Verification of Robust Multi-Agent Systems

2026-02-13

AI Summary

This work addresses the verification of robust strategies for stochastic multi-agent systems subject to uncertain transition probabilities, partial observability, and adversarial agents, with the goal of satisfying temporal specifications. The authors propose a probabilistic alternating-time temporal logic (ATL) framework that integrates bounded-memory strategies with observational information, offering the first unified formalization of robustness, partial observability, and bounded memory within a single model-checking setting. They rigorously define the corresponding robust model-checking problem and analyze its computational complexity under various perturbation models, thereby establishing precise complexity bounds. This theoretical foundation advances the trustworthy verification of multi-agent systems operating in uncertain and adversarial environments.

Technology Category

• Multiagent Systems: Adversarial Agents
• Machine Learning: Adversarial Learning & Robustness
• Reasoning under Uncertainty: Stochastic Optimization

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

Abstract

Stochastic multi-agent systems are a central modeling framework for autonomous controllers, communication protocols, and cyber-physical infrastructures. In many such systems, however, transition probabilities are only estimated from data and may therefore be partially unknown or subject to perturbations. In this paper, we study the verification of robust strategies in stochastic multi-agent systems with imperfect information, in which coalitions must satisfy a temporal specification while dealing with uncertain system transitions, partial observation, and adversarial agents. By focusing on bounded-memory strategies, we introduce a robust variant of the model-checking problem for a probabilistic, observation-based extension of Alternating-time Temporal Logic. We characterize the complexity of this problem under different notions of perturbation, thereby clarifying the computational cost of robustness in stochastic multi-agent verification and supporting the use of bounded-memory strategies in uncertain environments.

Problem

• stochastic multi-agent systems
• robust verification
• imperfect information
• temporal specification
• bounded-memory strategies

Innovation

• robust model checking
• stochastic multi-agent systems
• bounded-memory strategies
• imperfect information
• Alternating-time Temporal Logic