DANLI: Deliberative Agent for Following Natural Language Instructions

TL;DR

DANLI introduces a neuro-symbolic deliberative agent that enhances task performance and transparency in following natural language instructions for embodied AI, outperforming reactive models on complex benchmarks.

Contribution

The paper presents a novel neuro-symbolic deliberative framework that combines reasoning and planning with neural and symbolic representations for embodied AI.

Findings

Achieves over 70% improvement on TEACh benchmark

Provides transparency and explainability in agent behaviors

Demonstrates effectiveness in complex, long-horizon tasks

Abstract

Recent years have seen an increasing amount of work on embodied AI agents that can perform tasks by following human language instructions. However, most of these agents are reactive, meaning that they simply learn and imitate behaviors encountered in the training data. These reactive agents are insufficient for long-horizon complex tasks. To address this limitation, we propose a neuro-symbolic deliberative agent that, while following language instructions, proactively applies reasoning and planning based on its neural and symbolic representations acquired from past experience (e.g., natural language and egocentric vision). We show that our deliberative agent achieves greater than 70% improvement over reactive baselines on the challenging TEACh benchmark. Moreover, the underlying reasoning and planning processes, together with our modular framework, offer impressive transparency and explainability to the behaviors of the agent. This enables an in-depth understanding of the agent's capabilities, which shed light on challenges and opportunities for future embodied agents for instruction following. The code is available at https://github.com/sled-group/DANLI.