{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/reasonplan-unified-scene-prediction-and","title":"ReasonPlan: Unified Scene Prediction and Decision Reasoning for Closed-loop Autonomous Driving","arxiv_id":"2505.20024","date":"2025-05-26","proceeding":null,"authors":["Xueyi Liu","Zuodong Zhong","Yuxin Guo","Yun-Fu Liu","Zhiguo Su","Qichao Zhang","Junli Wang","Yinfeng Gao","Yupeng Zheng","Qiao Lin","Huiyong Chen","Dongbin Zhao"],"abstract":"Due to the powerful vision-language reasoning and generalization abilities, multimodal large language models (MLLMs) have garnered significant attention in the field of end-to-end (E2E) autonomous driving. However, their application to closed-loop systems remains underexplored, and current MLLM-based methods have not shown clear superiority to mainstream E2E imitation learning approaches. In this work, we propose ReasonPlan, a novel MLLM fine-tuning framework designed for closed-loop driving through holistic reasoning with a self-supervised Next Scene Prediction task and supervised Decision Chain-of-Thought process. This dual mechanism encourages the model to align visual representations with actionable driving context, while promoting interpretable and causally grounded decision making. We curate a planning-oriented decision reasoning dataset, namely PDR, comprising 210k diverse and high-quality samples. Our method outperforms the mainstream E2E imitation learning method by a large margin of 19% L2 and 16.1 driving score on Bench2Drive benchmark. Furthermore, ReasonPlan demonstrates strong zero-shot generalization on unseen DOS benchmark, highlighting its adaptability in handling zero-shot corner cases. Code and dataset will be found in https://github.com/Liuxueyi/ReasonPlan.","url_abs":"https://arxiv.org/abs/2505.20024v1","url_pdf":"https://arxiv.org/pdf/2505.20024v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"reasonplan-unified-scene-prediction-and","repo_url":"https://github.com/liuxueyi/reasonplan","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"autonomous-driving","task_name":"Autonomous Driving"},{"task_slug":"bench2drive","task_name":"Bench2Drive"},{"task_slug":"imitation-learning","task_name":"Imitation Learning"},{"task_slug":"zero-shot-generalization","task_name":"Zero-shot Generalization"}],"methods":[{"method_slug":"align","method_name":"ALIGN"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/bench2drive-on-bench2drive","task":"Bench2Drive","dataset":"Bench2Drive","model":"ReasonPlan","rank_in_archive_order":17,"of":35,"metrics":{"Driving Score":"64.01"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2505.20024","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}