# CLMASP: Coupling Large Language Models with Answer Set Programming for Robotic Task Planning

arXiv: https://arxiv.org/abs/2406.03367 · HTML: https://mlsanity.com/paper/2406.03367/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 17 of its 49 references that are in the map.
- First posted on arXiv 5 Jun 2024.

## Placed in

- LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/)

## Builds on (most cited first, 17 of 17)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Code as Policies: Language Model Programs for Embodied Control](https://mlsanity.com/paper/2209.07753/) (2022)
- [Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents](https://mlsanity.com/paper/2201.07207/) (2022)
- [CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing](https://mlsanity.com/paper/2305.11738/) (2023)
- [LLM+P: Empowering Large Language Models with Optimal Planning Proficiency](https://mlsanity.com/paper/2304.11477/) (2023)
- [LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Models](https://mlsanity.com/paper/2212.04088/) (2022)
- [Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoning](https://mlsanity.com/paper/2305.12295/) (2023)
- [EmbodiedGPT: Vision-Language Pre-Training via Embodied Chain of Thought](https://mlsanity.com/paper/2305.15021/) (2023)
- [Language Models Meet World Models: Embodied Experiences Enhance Language Models](https://mlsanity.com/paper/2305.10626/) (2023)
- [Multi-shot ASP solving with clingo](https://mlsanity.com/paper/1705.09811/) (2017)
- [AutoTAMP: Autoregressive Task and Motion Planning with LLMs as Translators and Checkers](https://mlsanity.com/paper/2306.06531/) (2023)
- [Embodied Task Planning with Large Language Models](https://mlsanity.com/paper/2307.01848/) (2023)
- [Coupling Large Language Models with Logic Programming for Robust and General Reasoning from Text](https://mlsanity.com/paper/2307.07696/) (2023)
- [Grounding LLMs For Robot Task Planning Using Closed-loop State Feedback](https://mlsanity.com/paper/2402.08546/) (2024)
- [Answer Set Planning: A Survey](https://mlsanity.com/paper/2202.05793/) (2022)
- [Omission-based Abstraction for Answer Set Programs](https://mlsanity.com/paper/2004.01410/) (2020)
- [A Unified View on Forgetting and Strong Equivalence Notions in Answer Set Programming](https://mlsanity.com/paper/2312.07993/) (2023)

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

- [PDE-Controller: LLMs for Autoformalization and Reasoning of PDEs](https://mlsanity.com/paper/2502.00963/) (2025)
- [NeSyPr: Neurosymbolic Proceduralization For Efficient Embodied Reasoning](https://mlsanity.com/paper/2510.19429/) (2025)
- [LLMs as ASP Programmers: Self-Correction Enables Task-Agnostic Nonmonotonic Reasoning](https://mlsanity.com/paper/2604.27960/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) possess extensive foundational knowledge and moderate reasoning abilities, making them suitable for general task planning in open-world scenarios. However, it is challenging to ground a LLM-generated plan to be executable for the specified robot with certain restrictions. This paper introduces CLMASP, an approach that couples LLMs with Answer Set Programming (ASP) to overcome the limitations, where ASP is a non-monotonic logic programming formalism renowned for its capacity to represent and reason about a robot's action knowledge. CLMASP initiates with a LLM generating a basic skeleton plan, which is subsequently tailored to the specific scenario using a vector database. This plan is then refined by an ASP program with a robot's action knowledge, which integrates implementation details into the skeleton, grounding the LLM's abstract outputs in practical robot contexts. Our experiments conducted on the VirtualHome platform demonstrate CLMASP's efficacy. Compared to the baseline executable rate of under 2% with LLM approaches, CLMASP significantly improves this to over 90%.