LLM+AL: Bridging Large Language Models and Action Languages for Complex Reasoning about Actions

TL;DR

This paper introduces LLM+AL, a hybrid approach combining large language models with action languages to improve complex reasoning about actions, outperforming standalone LLMs with minimal human correction.

Contribution

The paper presents a novel method that integrates LLMs with symbolic action languages, enhancing reasoning capabilities and automated knowledge generation for complex action reasoning tasks.

Findings

LLM+AL consistently produces correct answers with minimal human correction.

Standalone LLMs fail to improve even with human feedback.

LLM+AL enables automated generation of action languages.

Abstract

Large Language Models (LLMs) have made significant strides in various intelligent tasks but still struggle with complex action reasoning tasks that require systematic search. To address this limitation, we propose a method that bridges the natural language understanding capabilities of LLMs with the symbolic reasoning strengths of action languages. Our approach, termed "LLM+AL," leverages the LLM's strengths in semantic parsing and commonsense knowledge generation alongside the action language's proficiency in automated reasoning based on encoded knowledge. We compare LLM+AL against state-of-the-art LLMs, including ChatGPT-4, Claude 3 Opus, Gemini Ultra 1.0, and o1-preview, using benchmarks for complex reasoning about actions. Our findings indicate that, although all methods exhibit errors, LLM+AL, with relatively minimal human corrections, consistently leads to correct answers, whereas standalone LLMs fail to improve even with human feedback. LLM+AL also contributes to automated generation of action languages.