Autonomous multi-agent systems are fundamentally fragile: they struggle to solve the Hayekian Information problem (eliciting dispersed private knowledge) and the Hurwiczian Incentive problem (aligning local actions with global objectives), making coordination computationally intractable. I introduce Mechanism-Based Intelligence (MBI), a paradigm that reconceptualizes intelligence as emergent from the coordination of multiple "brains", rather than a single one. At its core, the Differentiable Price Mechanism (DPM) computes the exact loss gradient $$ \mathbf{G}_i = - \frac{\partial \mathcal{L}}{\partial \mathbf{x}_i} $$ as a dynamic, VCG-equivalent incentive signal, guaranteeing Dominant Strategy Incentive Compatibility (DSIC) and convergence to the global optimum. A Bayesian extension ensures incentive compatibility under asymmetric information (BIC). The framework scales linearly ($\mathcal{O}(N)$) with the number of agents, bypassing the combinatorial complexity of Dec-POMDPs and is empirically 50x faster than Model-Free Reinforcement Learning. By structurally aligning agent self-interest with collective objectives, it provides a provably efficient, auditable and generalizable approach to coordinated, trustworthy and scalable multi-agent intelligence grounded in economic principles.

翻译：自主多智能体系统本质上是脆弱的：它们难以解决哈耶克信息问题（激发分散的私有知识）和赫维茨激励问题（使局部行动与全局目标对齐），导致协调在计算上难以处理。本文引入基于机制的智能（MBI），这一范式将智能重新概念化为源自多个“大脑”而非单一大脑的协调涌现。其核心是可微分价格机制（DPM），该机制将精确的损失梯度 $$ \mathbf{G}_i = - \frac{\partial \mathcal{L}}{\partial \mathbf{x}_i} $$ 计算为一种动态的、与VCG机制等效的激励信号，从而保证占优策略激励相容性（DSIC）并收敛至全局最优解。一个贝叶斯扩展确保了在非对称信息下的激励相容性（BIC）。该框架的规模随智能体数量呈线性增长（$\mathcal{O}(N)$），绕过了Dec-POMDP的组合复杂性，并且经验证明比无模型强化学习快50倍。通过从结构上将智能体的自利与集体目标对齐，它提供了一种基于经济学原理的、可证明高效、可审计且可泛化的方法，用于实现协调、可信且可扩展的多智能体智能。