让智能体适度分歧，反而能提升系统应对复杂环境的适应力。
The Hidden Strength of Disagreement: Unraveling the Consensus-Diversity Tradeoff in Adaptive Multi-Agent Systems
- 用隐式共识机制，让智能体自主决策
- 部分偏离群体规范可提升探索与抗冲击能力
- 适合需要长期适应性的动态系统场景
共识形成在多智能体系统中至关重要，需在集体一致性和个体多样性间取得平衡。传统基于大模型的多智能体系统依赖显式协调（如提示或投票），易导致过早同质化。本文提出，通过上下文学习实现隐式共识——智能体交换信息但独立决策，能在需要长期适应性的动态环境中表现更优。保留部分多样性有助于探索新策略并应对外部冲击。我们形式化了共识-多样性权衡，证明隐式方法在特定条件下优于显式方法。三个实验场景（动态灾害响应、信息传播与操纵、动态公共品提供）均表明，适度偏离群体规范能显著提升系统的探索能力、鲁棒性与整体性能。研究揭示了基于上下文学习的涌现协同机制，强调保留多样性对韧性决策的价值。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。