Assured autonomy: How operations research powers and orchestrates generative AI systems

TL;DR

This paper proposes a framework integrating operations research with generative AI to enhance safety, robustness, and verifiability in autonomous decision-making systems within operational workflows.

Contribution

It introduces a novel conceptual framework combining flow-based generative models and adversarial robustness for assured autonomy in safety-critical domains.

Findings

Flow-based models enable constraint-aware generation and auditability.

Adversarial robustness ensures safety against worst-case perturbations.

Framework shifts OR's role to system architect for control and safety.

Abstract

Generative artificial intelligence (GenAI) is shifting from conversational assistants toward agentic systems -- autonomous decision-making systems that sense, decide, and act within operational workflows. This shift creates an autonomy paradox: as GenAI systems are granted greater operational autonomy, they should, by design, embody more formal structure, more explicit constraints, and stronger tail-risk discipline. We argue that stochastic generative models can be fragile in operational domains unless paired with mechanisms that provide verifiable feasibility, robustness to distribution shift, and stress testing under high-consequence scenarios. To address this challenge, we develop a conceptual framework for assured autonomy grounded in operations research (OR), built on two complementary approaches. First, flow-based generative models frame generation as deterministic transport characterized by an ordinary differential equation, enabling auditability, constraint-aware generation, and connections to optimal transport, robust optimization, and sequential decision control. Second, operational safety is formulated through an adversarial robustness lens: decision rules are evaluated against worst-case perturbations within uncertainty or ambiguity sets, making unmodeled risks part of the design. This framework clarifies how increasing autonomy shifts OR's role from solver to guardrail to system architect, with responsibility for control logic, incentive protocols, monitoring regimes, and safety boundaries. These elements define a research agenda for assured autonomy in safety-critical, reliability-sensitive operational domains.