The autonomous driving (AD) system has exhibited remarkable performance in complex driving scenarios. However, generalization is still a key limitation for the current system, which refers to the ability to handle unseen scenarios or unfamiliar sensor configurations.Related works have explored the use of Vision-Language Models (VLMs) to address few-shot or zero-shot tasks. While promising, these methods introduce a new challenge: the emergence of a hybrid AD system, where two distinct systems are used to plan a trajectory, leading to potential inconsistencies. Alternative research directions have explored Vision-Language-Action (VLA) frameworks that generate control actions from VLM directly. However, these end-to-end solutions demonstrate prohibitive computational demands. To overcome these challenges, we introduce Risk Semantic Distillation (RSD), a novel framework that leverages VLMs to enhance the training of End-to-End (E2E) AD backbones. By providing risk attention for key objects, RSD addresses the issue of generalization. Specifically, we introduce RiskHead, a plug-in module that distills causal risk estimates from Vision-Language Models into Bird's-Eye-View (BEV) features, yielding interpretable risk-attention maps.This approach allows BEV features to learn richer and more nuanced risk attention representations, which directly enhance the model's ability to handle spatial boundaries and risky objects.By focusing on risk attention, RSD aligns better with human-like driving behavior, which is essential to navigate in complex and dynamic environments. Our experiments on the Bench2Drive benchmark demonstrate the effectiveness of RSD in managing complex and unpredictable driving conditions. Due to the enhanced BEV representations enabled by RSD, we observed a significant improvement in both perception and planning capabilities.

Vision-based end-to-end (E2E) driving has garnered significant interest in the research community due to its scalability and synergy with multimodal large language models (MLLMs). However, current E2E driving benchmarks primarily feature nominal scenarios, failing to adequately test the true potential of these systems. Furthermore, existing open-loop evaluation metrics often fall short in capturing the multi-modal nature of driving or effectively evaluating performance in long-tail scenarios. To address these gaps, we introduce the Waymo Open Dataset for End-to-End Driving (WOD-E2E). WOD-E2E contains 4,021 driving segments (approximately 12 hours), specifically curated for challenging long-tail scenarios that that are rare in daily life with an occurring frequency of less than 0.03%. Concretely, each segment in WOD-E2E includes the high-level routing information, ego states, and 360-degree camera views from 8 surrounding cameras. To evaluate the E2E driving performance on these long-tail situations, we propose a novel open-loop evaluation metric: Rater Feedback Score (RFS). Unlike conventional metrics that measure the distance between predicted way points and the logs, RFS measures how closely the predicted trajectory matches rater-annotated trajectory preference labels. We have released rater preference labels for all WOD-E2E validation set segments, while the held out test set labels have been used for the 2025 WOD-E2E Challenge. Through our work, we aim to foster state of the art research into generalizable, robust, and safe end-to-end autonomous driving agents capable of handling complex real-world situations.

Maintaining good driving behavior in out-of-distribution scenarios remains a critical challenge in autonomous driving. A promising direction is to leverage the generalist knowledge and reasoning capabilities of large-language models by treating unusual driving scenarios as a logical reasoning task. In this work, we present Poutine, a method that uses an off-the-shelf 3B-parameter vision-language model (VLM) - without any additional components - to achieve robust end-to-end autonomous driving via a simple and scalable training recipe. To learn strong base driving capabilities, we first train Poutine-Base using self-supervised next-token prediction over vision, language, and trajectory (VLT) tokens, leveraging both nominal and long-tail driving data. In the second stage, we fine-tune Poutine-Base using Group Relative Policy Optimization (GRPO) with a small set of human preference-labeled examples. We evaluated our approach on the Waymo end-to-end driving benchmark curated for long-tail scenarios. The final Poutine model achieves an RFS of 7.99 on the test set, placing 1st in the 2025 Waymo Vision-Based End-to-End Driving Challenge by a significant margin. Our results suggest that handcrafted tokenizers or custom architectural components added to base VLMs in prior work are not necessary to achieve strong driving performance. Instead, this work highlights the potential of scalable VLT pretraining combined with lightweight RL fine-tuning to enable robust and generalizable autonomous driving.

Autonomous Driving (AD) systems have made notable progress, but their performance in long-tail, safety-critical scenarios remains limited. These rare cases contribute a disproportionate number of accidents. Vision-Language Action (VLA) models have strong reasoning abilities and offer a potential solution, but their effectiveness is limited by the lack of high-quality data and inefficient learning in such conditions. To address these challenges, we propose CoReVLA, a continual learning end-to-end autonomous driving framework that improves the performance in long-tail scenarios through a dual-stage process of data Collection and behavior Refinement. First, the model is jointly fine-tuned on a mixture of open-source driving QA datasets, allowing it to acquire a foundational understanding of driving scenarios. Next, CoReVLA is deployed within the Cave Automatic Virtual Environment (CAVE) simulation platform, where driver takeover data is collected from real-time interactions. Each takeover indicates a long-tail scenario that CoReVLA fails to handle reliably. Finally, the model is refined via Direct Preference Optimization (DPO), allowing it to learn directly from human preferences and thereby avoid reward hacking caused by manually designed rewards. Extensive open-loop and closed-loop experiments demonstrate that the proposed CoReVLA model can accurately perceive driving scenarios and make appropriate decisions. On the Bench2Drive benchmark, CoReVLA achieves a Driving Score (DS) of 72.18 and a Success Rate (SR) of 50%, outperforming state-of-the-art methods by 7.96 DS and 15% SR under long-tail, safety-critical scenarios. Furthermore, case studies demonstrate the model's ability to continually improve its performance in similar failure-prone scenarios by leveraging past takeover experiences. All codea and preprocessed datasets are available at: https://github.com/FanGShiYuu/CoReVLA

