# AURORA: A Natural Language-Driven Agentic Framework for Understanding, Reasoning, and Orchestrating Reliable Air-Ground Co-Simulation

arXiv: https://arxiv.org/abs/2609.19527 · HTML: https://mlsanity.com/paper/2609.19527/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 14 of its 44 references that are in the map.
- First posted on arXiv 17 Sep 2026.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)
- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 14 of 14)

- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [OPV2V: An Open Benchmark Dataset and Fusion Pipeline for Perception with Vehicle-to-Vehicle Communication](https://mlsanity.com/paper/2109.07644/) (2021)
- [Guided Conditional Diffusion for Controllable Traffic Simulation](https://mlsanity.com/paper/2210.17366/) (2022)
- [Language Conditioned Traffic Generation](https://mlsanity.com/paper/2307.07947/) (2023)
- [Traffic Scene Generation from Natural Language Description for Autonomous Vehicles with Large Language Model](https://mlsanity.com/paper/2409.09575/) (2024)
- [V2X-LLM: Enhancing V2X Integration and Understanding in Connected Vehicle Corridors](https://mlsanity.com/paper/2503.02239/) (2025)
- [AirV2X: Unified Air-Ground Vehicle-to-Everything Collaboration](https://mlsanity.com/paper/2506.19283/) (2025)
- [Agentic UAVs: LLM-Driven Autonomy with Integrated Tool-Calling and Cognitive Reasoning](https://mlsanity.com/paper/2509.13352/) (2025)
- [Planning Safety Trajectories with Dual-Phase, Physics-Informed, and Transportation Knowledge-Driven Large Language Models](https://mlsanity.com/paper/2504.04562/) (2025)
- [Automated Vehicles Should be Connected with Natural Language](https://mlsanity.com/paper/2507.01059/) (2025)
- [CARLA-Air: Fly Drones Inside a CARLA World -- A Unified Infrastructure for Air-Ground Embodied Intelligence](https://mlsanity.com/paper/2603.28032/) (2026)
- [Integrating Large Language Models for UAV Control in Simulated Environments: A Modular Interaction Approach](https://mlsanity.com/paper/2410.17602/) (2024)
- [SkySim: A ROS2-based Simulation Environment for Natural Language Control of Drone Swarms using Large Language Models](https://mlsanity.com/paper/2602.01226/) (2026)
- [AirSimAG: A High-Fidelity Simulation Platform for Air-Ground Collaborative Robotics](https://mlsanity.com/paper/2603.23079/) (2026)

## Abstract (arXiv)

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.