Swarm Intelligence Enhanced Reasoning: A Density-Driven Framework for LLM-Based Multi-Agent Optimization

2025-05-21

AI Summary

Current large language models (LLMs) struggle to guarantee solution optimality and robustness in complex reasoning tasks. Method: We formulate LLM-based reasoning as a multi-objective optimization problem and propose the first density-driven swarm intelligence–enhanced reasoning framework. Our approach integrates kernel density estimation with non-dominated sorting to jointly guide multiple agents toward high-quality and diverse solution paths. It further incorporates step-wise quality assessment and a dynamic threshold–based termination mechanism to enable adaptive reasoning optimization. Contribution/Results: The method significantly outperforms Chain-of-Thought and Multi-Agent Debate baselines on mathematical reasoning and code generation benchmarks, achieving superior accuracy while maintaining strong generalization and robustness across diverse problem instances.

Technology Category

• Search and Optimization: Metareasoning and Metaheuristics
• Machine Learning: Large Multimodal Models (LMMs)
• Knowledge Representation and Reasoning: Computational Complexity of Reasoning

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Large language models for search
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

Recently, many approaches, such as Chain-of-Thought (CoT) prompting and Multi-Agent Debate (MAD), have been proposed to further enrich Large Language Models' (LLMs) complex problem-solving capacities in reasoning scenarios. However, these methods may fail to solve complex problems due to the lack of ability to find optimal solutions. Swarm Intelligence has been serving as a powerful tool for finding optima in the field of traditional optimization problems. To this end, we propose integrating swarm intelligence into the reasoning process by introducing a novel Agent-based Swarm Intelligence (ASI) paradigm. In this paradigm, we formulate LLM reasoning as an optimization problem and use a swarm intelligence scheme to guide a group of LLM-based agents in collaboratively searching for optimal solutions. To avoid swarm intelligence getting trapped in local optima, we further develop a Swarm Intelligence Enhancing Reasoning (SIER) framework, which develops a density-driven strategy to enhance the reasoning ability. To be specific, we propose to perform kernel density estimation and non-dominated sorting to optimize both solution quality and diversity simultaneously. In this case, SIER efficiently enhances solution space exploration through expanding the diversity of the reasoning path. Besides, a step-level quality evaluation is used to help agents improve solution quality by correcting low-quality intermediate steps. Then, we use quality thresholds to dynamically control the termination of exploration and the selection of candidate steps, enabling a more flexible and efficient reasoning process. Extensive experiments are ...

Problem

• Enhancing LLM reasoning with swarm intelligence optimization
• Preventing local optima traps via density-driven strategies
• Improving solution quality and diversity simultaneously

Innovation

• Integrates swarm intelligence into LLM reasoning
• Uses density-driven strategy to avoid local optima
• Employs step-level quality evaluation for correction