Accepted at 2026 IEEE International Conference on Intelligent Robots and Systems (IROS)</p>\n","updatedAt":"2026-07-17T17:43:29.516Z","author":{"_id":"672288dd7055eec76d377268","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/672288dd7055eec76d377268/bBQ51VwKZJIkHkNffuEuJ.jpeg","fullname":"Yuan Gao","name":"Yuan-avs","type":"user","isPro":true,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":3,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.7571131587028503},"editors":["Yuan-avs"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/672288dd7055eec76d377268/bBQ51VwKZJIkHkNffuEuJ.jpeg"],"reactions":[],"isReport":false}},{"id":"6a5af994e23d004c576ed8ab","author":{"_id":"63d3e0e8ff1384ce6c5dd17d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg","fullname":"Librarian Bot (Bot)","name":"librarian-bot","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":376,"isUserFollowing":false},"createdAt":"2026-07-18T03:57:08.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"This is an automated message from the [Librarian Bot](https://huggingface.co/librarian-bots). I found the following papers similar to this paper. \n\nThe following papers were recommended by the Semantic Scholar API \n\n* [From Driving Videos to Simulatable Scenarios](https://huggingface.co/papers/2606.21993) (2026)\n* [TrafficAlign: Aligning Large Language Models for Traffic Scenario Generation](https://huggingface.co/papers/2606.29097) (2026)\n* [RAG-Driven Multi-Agent LLM Framework with Task Decomposition for Beyond 5G Auto-Configuration](https://huggingface.co/papers/2606.01222) (2026)\n* [AutoSG: LLM-Driven Solver Generation Solely from Task Prompts for Expensive Optimization](https://huggingface.co/papers/2605.25658) (2026)\n* [Sakura: An Approach for Generating Complex Tests from Natural Language Test Descriptions](https://huggingface.co/papers/2606.00530) (2026)\n* [In-Context Model Predictive Generation: Open-Vocabulary Motion Synthesis from Language Models to Physics](https://huggingface.co/papers/2606.26981) (2026)\n* [LUNA-AD: Lightweight Uncertainty-Aware Language Model with Lifelong Learning for Autonomous Driving](https://huggingface.co/papers/2606.08470) (2026)\n\n\n Please give a thumbs up to this comment if you found it helpful!\n\n If you want recommendations for any Paper on Hugging Face checkout [this](https://huggingface.co/spaces/librarian-bots/recommend_similar_papers) Space\n\n You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: `@librarian-bot recommend`","html":"<p>This is an automated message from the <a href=\"https://huggingface.co/librarian-bots\">Librarian Bot</a>. I found the following papers similar to this paper. </p>\n<p>The following papers were recommended by the Semantic Scholar API </p>\n<ul>\n<li><a href=\"https://huggingface.co/papers/2606.21993\">From Driving Videos to Simulatable Scenarios</a> (2026)</li>\n<li><a href=\"https://huggingface.co/papers/2606.29097\">TrafficAlign: Aligning Large Language Models for Traffic Scenario Generation</a> (2026)</li>\n<li><a href=\"https://huggingface.co/papers/2606.01222\">RAG-Driven Multi-Agent LLM Framework with Task Decomposition for Beyond 5G Auto-Configuration</a> (2026)</li>\n<li><a href=\"https://huggingface.co/papers/2605.25658\">AutoSG: LLM-Driven Solver Generation Solely from Task Prompts for Expensive Optimization</a> (2026)</li>\n<li><a href=\"https://huggingface.co/papers/2606.00530\">Sakura: An Approach for Generating Complex Tests from Natural Language Test Descriptions</a> (2026)</li>\n<li><a href=\"https://huggingface.co/papers/2606.26981\">In-Context Model Predictive Generation: Open-Vocabulary Motion Synthesis from Language Models to Physics</a> (2026)</li>\n<li><a href=\"https://huggingface.co/papers/2606.08470\">LUNA-AD: Lightweight Uncertainty-Aware Language Model with Lifelong Learning for Autonomous Driving</a> (2026)</li>\n</ul>\n<p> Please give a thumbs up to this comment if you found it helpful!