Large Language Models Are Neurosymbolic Reasoners

TL;DR

This paper explores using Large Language Models as symbolic reasoners in text-based games, demonstrating significant improvements in symbolic reasoning tasks with an average performance of 88%.

Contribution

It introduces a novel LLM-based agent framework that effectively handles symbolic reasoning in text-based environments, enhancing LLM capabilities for complex symbolic tasks.

Findings

Achieved 88% average performance across symbolic tasks

Enhanced LLM reasoning capabilities in text-based games

Demonstrated effectiveness of symbolic modules with LLMs

Abstract

A wide range of real-world applications is characterized by their symbolic nature, necessitating a strong capability for symbolic reasoning. This paper investigates the potential application of Large Language Models (LLMs) as symbolic reasoners. We focus on text-based games, significant benchmarks for agents with natural language capabilities, particularly in symbolic tasks like math, map reading, sorting, and applying common sense in text-based worlds. To facilitate these agents, we propose an LLM agent designed to tackle symbolic challenges and achieve in-game objectives. We begin by initializing the LLM agent and informing it of its role. The agent then receives observations and a set of valid actions from the text-based games, along with a specific symbolic module. With these inputs, the LLM agent chooses an action and interacts with the game environments. Our experimental results demonstrate that our method significantly enhances the capability of LLMs as automated agents for symbolic reasoning, and our LLM agent is effective in text-based games involving symbolic tasks, achieving an average performance of 88% across all tasks.