Grounding Language in Robotic Affordances](https://mlsanity.com/paper/2204.01691/) (2022)
- [What Makes Good In-Context Examples for GPT-3?](https://mlsanity.com/paper/2101.06804/) (2021)
- [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)
- [Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality](https://mlsanity.com/paper/2204.03162/) (2022)
- [Image Segmentation Using Text and Image Prompts](https://mlsanity.com/paper/2112.10003/) (2021)
- [VirtualHome: Simulating Household Activities via Programs](https://mlsanity.com/paper/1806.07011/) (2018)
- [Integrated Task and Motion Planning](https://mlsanity.com/paper/2010.01083/) (2020)
- [Open-vocabulary Queryable Scene Representations for Real World Planning](https://mlsanity.com/paper/2209.09874/) (2022)
- [Keep CALM and Explore: Language Models for Action Generation in Text-based Games](https://mlsanity.com/paper/2010.02903/) (2020)
- [Pre-trained Language Models as Prior Knowledge for Playing Text-based Games](https://mlsanity.com/paper/2107.08408/) (2021)
- [Generating Executable Action Plans with Environmentally-Aware Language Models](https://mlsanity.com/paper/2210.04964/) (2022)

## Built on by (most cited first, 30 of 30)

- [The Rise and Potential of Large Language Model Based Agents: A Survey](https://mlsanity.com/paper/2309.07864/) (2023)
- [Language Models can Solve Computer Tasks](https://mlsanity.com/paper/2303.17491/) (2023)
- [A Survey on Vision-Language-Action Models for Embodied AI](https://mlsanity.com/paper/2405.14093/) (2024)
- [REFLECT: Summarizing Robot Experiences for Failure Explanation and Correction](https://mlsanity.com/paper/2306.15724/) (2023)
- [Translating Natural Language to Planning Goals with Large-Language Models](https://mlsanity.com/paper/2302.05128/) (2023)
- [Flooding Spread of Manipulated Knowledge in LLM-Based Multi-Agent Communities](https://mlsanity.com/paper/2407.07791/) (2024)
- [GPT-4V(ision) for Robotics: Multimodal Task Planning from Human Demonstration](https://mlsanity.com/paper/2311.12015/) (2023)
- [Multi-Agent Evolve: LLM Self-Improve through Co-evolution](https://mlsanity.com/paper/2510.23595/) (2025)
- [Grounding Complex Natural Language Commands for Temporal Tasks in Unseen Environments](https://mlsanity.com/paper/2302.11649/) (2023)
- [Robot Utility Models: General Policies for Zero-Shot Deployment in New Environments](https://mlsanity.com/paper/2409.05865/) (2024)
- [Natural Language Can Help Bridge the Sim2Real Gap](https://mlsanity.com/paper/2405.10020/) (2024)
- [Learning to Reason over Scene Graphs: A Case Study of Finetuning GPT-2 into a Robot Language Model for Grounded Task Planning](https://mlsanity.com/paper/2305.07716/) (2023)
- [Generating consistent PDDL domains with Large Language Models](https://mlsanity.com/paper/2404.07751/) (2024)
- [Self-driven Grounding: Large Language Model Agents with Automatical Language-aligned Skill Learning](https://mlsanity.com/paper/2309.01352/) (2023)
- [REMAC: Self-Reflective and Self-Evolving Multi-Agent Collaboration for Long-Horizon Robot Manipulation](https://mlsanity.com/paper/2503.22122/) (2025)
- [RoboAgent: Chaining Basic Capabilities for Embodied Task Planning](https://mlsanity.com/paper/2604.07774/) (2026)
- [Robot Operation of Home Appliances by Reading User Manuals](https://mlsanity.com/paper/2505.20424/) (2025)
- [Scene Graph-Guided Proactive Replanning for Failure-Resilient Embodied Agent](https://mlsanity.com/paper/2508.11286/) (2025)
- [STAR: A Foundation Model-driven Framework for Robust Task Planning and Failure Recovery in Robotic Systems](https://mlsanity.com/paper/2503.06060/) (2025)
- [Self-Corrective Task Planning by Inverse Prompting with Large Language Models](https://mlsanity.com/paper/2503.07317/) (2025)
- [RAIDER: Tool-Equipped Large Language Model Agent for Robotic Action Issue Detection, Explanation and Recovery](https://mlsanity.com/paper/2503.17703/) (2025)
- [RoboPARA: Dual-Arm Robot Planning with Parallel Allocation and Recomposition Across Tasks](https://mlsanity.com/paper/2506.06683/) (2025)
- [SAI: Solving AI Tasks with Systematic Artificial Intelligence in Communication Network](https://mlsanity.com/paper/2310.09049/) (2023)
- [Mixed-Initiative Dialog for Human-Robot Collaborative Manipulation](https://mlsanity.com/paper/2508.05535/) (2025)
- [KITE: Keyframe-Indexed Tokenized Evidence for VLM-Based Robot Failure Analysis](https://mlsanity.com/paper/2604.07034/) (2026)
- [LangPert: Detecting and Handling Task-level Perturbations for Robust Object Rearrangement](https://mlsanity.com/paper/2504.09893/) (2025)
- [Leveraging Pre-trained Large Language Models with Refined Prompting for Online Task and Motion Planning](https://mlsanity.com/paper/2504.21596/) (2025)
- [Grounded Vision-Language Interpreter for Long-Horizon Bimanual Task and Motion Planning](https://mlsanity.com/paper/2506.03270/) (2025)
- [ProTracer: Proprioception-Guided Failure Diagnosis in Robot Manipulation](https://mlsanity.com/paper/2609.21369/) (2026)
- [FRAMES: Failure Recovery And Monitoring of Embodied Skills for Humanoid Loco-Manipulation](https://mlsanity.com/paper/2609.22538/) (2026)

## Abstract (arXiv)

Extracting commonsense knowledge from a large language model (LLM) offers a path to designing intelligent robots. Existing approaches that leverage LLMs for planning are unable to recover when an action fails and often resort to retrying failed actions, without resolving the error's underlying cause. We propose a novel approach (CAPE) that attempts to propose corrective actions to resolve precondition errors during planning. CAPE improves the quality of generated plans by leveraging few-shot reasoning from action preconditions. Our approach enables embodied agents to execute more tasks than baseline methods while ensuring semantic correctness and minimizing re-prompting. In VirtualHome, CAPE generates executable plans while improving a human-annotated plan correctness metric from 28.89% to 49.63% over SayCan. Our improvements transfer to a Boston Dynamics Spot robot initialized with a set of skills (specified in language) and associated preconditions, where CAPE improves the correctness metric of the executed task plans by 76.49% compared to SayCan. Our approach enables the robot to follow natural language commands and robustly recover from failures, which baseline approaches largely cannot resolve or address inefficiently.