Longkun Li

Longkun Li, Evangelos Pournaras

Autonomous vehicles generate large volumes of data for applications such as fleet monitoring, model retraining, and high-definition map updates. Existing studies often rely on generic traffic traces, which do not capture the characteristics of autonomous driving workloads. This paper proposes a system-level workload modeling framework for vehicle-to-cloud data. We classify offloaded data into three types: telemetry, event-driven fleet learning, and high-definition map updates, while we model their generation using a parameterized formulation based on empirical data. Using a real-world mobility trace from Munich, we analyze the resulting workloads over time and space. The results show that workload scales with vehicle penetration, exhibits temporal structure and spatial imbalance across access points, and is distinguished from baseline traffic models.

Longkun Li, Yuanben Zou, Jinghan Wu et al.

Graph-RAG improves LLM reasoning using structured knowledge, yet conventional designs rely on a centralized knowledge graph. In distributed and access-restricted settings (e.g., hospitals or multinational organizations), retrieval must select relevant domains and appropriate traversal depth without global graph visibility or exhaustive querying. To address this challenge, we introduce \textbf{SCOUT-RAG} (\textit{\underline{S}calable and \underline{CO}st-efficient \underline{U}nifying \underline{T}raversal}), a distributed agentic Graph-RAG framework that performs progressive cross-domain retrieval guided by incremental utility goals. SCOUT-RAG employs four cooperative agents that: (i) estimate domain relevance, (ii) decide when to expand retrieval to additional domains, (iii) adapt traversal depth to avoid unnecessary graph exploration, and (iv) synthesize the high-quality answers. The framework is designed to minimize retrieval regret, defined as missing useful domain information, while controlling latency and API cost. Across multi-domain knowledge settings, SCOUT-RAG achieves performance comparable to centralized baselines, including DRIFT and exhaustive domain traversal, while substantially reducing cross-domain calls, total tokens processed, and latency.