AURORA: A Natural Language-Driven Agentic Framework for Understanding, Reasoning, and Orchestrating Reliable Air-Ground Co-Simulation
推荐理由
Air–ground transportation research increasingly relies on co-simulation, yet constructing scenarios remains labor-intensive and difficult to validate. More imp…
核心判断
论文摘要（中文）
PDF 摘要：中文翻译尚未生成，请点击“显示原文依据”查看英文内容。
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, preexecution 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.
研究动机（中文总结）
全文第 1 页依据：中文翻译尚未生成，请点击“显示原文依据”查看英文内容。
AURORA: A Natural Language–Driven Agentic Framework for Understanding, Reasoning, and Orchestrating Reliable Air–Ground Co-Simulation Keshu Wu1, Hao Zhang 1, Rui Gan 2, Xiangbo Gao 3, Xiaopeng Li 2, Zhengzhong Tu 3, and Yang Zhou 1,† Abstract— Air–ground transportation research increasingly relies on co-simulation, yet constructing scenarios remains labor-intensive and difficult to validate.
创新与贡献（中文总结）
全文第 1 页依据：中文翻译尚未生成，请点击“显示原文依据”查看英文内容。
We presentAURORA 1 (A Natural Language–Driven Agentic Framework forUnderstanding,Reasoning, and OrchestratingReliableAir–Ground Co-Simulation), which treats language-driven scenario generation ascompilation with verification.
方法与证据
方法（中文总结）
全文第 1 页依据：中文翻译尚未生成，请点击“显示原文依据”查看英文内容。
We presentAURORA 1 (A Natural Language–Driven Agentic Framework forUnderstanding,Reasoning, and OrchestratingReliableAir–Ground Co-Simulation), which treats language-driven scenario generation ascompilation with verification.
实验结果（中文总结）
全文第 1 页依据：中文翻译尚未生成，请点击“显示原文依据”查看英文内容。
Experiments across multiple language models show that structured execution substantially improves reliability, while runtime verification exposes silent failures that completion-based evaluation overlooks.