MAGNIFIED: RL Fine-tuning of Multimodal Large Language Models for Motion Planning

• URL: http://arxiv.org/abs/2606.20641v1
• Date: Tue, 02 Jun 2026 16:07:28 GMT
• Title: MAGNIFIED: RL Fine-tuning of Multimodal Large Language Models for Motion Planning
• Abstract summary: Multi-modal Large Language Models (MLLMs) have demonstrated remarkable capabilities in semantic understanding and common sense reasoning.<n>Next-token text prediction objectives may fall short of fulfilling the planning objectives for autonomous vehicles.<n>We propose a reinforcement learning fine-tuning approach, MAGNIFIED, that aligns the MLLM-based driving agent with planning objectives by learning from token-level rewards.
• Score: 16.474293563670415
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multi-modal Large Language Models (MLLMs) have demonstrated remarkable capabilities in semantic understanding and common sense reasoning, making them promising candidates for solving planning problems in autonomous driving. However, the next-token text prediction objectives traditionally used in pre-training and supervised fine-tuning (SFT) of MLLMs may fall short of fulfilling the planning objectives for autonomous vehicles. The next-token prediction objective merely encourages per-token imitation in text, often irrespective of multi-step consequences and the alignment with crucial planning considerations such as giving space to other road actors. To overcome these limitations, we propose a reinforcement learning fine-tuning (RLFT) approach, MAGNIFIED, that aligns the MLLM-based driving agent with planning objectives by learning from token-level rewards. By mapping a sequence of predicted tokens to corresponding vehicle trajectories and learning from planning rewards, MAGNIFIED optimizes for the true planning objectives rather than focusing solely on token prediction accuracy, enabling the model to refine its understanding of the planning task beyond simple imitation. We validate our approach on the Waymo Open Motion Dataset with a novel setup incorporating rasterized birds-eye views and tokenized trajectories as inputs and planning-oriented outputs. An initial SFT phase establishes a strong baseline in outputting plan trajectories as sequences of X-Y coordinates in text, while subsequent RL fine-tuning substantially enhances planning performance relative to the SFT baseline (demonstrating over a 10.5% reduction in overlap rate and a 38.9% reduction in off-road rate), underscoring the potential of RLFT on MLLMs to achieve vehicle planning that is better aligned with compliant, comfortable, and efficient driving.

Related papers

• Efficient and Explainable End-to-End Autonomous Driving via Masked Vision-Language-Action Diffusion [23.834662472392694]
  Masked Vision-Language-Action Diffusion for Autonomous Driving (MVLAD-AD) is a novel framework designed to bridge the gap between efficient planning and semantic explainability.<n>We introduce a discrete action tokenization strategy that constructs a compact codebook of kinematically feasible waypoints from real-world driving distributions.<n>Experiments on nuScenes and derived benchmarks demonstrate that MVLAD-AD achieves superior efficiency and outperforms state-of-the-art autoregressive and diffusion baselines in planning precision.
  arXiv  Detail & Related papers  (2026-02-24T05:59:10Z)
• PILOT: Planning via Internalized Latent Optimization Trajectories for Large Language Models [51.43746425777865]
  Large Language Models (LLMs) often lack the capacity to formulate global strategies, leading to error propagation in long-horizon tasks.<n>We propose PILOT, a framework designed to internalize the strategic oversight of large models into intrinsic Latent Guidance.
  arXiv  Detail & Related papers  (2026-01-07T12:38:56Z)
• ImagiDrive: A Unified Imagination-and-Planning Framework for Autonomous Driving [64.12414815634847]
  Vision-Language Models (VLMs) and Driving World Models (DWMs) have independently emerged as powerful recipes addressing different aspects of this challenge.<n>We propose ImagiDrive, a novel end-to-end autonomous driving framework that integrates a VLM-based driving agent with a DWM-based scene imaginer.
  arXiv  Detail & Related papers  (2025-08-15T12:06:55Z)
• Plan-R1: Safe and Feasible Trajectory Planning as Language Modeling [74.41886258801209]
  We propose a two-stage trajectory planning framework that decouples principle alignment from behavior learning.<n>Plan-R1 significantly improves planning safety and feasibility, achieving state-of-the-art performance.
  arXiv  Detail & Related papers  (2025-05-23T09:22:19Z)
• Distilling Multi-modal Large Language Models for Autonomous Driving [64.63127269187814]
  Recent end-to-end autonomous driving systems leverage large language models (LLMs) as planners to improve generalizability to rare events.<n>We propose DiMA, an end-to-end autonomous driving system that maintains the efficiency of an LLM-free (or vision-based) planner while leveraging the world knowledge of an LLM.<n>Training with DiMA results in a 37% reduction in the L2 trajectory error and an 80% reduction in the collision rate of the vision-based planner, as well as a 44% trajectory error reduction in longtail scenarios.
  arXiv  Detail & Related papers  (2025-01-16T18:59:53Z)
• Tokenize the World into Object-level Knowledge to Address Long-tail Events in Autonomous Driving [43.156632952193966]
  Traditional end-to-end driving models suffer from long-tail events due to rare or unseen inputs within their training distributions. We propose TOKEN, a novel Multi-Modal Large Language Model (MM-LLM) that tokenizes the world into object-level knowledge. ToKEN effectively alleviates data scarcity and inefficient tokenization by leveraging a traditional end-to-end driving model.
  arXiv  Detail & Related papers  (2024-07-01T04:34:50Z)
• Asynchronous Large Language Model Enhanced Planner for Autonomous Driving [26.72215912937613]
  AsyncDriver is a new framework designed to guide real-time planners in making precise and controllable trajectory predictions. By capitalizing on the asynchronous nature of their inference frequencies, our approach have successfully reduced the computational cost introduced by LLM. Experiments show that our approach achieves superior closed-loop evaluation performance on nuPlan's challenging scenarios.
  arXiv  Detail & Related papers  (2024-06-20T17:59:03Z)
• Exploring and Benchmarking the Planning Capabilities of Large Language Models [57.23454975238014]
  This work lays the foundations for improving planning capabilities of large language models (LLMs) We construct a comprehensive benchmark suite encompassing both classical planning benchmarks and natural language scenarios. We investigate the use of many-shot in-context learning to enhance LLM planning, exploring the relationship between increased context length and improved planning performance.
  arXiv  Detail & Related papers  (2024-06-18T22:57:06Z)
• LLM-Assist: Enhancing Closed-Loop Planning with Language-Based Reasoning [65.86754998249224]
  We develop a novel hybrid planner that leverages a conventional rule-based planner in conjunction with an LLM-based planner. Our approach navigates complex scenarios which existing planners struggle with, produces well-reasoned outputs while also remaining grounded through working alongside the rule-based approach.
  arXiv  Detail & Related papers  (2023-12-30T02:53:45Z)
• GPT-Driver: Learning to Drive with GPT [47.14350537515685]
  We present a simple yet effective approach that can transform the OpenAI GPT-3.5 model into a reliable motion planner for autonomous vehicles. We capitalize on the strong reasoning capabilities and generalization potential inherent to Large Language Models (LLMs) We evaluate our approach on the large-scale nuScenes dataset, and extensive experiments substantiate the effectiveness, generalization ability, and interpretability of our GPT-based motion planner.
  arXiv  Detail & Related papers  (2023-10-02T17:59:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.