Dissecting Tool-Integrated Reasoning: An Empirical Study and Analysis

TL;DR

This paper evaluates Tool-Integrated Reasoning (TIR) in large language models using a new benchmark and metrics, showing TIR improves reasoning accuracy and efficiency across diverse domains.

Contribution

It introduces ReasonZoo, a comprehensive reasoning benchmark, and two novel metrics, PAC and AUC-PCC, to assess TIR's effectiveness and efficiency in LLMs.

Findings

TIR-enabled models outperform non-TIR models in various reasoning tasks.

TIR improves reasoning efficiency, reducing overthinking.

TIR demonstrates domain-general benefits in complex reasoning.

Abstract

Large Language Models (LLMs) have made significant strides in reasoning tasks through methods like chain-of-thought (CoT) reasoning. However, they often fall short in tasks requiring precise computations. Tool-Integrated Reasoning (TIR) has emerged as a solution by incorporating external tools into the reasoning process. Nevertheless, the generalization of TIR in improving the reasoning ability of LLM is still unclear. Additionally, whether TIR has improved the model's reasoning behavior and helped the model think remains to be studied. We introduce ReasonZoo, a comprehensive benchmark encompassing nine diverse reasoning categories, to evaluate the effectiveness of TIR across various domains. Additionally, we propose two novel metrics, Performance-Aware Cost (PAC) and Area Under the Performance-Cost Curve (AUC-PCC), to assess reasoning efficiency. Our empirical evaluation demonstrates that TIR-enabled models consistently outperform their non-TIR counterparts in both mathematical and non-mathematical tasks. Furthermore, TIR enhances reasoning efficiency, as evidenced by improved PAC and AUC-PCC, indicating reduced overthinking and more streamlined reasoning. These findings underscore the domain-general benefits of TIR and its potential to advance LLM capabilities in complex reasoning tasks.