REARL, a closed-loop simulation enhancement framework that integrates real traffic data with large language model (LLM) and modulates the simulated vehicle with reference to that real action, is proposed.
Abstract
Accurate simulation is crucial for autonomous driving development, yet capturing real-world traffic complexity remains challenging. Existing simulators that rely on predefined rules or static data playback struggle with dynamic traffic. CRITICAL uses real traffic data and a large language model (LLM) to adjust the initial simulation configuration, but the simulated distribution still diverges from real traffic as the rollout evolves. We propose REARL, a closed-loop simulation enhancement framework that integrates real traffic data with LLMs. Real traffic data are clustered, and each cluster center is used as a representative scenario that provides typical real-world traffic patterns for the LLM. A timed sliding-window detector then monitors discrepancies in vehicle speed distribution and mean spacing between pairs of vehicles. If a metric exceeds a threshold, the LLM adjusts vehicle decision-making; otherwise the existing controller is kept. The LLM also selects a matching real vehicle from a traffic snapshot and modulates the simulated vehicle with reference to that real action. In a controlled HighD highway setting, compared with the CRITICAL baseline and a PPO-based learning baseline, REARL reduces the Hellinger distance for speed distributions to 0.3067 and the MAPE for mean spacing to 0.8371, while achieving a time headway (THW) of 22.8575 and a lane change rate of 0.0708.
The results demonstrate the value of behavior-centered benchmarking and establish SIREN as an extensible data-generation and evaluation platform for autonomous-driving and transportation safety research.
Yi-Chen Zhu, Tian Zhao, Haoxin Leng et al.· 0 citations
Autonomous driving planners are typically evaluated using aggregate metrics such as driving score, destination rate, and collision rate, which do not explicitly measure compliance with traffic rules. As a result, planners can achieve high benchmark scores while still exhibiting unsafe or illegal behaviors, limiting the...
Victoria Smirnova, V. Zinkovich, Gregorii Bukhtuev et al.· 0 citations
This paper proposes integrating a Large Language Model (LLM) into signal control: roadside devices perceive traffic states, prompt engineering is constructed, and the LLM is driven to reason and generate control signals, on this basis, a CAV speed guidance algorithm is proposed.
Jun-Yao Lin, Yi-Cai Zhang, Tao Wang· Systems· 0 citations
Autonomous driving system (ADS) testing is essential to ensure the safety and reliability of autonomous vehicles (AVs) prior to deployment. As ADSs are increasingly deployed in multi-AV traffic environments, it becomes crucial to assess their cooperative performance, particularly with respect to deadlock, a fundamental...
Ming-Fei Cheng, Xiao-Fei Xie, Li-Li Quan et al.· Proceedings of the ACM on So...· 0 citations
The energy performance of road vehicles has traditionally been evaluated using driving cycles, in which a prescribed speed profile is tracked either in simulation or by a physical vehicle. Recent research has proposed an alternative framework based on operating conditions, where the driving environment is described in...
Luigi Romano, M. Godio, F. Bruzelius et al.· 0 citations
An IoV-TraSim framework for adaptive traffic simulation based on vehicle-to-X communications is proposed, which incorporates the road topology derived from OpenStreetMap, the V2X sensing infrastructure modelled by RSU/OBU, microscopic agent-based vehicle movement, congestion-aware speed modulation, and a heuristic cali...
M. M. Abed, S. N. Maryoush, M. K. Musa· VFAST Transactions on Softwa...· 0 citations
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduNov 17, 2026
By studying the computational foundations of language learning, Associate Professor Jacob Andreas builds intelligent systems that can communicate effectively with humans.
Microsoft Research Blog· microsoft.comNov 16, 2026
AI coding agents are increasingly help developers fix bugs and build features largely on their own, but every interaction with their models consumes tokens. In each session, an agent sends instructions, tool descriptions, and session history to its model. Most efforts to reduce this cost focus on individual tasks. Yet developers return to the same […] The post TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient appeared first on Microsoft Research.
MIT News · Artificial Intelligence· news.mit.eduNov 13, 2026