</p>\n<p> If you want recommendations for any Paper on Hugging Face checkout <a href=\"https://huggingface.co/spaces/librarian-bots/recommend_similar_papers\">this</a> Space</p>\n<p> You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: <code>@librarian-bot recommend</code></p>\n","updatedAt":"2026-07-18T03:57:08.884Z","author":{"_id":"63d3e0e8ff1384ce6c5dd17d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg","fullname":"Librarian Bot (Bot)","name":"librarian-bot","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":376,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.713338315486908},"editors":["librarian-bot"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2607.14387","authors":[{"_id":"6a5a17f41d9eb8b3e86d6946","name":"Yuan Gao","hidden":false},{"_id":"6a5a17f41d9eb8b3e86d6947","name":"Wenting Miao","hidden":false},{"_id":"6a5a17f41d9eb8b3e86d6948","name":"Mattia Piccinini","hidden":false},{"_id":"6a5a17f41d9eb8b3e86d6949","name":"Haoyu Wang","hidden":false},{"_id":"6a5a17f41d9eb8b3e86d694a","name":"Qunying Song","hidden":false},{"_id":"6a5a17f41d9eb8b3e86d694b","name":"Johannes Betz","hidden":false}],"mediaUrls":["https://cdn-uploads.huggingface.co/production/uploads/672288dd7055eec76d377268/xgNJp-ib4qwzUiaQmmI3c.png"],"publishedAt":"2026-07-15T00:00:00.000Z","submittedOnDailyAt":"2026-07-17T00:00:00.000Z","title":"Chat2Scenic: An Iterative RAG-Based Framework for Scenario Generation in Autonomous Driving","submittedOnDailyBy":{"_id":"672288dd7055eec76d377268","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/672288dd7055eec76d377268/bBQ51VwKZJIkHkNffuEuJ.jpeg","isPro":true,"fullname":"Yuan Gao","user":"Yuan-avs","type":"user","name":"Yuan-avs"},"summary":"Validating autonomous driving systems requires diverse, regulation-compliant test scenarios. In simulation-based testing, scenarios are defined as executable scripts. Yet automatically generating such scripts from regulatory descriptions remains an open challenge, and existing approaches face fundamental trade-offs. Retrieval-assemble methods achieve reasonable compilation rates but lack scalability, whereas retrieval-based full-script generation suffers from low compilation success rates. We present Chat2Scenic, the first iterative retrieval-augmented framework to generate scenario scripts in Domain Specific Language (DSL). Specifically, Chat2Scenic provides a chatbot interface that supports interactive scenario refinement and integrates Retrieval-augmented Generation (RAG) to ground scenario generation in regulatory knowledge and DSL syntax. Furthermore, we propose an open benchmark for scenario generation comprising 123 scenarios from various regulations, including NHTSA and United Nations Vehicle Regulations, as well as other sources. Extensive evaluation with State-of-the-Art (SOTA) Large Language Models (LLMs) demonstrates that Chat2Scenic achieves 76.42% Compilation Success Rate (CSR) and 58.17% Framework Accuracy (FA), outperforming existing methods (Retrieval Assemble with 30.08% CSR, 11.03% FA and Retrieval full script generation with 16.26% CSR, 10.86% FA). To facilitate future research, we release our code as open source at https://github.com/TUM-AVS/chat2scenic.","upvotes":4,"discussionId":"6a5a17f41d9eb8b3e86d694c","projectPage":"https://anonymous-research-paper.github.io/Chat2Scenic/","githubRepo":"https://github.com/TUM-AVS/Chat2scenic","githubRepoAddedBy":"user","githubStars":6,"organization":{"_id":"6a4f83663e43ae629a202b05","name":"TUM-AVS","fullname":"TUM - Professorship of Autonomous Vehicle Systems","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/6723459e7ddd97700c1c1c6a/AJSXS1Qq8ywx4puQ91Fhm.png"}},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"672288dd7055eec76d377268","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/672288dd7055eec76d377268/bBQ51VwKZJIkHkNffuEuJ.jpeg","isPro":true,"fullname":"Yuan Gao","user":"Yuan-avs","type":"user"},{"_id":"69bcf5d20b92270da8a7c503","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/MjiG7LPVr9s8Y0lX5P7Jp.png","isPro":false,"fullname":"佐々木 咲良","user":"lucasifg4","type":"user"},{"_id":"69bba6dec13f259f186dbb64","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/Wo7iu23ViolMlZDV6A4IV.png","isPro":false,"fullname":"Oliver Hill","user":"mateongu248","type":"user"},{"_id":"69bcb51f2bae61f967537c26","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/_Y2gTEvCx1aLnx9LUov_C.png","isPro":false,"fullname":"Петров Роман","user":"ameliar","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0,"organization":{"_id":"6a4f83663e43ae629a202b05","name":"TUM-AVS","fullname":"TUM - Professorship of Autonomous Vehicle Systems","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/6723459e7ddd97700c1c1c6a/AJSXS1Qq8ywx4puQ91Fhm.png"},"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2607/2607.14387.md","query":{}}">

Get this paper in your agent:

Don't have the latest CLI?

Cite arxiv.org/abs/2607.14387 in a model README.md to link it from this page.

Cite arxiv.org/abs/2607.14387 in a Space README.md to link it from this page.