Evolution of Thought: Diverse and High-Quality Reasoning via Multi-Objective Optimization

TL;DR

This paper introduces Evolution of Thought (EoT), a multi-objective optimization framework that enhances reasoning diversity and quality in multi-modal large language models by using genetic algorithms and a condensation-aggregation mechanism.

Contribution

The paper presents a novel multi-objective reasoning framework combining genetic algorithms and clustering to improve diversity and efficiency in reasoning paths for MLLMs.

Findings

EoT outperforms baseline methods in reasoning quality.

EoT improves reasoning diversity and efficiency.

Validated on vision-language and language reasoning tasks.

Abstract

As multi-modal large language models (MLLMs) are increasingly applied to complex reasoning tasks, the diversity and quality of reasoning paths become crucial factors affecting their performance. Although current methods aim to enhance reasoning quality through path expansion, they often neglect the diversity of reasoning paths and effective information sharing, leading to local optima and inefficiency. To address these challenges, we propose Evolution of Thought (EoT), a multi-objective framework designed to improve reasoning by fostering both high-quality and diverse reasoning paths. Specifically, we introduce the Non-dominated Sorting Genetic Algorithm II for multi-objective optimization, utilizing crossover and mutation operators to promote greater diversity in reasoning solutions. Additionally, we propose a Condensation-Aggregation mechanism to cluster and eliminate redundant paths, facilitate improved information sharing among parent nodes, and ultimately enhance both the efficiency and quality of the reasoning process. Validation experiments on various vision-language and language reasoning tasks demonstrate that EoT achieves superior reasoning performance and efficiency compared to other competitive baselines. Our study provides a novel perspective on the design of heuristic reasoning frameworks for MLLMs.