Autonomous driving has the potential to revolutionize transportation systems by operating with minimal or no human intervention, thereby eliminating many human errors. However, it faces significant safety challenges in diverse traffic scenarios, extreme weather conditions, and complex interactions with human-driven vehicles (Zhou et al. (2023); Xu et al. (2025)). Existing studies have suggested that extreme weather conditions, including heavy rain, snow, and fog, can significantly reduce the ability of autonomous driving in detecting objects, planning trajectories, and making driving decisions (Zang et al. (2019), Mehra et al. (2020)), posing significant safety concerns. Therefore, there is an urgent need to develop autonomous driving technologies that are robust to rare and diverse environmental conditions to ensure safe and reliable operation. End-to-end autonomous driving has become the prevailing paradigm for high-level autonomy, offering a unified learning-based framework that directly maps raw sensory inputs to driving actions. Compared to traditional modular pipelines that decompose driving into discrete stages (Figure 1a), end-to-end frameworks simplify system design, reduce interface mismatches, and enable global optimization of the driving policy. Among recent advances, vision-language models (VLMs) have emerged as powerful backbones for end-to-end reasoning (Xiao et al. (2024); Chen et al. (2024); Feng et al. (2025)). By jointly encoding visual scenes and natural language prompts, VLMs offer rich semantic grounding and flexible context understanding, making them a natural fit for autonomous driving tasks. Leveraging these capabilities, recent works have introduced VLM-based end-to-end pipelines (Figure 1b), which show promising improvements in semantic generalization and reasoning ability (Hwang et al. (2024); Xing et al. (2025); Zhou et al. (2025); Huang et al. (2024); Tian et al. (2024b)).

Recent advances in autonomous driving research towards motion planners that are robust, safe, and adaptive. However, existing rule-based and data-driven planners lack adaptability to long-tail scenarios, while knowledge-driven methods offer strong reasoning but face challenges in representation, control, and real-world evaluation. To address these challenges, we present LiloDriver, a lifelong learning framework for closed-loop motion planning in long-tail autonomous driving scenarios. By integrating large language models (LLMs) with a memory-augmented planner generation system, LiloDriver continuously adapts to new scenarios without retraining. It features a four-stage architecture including perception, scene encoding, memory-based strategy refinement, and LLM-guided reasoning. Evaluated on the nuPlan benchmark, LiloDriver achieves superior performance in both common and rare driving scenarios, outperforming static rule-based and learning-based planners. Our results highlight the effectiveness of combining structured memory and LLM reasoning to enable scalable, human-like motion planning in real-world autonomous driving. Our code is available at https://github.com/Hyan-Yao/LiloDriver.

The autonomous driving industry is increasingly adopting end-to-end learning from sensory inputs to minimize human biases in system design. Traditional end-to-end driving models, however, suffer from long-tail events due to rare or unseen inputs within their training distributions. To address this, we propose TOKEN, a novel Multi-Modal Large Language Model (MM-LLM) that tokenizes the world into object-level knowledge, enabling better utilization of LLM's reasoning capabilities to enhance autonomous vehicle planning in long-tail scenarios. TOKEN effectively alleviates data scarcity and inefficient tokenization by leveraging a traditional end-to-end driving model to produce condensed and semantically enriched representations of the scene, which are optimized for LLM planning compatibility through deliberate representation and reasoning alignment training stages. Our results demonstrate that TOKEN excels in grounding, reasoning, and planning capabilities, outperforming existing frameworks with a 27% reduction in trajectory L2 error and a 39% decrease in collision rates in long-tail scenarios. Additionally, our work highlights the importance of representation alignment and structured reasoning in sparking the common-sense reasoning capabilities of MM-LLMs for effective planning.

Realistic traffic simulation is crucial for developing self-driving software in a safe and scalable manner prior to real-world deployment. Typically, imitation learning (IL) is used to learn human-like traffic agents directly from real-world observations collected offline, but without explicit specification of traffic rules, agents trained from IL alone frequently display unrealistic infractions like collisions and driving off the road. This problem is exacerbated in out-of-distribution and long-tail scenarios. On the other hand, reinforcement learning (RL) can train traffic agents to avoid infractions, but using RL alone results in unhuman-like driving behaviors. We propose Reinforcing Traffic Rules (RTR), a holistic closed-loop learning objective to match expert demonstrations under a traffic compliance constraint, which naturally gives rise to a joint IL + RL approach, obtaining the best of both worlds. Our method learns in closed-loop simulations of both nominal scenarios from real-world datasets as well as procedurally generated long-tail scenarios. Our experiments show that RTR learns more realistic and generalizable traffic simulation policies, achieving significantly better tradeoffs between human-like driving and traffic compliance in both nominal and long-tail scenarios. Moreover, when used as a data generation tool for training prediction models, our learned traffic policy leads to considerably improved downstream prediction metrics compared to baseline traffic agents. For more information, visit the project website: https://waabi.ai/rtr