LLM-State: Open World State Representation for Long-horizon Task Planning with Large Language Model

TL;DR

This paper introduces LLM-State, an open-world state representation method that leverages large language models to track object attributes and changes for improved long-horizon task planning in household environments.

Contribution

It proposes a continuous, expandable object attribute representation that enhances long-term state tracking and decision-making in LLM-based task planning.

Findings

Significant performance improvements over baseline methods.

Effective in both simulated and real-world scenarios.

Robust long-horizon state reasoning demonstrated.

Abstract

This work addresses the problem of long-horizon task planning with the Large Language Model (LLM) in an open-world household environment. Existing works fail to explicitly track key objects and attributes, leading to erroneous decisions in long-horizon tasks, or rely on highly engineered state features and feedback, which is not generalizable. We propose an open state representation that provides continuous expansion and updating of object attributes from the LLM's inherent capabilities for context understanding and historical action reasoning. Our proposed representation maintains a comprehensive record of an object's attributes and changes, enabling robust retrospective summary of the sequence of actions leading to the current state. This allows continuously updating world model to enhance context understanding for decision-making in task planning. We validate our model through experiments across simulated and real-world task planning scenarios, demonstrating significant improvements over baseline methods in a variety of tasks requiring long-horizon state tracking and reasoning. (Video\footnote{Video demonstration: \url{https://youtu.be/QkN-8pxV3Mo}.})