Inner Monologue: Embodied Reasoning through Planning with Language Models

TL;DR

This paper explores how Large Language Models can use natural language feedback to improve planning and reasoning in embodied robotic tasks without additional training, by forming an inner monologue for better decision-making.

Contribution

It introduces the concept of leveraging environment feedback for LLMs to enhance embodied reasoning through an inner monologue, improving task performance in robotic control scenarios.

Findings

Language feedback improves instruction completion in robotic tasks

Inner monologue enables better reasoning in embodied environments

Effective across simulated and real-world tasks

Abstract

Recent works have shown how the reasoning capabilities of Large Language Models (LLMs) can be applied to domains beyond natural language processing, such as planning and interaction for robots. These embodied problems require an agent to understand many semantic aspects of the world: the repertoire of skills available, how these skills influence the world, and how changes to the world map back to the language. LLMs planning in embodied environments need to consider not just what skills to do, but also how and when to do them - answers that change over time in response to the agent's own choices. In this work, we investigate to what extent LLMs used in such embodied contexts can reason over sources of feedback provided through natural language, without any additional training. We propose that by leveraging environment feedback, LLMs are able to form an inner monologue that allows them to more richly process and plan in robotic control scenarios. We investigate a variety of sources of feedback, such as success detection, scene description, and human interaction. We find that closed-loop language feedback significantly improves high-level instruction completion on three domains, including simulated and real table top rearrangement tasks and long-horizon mobile manipulation tasks in a kitchen environment in the real world.