用可微激励机制让多智能体自动协调，实现全局最优且可信。
Mechanism-Based Intelligence (MBI): Differentiable Incentives for Rational Coordination and Guaranteed Alignment in Multi-Agent Systems
- 设计可微价格机制，将梯度作为动态激励信号
- 保证每个智能体说真话，且整体收敛到全局最优
- 适合需要高效可靠协作的复杂系统，如自动驾驶、供应链
自主多智能体系统本质脆弱：难以解决哈耶克的信息问题（获取分散的私有知识）和赫维茨的激励问题（使局部行为与全局目标对齐），导致协调计算上不可行。本文提出机制型智能（MBI），将智能重新定义为多个‘大脑’协同产生的结果，而非单一主体。核心是可微价格机制（DPM），其计算出精确损失梯度 $\mathbf{G}_i = - \frac{\partial \mathcal{L}}{\partial \mathbf{x}_i}$ 作为动态、VCG等价的激励信号，确保主导策略激励相容（DSIC）并收敛至全局最优。贝叶斯扩展在信息不对称下仍保持激励相容（BIC）。该框架随智能体数量线性扩展（$\mathcal{O}(N)$），绕过决策马尔可夫过程的组合复杂性，实证比无模型强化学习快50倍。通过结构化地将个体自利与集体目标对齐，提供一种可证明高效、可审计、可泛化的多智能体协同智能方法，基于经济原则。
原文摘要 · Abstract (English)
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.
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。