MAAICLCYFeb 23, 2025

The Hidden Strength of Disagreement: Unraveling the Consensus-Diversity Tradeoff in Adaptive Multi-Agent Systems

arXiv:2502.16565v28 citationsh-index: 6EMNLP
Originality Highly original
AI Analysis

This addresses the challenge of premature homogenization in multi-agent systems for applications like disaster response and public goods provision, offering a novel approach to enhance adaptability and resilience.

The paper tackles the problem of balancing consensus and diversity in multi-agent systems, showing that implicit consensus methods, where agents independently form decisions via in-context learning, outperform explicit coordination in dynamic environments by boosting exploration, robustness, and performance across three scenarios.

Consensus formation is pivotal in multi-agent systems (MAS), balancing collective coherence with individual diversity. Conventional LLM-based MAS primarily rely on explicit coordination, e.g., prompts or voting, risking premature homogenization. We argue that implicit consensus, where agents exchange information yet independently form decisions via in-context learning, can be more effective in dynamic environments that require long-horizon adaptability. By retaining partial diversity, systems can better explore novel strategies and cope with external shocks. We formalize a consensus-diversity tradeoff, showing conditions where implicit methods outperform explicit ones. Experiments on three scenarios -- Dynamic Disaster Response, Information Spread and Manipulation, and Dynamic Public-Goods Provision -- confirm partial deviation from group norms boosts exploration, robustness, and performance. We highlight emergent coordination via in-context learning, underscoring the value of preserving diversity for resilient decision-making.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes