{"ID":2826432,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.20688","arxiv_id":"2512.20688","title":"Mechanism-Based Intelligence (MBI): Differentiable Incentives for Rational Coordination and Guaranteed Alignment in Multi-Agent Systems","abstract":"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.","short_abstract":"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 Int...","url_abs":"https://arxiv.org/abs/2512.20688","url_pdf":"https://arxiv.org/pdf/2512.20688v1","authors":"[\"Stefano Grassi\"]","published":"2025-12-22T22:22:13Z","proceeding":"cs.GT","tasks":"[\"cs.GT\",\"cs.AI\",\"cs.LG\",\"cs.MA\"]","methods":"[\"Reinforcement Learning\"]","has_code":false}