AURORA: A Natural Language-Driven Agentic Framework for Understanding, Reasoning, and Orchestrating Reliable Air-Ground Co-Simulation
Keshu Wu and colleagues at Texas A&M and collaborators treat air-ground co-simulation scenario generation as compilation with verification, so a scenario that runs is also checked against the relationships the user asked for.
Ask this paper
The failure it targets is a silent one. A generated scenario can execute without error while failing to realize the requested spatial, temporal, communication or behavioral relationships, which makes runtime success a poor acceptance signal.
Natural language in, verified scenario out. AURORA parses the request into an intermediate representation, orchestrates simulator construction from it, and checks the built scenario back against the parsed constraints.
Agentic orchestration across two simulators. The framework coordinates air and ground simulation components that are normally wired together by hand for each study.
Verification is the contribution. The compile-then-check structure is what separates this from prompt-to-script scenario generators, which report execution success only.
Abstract
Air-ground transportation research increasingly relies on co-simulation, yet constructing scenarios remains labor-intensive and difficult to validate. More importantly, a generated scenario may execute successfully while failing to realize the spatial, temporal, communication, or behavioral relationships requested by the user. This paper presents AURORA, a natural-language-driven agentic framework that treats air-ground scenario generation as a process of compilation with verification. Central to AURORA is the Air-Ground Scenario Graph (AGSG), a typed intermediate representation that explicitly connects agents, aerial missions, events, communication links, success conditions, and their cross-domain dependencies. This shared representation enables simulator-grounded parsing, joint road-airspace grounding, temporal planning, pre-execution feasibility checking, trace-based runtime verification, failure localization, and bounded repair within a unified workflow. We further introduce AURORA-Bench to evaluate not only whether generated scenarios execute, but whether they faithfully realize the requested interactions. Experiments across multiple language models show that structured execution substantially improves reliability, while runtime verification exposes silent failures that completion-based evaluation overlooks. Localized repair further resolves many violations without regenerating the entire scenario. The results show that reliable scenario generation requires verifying realized behavior, not merely executable code, and demonstrate the value of explicit intermediate representations for verifiable and repairable language-driven co-simulation.