Assured Autonomy: How Operations Research Powers and Orchestrates Generative AI Systems

TL;DR

The paper addresses the gap between generative AI's promise and the guarantees required for safety-critical operations. It proposes an assured autonomy framework that combines flow-based, deterministic transport with distributionally robust, minimax safety to enforce feasibility, stability, and tail-risk discipline within operational loops. By shifting OR's role from solver to guardrail to system architect, it outlines a holistic architecture—inference/substrate, constraint-preserving generation, and governance layers—and demonstrates how this approach applies across supply chains, mobility, healthcare, and power grids, while outlining a concrete research agenda. The work emphasizes auditable design, explicit escalation/fallback mechanisms, and performance evaluation under worst-case regimes, offering a practical path to scalable, responsible autonomous GenAI systems.

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 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.

Figures (3)

• Figure 1: The OR-AI Integration Architecture for Assured Autonomy
• Figure 2: Structural contrast between flow-based and diffusion-based generative models under constraints. Red curves denote a constrained feasible region. Left: flow-based models transport samples deterministically from a reference distribution $Q$ to a target distribution $P$, allowing constraints to be incorporated directly into the transformation. Right: diffusion-based models generate samples through iterative stochastic refinement, with randomness injected at each step and constraints typically enforced through guidance or correction mechanisms.
• Figure 3: Minimax Game-Theoretic Framework for AI Safety