# Feedback-Coupled Memory Systems in Continuous Time

arXiv: https://arxiv.org/abs/2607.09714 · HTML: https://mlsanity.com/paper/2607.09714/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 2 of its 18 references that are in the map.
- First posted on arXiv 24 Jun 2026.

## Builds on (most cited first, 2 of 2)

- [Mechanism-Based Intelligence (MBI): Differentiable Incentives for Rational Coordination and Guaranteed Alignment in Multi-Agent Systems](https://mlsanity.com/paper/2512.20688/) (2025)
- [Feedback-Coupled Memory Systems: A Dynamical Model for Adaptive Coordination](https://mlsanity.com/paper/2603.11560/) (2026)

## Abstract (arXiv)

The Feedback-Coupled Memory Systems (FCMS) architecture formalizes closed-loop coordination through four abstract operators, two of which - the agent update operator fi and the environmental update operator Psi - are left axiomatically undefined in the original framework. To address this, fi is defined by Mechanism-Based Intelligence (MBI), where agents update locally through a decentralized price mechanism and economic principles, and Psi is defined by the Coupled Memory Graph Process (CMGP), a non-Markovian framework where the environment is treated as a physical substrate that records and responds to trajectory history coherently without external forcing. The resulting continuous-time FCMS instantiation achieves Lyapunov global dissipativity governed by the computable threshold 4β2 < 2ημγ2. This generalizes both the discrete FCMS stability condition 4ηβ2 < γ and CMGP's physical bifurcation threshold αc = 1/K, confirming that memory dissipation must outpace feedback gain as a universal organizing principle. Numerical simulation with N=2 agents and mean-field validation at N=106 confirm the stability threshold and the self-reinforcing coordination cascade that emerges when it is violated.