MTDrive: Multi-turn Interactive Reinforcement Learning for Autonomous Driving

2026-01-30 · Xidong Li, Mingyu Guo, Chenchao Xu, Bailin Li, Wenjing Zhu, Yangang Zou, Rui Chen, Zehuan Wang arxiv

Trajectory planning is a core task in autonomous driving, requiring the prediction of safe and comfortable paths across diverse scenarios. Integrating Multi-modal Large Language Models (MLLMs) with Reinforcement Learning (RL) has shown promise in addressing "long-tail" scenarios. However, existing methods are constrained to single-turn reasoning, limiting their ability to handle complex tasks requiring iterative refinement. To overcome this limitation, we present MTDrive, a multi-turn framework that enables MLLMs to iteratively refine trajectories based on environmental feedback. MTDrive introduces Multi-Turn Group Relative Policy Optimization (mtGRPO), which mitigates reward sparsity by computing relative advantages across turns. We further construct an interactive trajectory understanding dataset from closed-loop simulation to support multi-turn training. Experiments on the NAVSIM benchmark demonstrate superior performance compared to existing methods, validating the effectiveness of our multi-turn reasoning paradigm. Additionally, we implement system-level optimizations to reduce data transfer overhead caused by high-resolution images and multi-turn sequences, achieving 2.5x training throughput. Our data, models, and code will be made available soon.

📄 PDF Abstract BibTeX arXiv:2601.22930

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning Trajectory Planning Autonomous Driving

MedSAM-Agent: Empowering Interactive Medical Image Segmentation with Multi-turn Agentic Reinforcement Learning

2026-02-03 · Shengyuan Liu, Liuxin Bao, Qi Yang, Wanting Geng 외 arxiv

Medical image segmentation is evolving from task-specific models toward generalizable frameworks. Recent research leverages Multi-modal Large Language Models (MLLMs) as autonomous agents, employing reinforcement learning…

Medical Image Segmentation Interactive Segmentation Reinforcement Learning

Multi-task Safe Reinforcement Learning for Navigating Intersections in Dense Traffic

2022-02-19 · Yuqi Liu, Qichao Zhang, Dongbin Zhao

Multi-task intersection navigation including the unprotected turning left, turning right, and going straight in dense traffic is still a challenging task for autonomous driving. For the human driver, the negotiation skil…

Autonomous Driving reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)+1

Process-Supervised Reinforcement Learning for Interactive Multimodal Tool-Use Agents

2025-09-17 · Weiting Tan, Xinghua Qu, Ming Tu, Meng Ge 외 arxiv

Effective interactive tool use requires agents to master Tool Integrated Reasoning (TIR): a complex process involving multi-turn planning and long-context dialogue management. To train agents for this dynamic process, pa…

Reinforcement Learning Mathematical Reasoning

Deep Interactive Reinforcement Learning for Path Following of Autonomous Underwater Vehicle

2020-01-10 · Qilei Zhang, Jinying Lin, Qixin Sha, Bo He 외

Autonomous underwater vehicle (AUV) plays an increasingly important role in ocean exploration. Existing AUVs are usually not fully autonomous and generally limited to pre-planning or pre-programming tasks. Reinforcement …

Deep Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

SMARTS: Scalable Multi-Agent Reinforcement Learning Training School for Autonomous Driving

2020-10-19 · Ming Zhou, Jun Luo, Julian Villella, Yaodong Yang 외

Multi-agent interaction is a fundamental aspect of autonomous driving in the real world. Despite more than a decade of research and development, the problem of how to competently interact with diverse road users in diver…

Autonomous Driving Multi-agent Reinforcement Learning reinforcement-learning Reinforcement Learning (RL)