Modeling Trust and Liquidity Under Payment System Stress: A Multi-Agent Approach

Masoud Amouzgar

cs.GTFeb 18, 2026

Modeling Trust and Liquidity Under Payment System Stress: A Multi-Agent Approach

Authors: Masoud Amouzgar

Organizations: Sharif University of Technology, Computer Science · Head of Payments, blu Bank

Abstract

Operational disruptions in retail payments can induce behavioral responses that outlast technical recovery and may amplify liquidity stress. We propose a multi-agent model linking card payment outages to trust dynamics, channel avoidance, and threshold-gated withdrawals. Customers and merchants interact through repeated payment attempts, while customers additionally influence one another on a Watts-Strogatz small-world network. Customers update bounded memory variables capturing accumulated negative experience (scar) and perceived systemic risk (rumor), with merchants contributing persistent broadcast signals that may lag operational recovery. We prove that, under mild conditions on memory persistence and threshold gating, aggregate withdrawal pressure can peak strictly after the outage nadir, including during the recovery phase. Simulations reproduce behavioral hysteresis and confirm delayed peaks of outflows. We further study payment substitution via instant transfer: substitution consistently reduces peak avoidance, yet its effect on cumulative outflows is non-monotonic under realistic merchant broadcast persistence. Robustness experiments across random seeds show stable qualitative behavior. The model highlights why "status green" is not equivalent to risk resolution and motivates incident response strategies that address perception, merchant messaging, and post-recovery communication in addition to technical remediation.

Figures & tables

Figure 1: Payment outage and behavioral response. The payment success probability (left axis) reaches its minimum during the outage, while customer avoidance and merchant broadcast severity (right axis) peak later and decay slowly during recovery.

Figure 2: Delayed emergence of withdrawal pressure. Aggregate withdrawal outflow peaks after the outage nadir, often during the recovery phase, confirming Theorem 1 .

Figure 3: Effect of merchant broadcast persistence. Sticky degraded broadcasts sustain elevated avoidance even after operational recovery, whereas immediate broadcast clearing leads to faster behavioral normalization.

Figure 4: Peak avoidance with and without payment substitution. Instant transfer availability consistently reduces peak avoidance across random seeds.

Figure 5: Liquidity impact of payment substitution. While substitution reduces peak panic, its effect on cumulative withdrawals is non-monotonic under realistic merchant broadcast persistence.

Figure 6: Instant transfer substitution usage during the incident. The plotted rate measures substitution usage among adverse card outcomes over time.

Figure 7: Robustness across random seeds. Distributions of (a) peak avoidance, (b) peak withdrawal pressure, and (c) cumulative run size show consistent qualitative behavior across stochastic realizations.

Appendix figures & tables1 asset

Supplementary material from the paper’s appendix.

Appendix

Symbol	Description	Typical Range
$N$	Number of customers	$10^{3}$ – $10^{4}$
$M$	Number of merchants	$10^{2}$ – $10^{3}$
$k$	Mean social degree	$6$ – $12$
$\beta$	Network rewiring probability	$0.05$ – $0.2$
$\lambda_{i}$	Baseline payment attempt rate	$[0.1,0.4]$
$\rho_{C}$	Scar memory persistence	$0.9$ – $0.99$

Appendix

Table 1: Key model parameters and ranges

Hysteresis

See all 8 papers

Trust Between AI Agents: Measuring Formation, Breakage, and Recovery, with Implications for Governing Multi-Agent Systems
Jun 12, 2026Yujiao ChenAI Agent Evaluation Multi-Agent Systems
Massachusetts Institute of Technology Cambridge, MA 02139
Beyond Task Success: Measuring Workflow Fidelity in LLM-Based Agentic Payment Systems
May 7, 2026Donghao Huang, Joon Kiat Chua, Zhaoxia WangFinancial Services Multi-Agent LLM Systems
School of Computing and Information Systems, Singapore Management University, 80 Stamford Rd, Singapore 178902, Singapore · Research and Development, Mastercard, 4250 Fairfax Dr, Arlington, VA 22203, USA
Trust-Gated Capability Control: Breaking the Trust-Vulnerability Paradox in Multi-Agent LLM Systems
Oct 4, 2026Mehedi Hasan Nipu, Chinmoy Mitra, Tarannum Ahmed Nowshin +1Trust in AI Multi-Agent System Security
Department of Electrical and Computer Engineering, North South University, Dhaka, Bangladesh · Department of Computer Science & Engineering Rajshahi University of Engineering & Technology Rajshahi, Bangladesh · Department of Computer Science and Engineering BRAC University,Dhaka, Bangladesh +1

Jun 12, 2026J/K move · Enter open · S save

Trust Between AI Agents: Measuring Formation, Breakage, and Recovery, with Implications for Governing Multi-Agent Systems

Yujiao Chen

Massachusetts Institute of Technology Cambridge, MA 02139

AI Agent Evaluation Multi-Agent Systems Trust in AI

Open paper AskPDF arXiv

As language-model agents increasingly work in teams, each agent must decide how much to trust its teammates. Yet we lack a standard way to measure trust between AI agents. We propose a behavioral measure based on costly verification. In a cooperative survival game, checking a teammate's work consumes resources, while trusting a wrong answer can be fatal. Relative to a memoryless version of the same model, reduced verification provides an observable measure of trust. Using this framework, we study trust formation, breakage, and recovery across six frontier model snapshots. When paired with a consistently reliable teammate, four snapshots (Claude Opus 4.6, Claude Sonnet 4.6, GPT-5.1, and Gemini 3.1 Pro) reduce verification by roughly 60-85%, whereas two smaller snapshots show little or no such adjustment. Failures reverse this discount, but models differ in how they respond. Some concentrate renewed scrutiny on the culprit, while others become more cautious toward the entire team. Recovery is slower than formation, and clustered failures sustain suspicion far longer than the same number of failures spread apart. These differences have practical consequences. Models that form trust verify less, decide more quickly, and achieve higher payoffs in our environment. By contrast, persistent over-verification is associated with indecision rather than safety. Our results show that trust dispositions can be measured before deployment and suggest that calibration, rather than maximal suspicion, should be the central concern in the governance of multi-agent AI systems.

Abstract

Hysteresis

Explore similar work

Trust Between AI Agents: Measuring Formation, Breakage, and Recovery, with Implications for Governing Multi-Agent Systems

Beyond Task Success: Measuring Workflow Fidelity in LLM-Based Agentic Payment Systems

Trust-Gated Capability Control: Breaking the Trust-Vulnerability Paradox in Multi-Agent LLM Systems