Guided Collaboration in Heterogeneous LLM-Based Multi-Agent Systems via Entropy-Based Understanding Assessment and Experience Retrieval

TL;DR

This paper introduces an entropy-based adaptive guidance framework for heterogeneous multi-agent systems with large language models, improving collaboration effectiveness by dynamically aligning guidance with agents' cognitive states and leveraging experience retrieval.

Contribution

It proposes a novel entropy-based guidance method combined with experience retrieval to enhance heterogeneous multi-agent collaboration, addressing cognitive mismatches and improving system robustness.

Findings

Consistently improves collaboration effectiveness on benchmark datasets.

Mitigates cognitive imbalance among heterogeneous agents.

Enhances stability and scalability of multi-agent systems.

Abstract

With recent breakthroughs in large language models (LLMs) for reasoning, planning, and complex task generation, artificial intelligence systems are transitioning from isolated single-agent architectures to multi-agent systems with collaborative intelligence. However, in heterogeneous multi-agent systems (HMAS), capability differences among agents give rise to consistent cognitive problems, where strong and weak models fail to contribute effectively. We define the collaboration as a strong-weak system. Through comprehensive experiments, we disclose a counterintuitive phenomenon in the strong-weak system: a strong-weak collaboration may under-perform weak-weak combinations, revealing that cognitive mismatching are key bottlenecks limiting heterogeneous cooperation. To overcome these challenges, we propose an Entropy-Based Adaptive Guidance Framework that dynamically aligns the guidance with the cognitive state of each agent. The framework quantifies the understanding of weak agents through multi-dimensional entropy metrics - covering expression, uncertainty, structure, coherence, and relevance - and adaptively adjusts the intensity of the guidance at light, moderate and intensive levels. Furthermore, a Retrieval-Augmented Generation (RAG) mechanism is incorporated to retain successful collaboration experiences, enabling both immediate adaptation and long-term learning. Extensive experiments on three benchmark datasets, GSM8K, MBPP, and CVRP demonstrate that our approach consistently enhances the effectiveness and stability of heterogeneous collaboration. The results highlight that adaptive guidance not only mitigates cognitive imbalance but also establishes a scalable pathway toward more robust, cooperative multi-agent intelligence.