# Mechanism-Based Intelligence (MBI): Differentiable Incentives for Rational Coordination and Guaranteed Alignment in Multi-Agent Systems

arXiv: https://arxiv.org/abs/2512.20688 · HTML: https://mlsanity.com/paper/2512.20688/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 39 references that are in the map.
- First posted on arXiv 22 Dec 2025.

## Builds on (most cited first, 9 of 9)

- [The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity](https://mlsanity.com/paper/2506.06941/) (2025)
- [Deep Visual Foresight for Planning Robot Motion](https://mlsanity.com/paper/1610.00696/) (2016)
- [The Complexity of Decentralized Control of Markov Decision Processes](https://mlsanity.com/paper/1301.3836/) (2013)
- [Deep Learning: A Critical Appraisal](https://mlsanity.com/paper/1801.00631/) (2018)
- [Open Problems in Cooperative AI](https://mlsanity.com/paper/2012.08630/) (2020)
- [Optimal Auctions through Deep Learning: Advances in Differentiable Economics](https://mlsanity.com/paper/1706.03459/) (2017)
- [Emergent Abilities in Large Language Models: A Survey](https://mlsanity.com/paper/2503.05788/) (2025)
- [Understanding the World Through Action](https://mlsanity.com/paper/2110.12543/) (2021)
- [Beyond Exponential Decay: Rethinking Error Accumulation in Large Language Models](https://mlsanity.com/paper/2505.24187/) (2025)

## Built on by (most cited first, 2 of 2)

- [Feedback-Coupled Memory Systems: A Dynamical Model for Adaptive Coordination](https://mlsanity.com/paper/2603.11560/) (2026)
- [Feedback-Coupled Memory Systems in Continuous Time](https://mlsanity.com/paper/2607.09714/) (2026)

## Abstract (arXiv)

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  Gi = - fracpartial Lpartial xi  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 (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.