Statler：用於具體推理的狀態維護語言模型
Statler: State-Maintaining Language Models for Embodied Reasoning
June 30, 2023
作者: Takuma Yoneda, Jiading Fang, Peng Li, Huanyu Zhang, Tianchong Jiang, Shengjie Lin, Ben Picker, David Yunis, Hongyuan Mei, Matthew R. Walter
cs.AI
摘要
大型語言模型（LLMs）提供了一個有前途的工具，使機器人能夠執行複雜的機器人推理任務。然而，當代LLMs的有限上下文窗口使得對長時間範圍進行推理變得困難。例如，家用機器人可能執行的具體任務通常要求規劃者考慮很久以前獲得的信息（例如，機器人先前在環境中遇到的許多物體的特性）。試圖使用LLM的隱式內部表示來捕捉世界狀態受到機器人行動歷史中缺乏任務和環境相關信息的限制，而依賴於透過提示向LLM傳遞信息的方法受到其有限上下文窗口的限制。在本文中，我們提出了Statler，這是一個賦予LLMs對世界狀態進行明確表示的“記憶”形式的框架，並且該記憶會隨時間保持。Statler的核心是使用兩個通用LLMs實例 - 世界模型閱讀器和世界模型寫入器 - 這兩者與並且維護世界狀態進行接口。通過提供對這種世界狀態“記憶”的訪問，Statler提高了現有LLMs在不受上下文長度限制的情況下對更長時間範圍進行推理的能力。我們在三個模擬桌面操作領域和一個真實機器人領域上評估了我們方法的有效性，並展示了它在基於LLMs的機器人推理中改進了最新技術。項目網站：https://statler-lm.github.io/
English
Large language models (LLMs) provide a promising tool that enable robots to
perform complex robot reasoning tasks. However, the limited context window of
contemporary LLMs makes reasoning over long time horizons difficult. Embodied
tasks such as those that one might expect a household robot to perform
typically require that the planner consider information acquired a long time
ago (e.g., properties of the many objects that the robot previously encountered
in the environment). Attempts to capture the world state using an LLM's
implicit internal representation is complicated by the paucity of task- and
environment-relevant information available in a robot's action history, while
methods that rely on the ability to convey information via the prompt to the
LLM are subject to its limited context window. In this paper, we propose
Statler, a framework that endows LLMs with an explicit representation of the
world state as a form of ``memory'' that is maintained over time. Integral to
Statler is its use of two instances of general LLMs -- a world-model reader and
a world-model writer -- that interface with and maintain the world state. By
providing access to this world state ``memory'', Statler improves the ability
of existing LLMs to reason over longer time horizons without the constraint of
context length. We evaluate the effectiveness of our approach on three
simulated table-top manipulation domains and a real robot domain, and show that
it improves the state-of-the-art in LLM-based robot reasoning. Project website:
https://statler-lm.github.io/