{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T07:06:21Z","timestamp":1788937581429,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":47,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032373588","type":"print"},{"value":"9783032373595","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-37359-5_29","type":"book-chapter","created":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T06:09:46Z","timestamp":1788934186000},"page":"521-538","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["SceneOrchestra: Efficient Agentic 3D Scene Synthesis via\u00a0Full Tool-Call Trajectory Generation"],"prefix":"10.1007","author":[{"given":"Yun","family":"He","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kelin","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthias","family":"Zwicker","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,10]]},"reference":[{"key":"29_CR1","unstructured":"Achiam, J., et al.: Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"29_CR2","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., et al.: Language models are few-shot learners. Adv. Neural. Inf. Process. Syst. 33, 1877\u20131901 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"29_CR3","doi-asserted-by":"crossref","unstructured":"\u00c7elen, A., et al.: I-design: personalized llm interior designer. In: European Conference on Computer Vision, pp. 217\u2013234. Springer (2024)","DOI":"10.1007\/978-3-031-92387-6_17"},{"key":"29_CR4","doi-asserted-by":"publisher","first-page":"5982","DOI":"10.52202\/068431-0433","volume":"35","author":"M Deitke","year":"2022","unstructured":"Deitke, M., et al.: Procthor: large-scale embodied ai using procedural generation. Adv. Neural. Inf. Process. Syst. 35, 5982\u20135994 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"29_CR5","doi-asserted-by":"crossref","unstructured":"Feng, W., et al.: Layoutgpt: compositional visual planning and generation with large language models. Adv. Neural Inf. Process. Syst. 36, 18225\u201318250 (2023)","DOI":"10.52202\/075280-0802"},{"key":"29_CR6","doi-asserted-by":"crossref","unstructured":"Fu, R., Wen, Z., Liu, Z., Sridhar, S.: Anyhome: open-vocabulary generation of structured and textured 3d homes. In: European Conference on Computer Vision, pp. 52\u201370. Springer (2024)","DOI":"10.1007\/978-3-031-72933-1_4"},{"key":"29_CR7","unstructured":"Fujimoto, S., Meger, D., Precup, D.: Off-policy deep reinforcement learning without exploration. In: International Conference on Machine Learning, pp. 2052\u20132062. PMLR (2019)"},{"issue":"11","key":"29_CR8","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1145\/3422622","volume":"63","author":"I Goodfellow","year":"2020","unstructured":"Goodfellow, I., et al.: Generative adversarial networks. Commun. ACM 63(11), 139\u2013144 (2020)","journal-title":"Commun. ACM"},{"key":"29_CR9","unstructured":"Google DeepMind: Gemini 3.1 pro. https:\/\/deepmind.google\/models\/gemini\/pro\/ (2026). Accessed 22 Jun 2026"},{"key":"29_CR10","doi-asserted-by":"crossref","unstructured":"Gu, Z., et al.: Artiscene: language-driven artistic 3d scene generation through image intermediary. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 2891\u20132901 (2025)","DOI":"10.1109\/CVPR52734.2025.00275"},{"key":"29_CR11","unstructured":"Hafner, D., Lillicrap, T., Norouzi, M., Ba, J.: Mastering atari with discrete world models. arXiv preprint arXiv:2010.02193 (2020)"},{"key":"29_CR12","unstructured":"He, Y., Pittaluga, F., Jiang, Z., Zwicker, M., Chandraker, M., Tasneem, Z.: Langdrivectrl: natural language controllable driving scene editing with multi-modal agents. arXiv preprint arXiv:2512.17445 (2025)"},{"key":"29_CR13","doi-asserted-by":"crossref","unstructured":"He, Y., Ren, X., Tang, D., Zhang, Y., Xue, X., Fu, Y.: Density-preserving deep point cloud compression. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2333\u20132342 (2022)","DOI":"10.1109\/CVPR52688.2022.00237"},{"key":"29_CR14","doi-asserted-by":"crossref","unstructured":"He, Y., Tang, D., Zhang, Y., Xue, X., Fu, Y.: Grad-pu: arbitrary-scale point cloud upsampling via gradient descent with learned distance functions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5354\u20135363 (2023)","DOI":"10.1109\/CVPR52729.2023.00518"},{"key":"29_CR15","doi-asserted-by":"crossref","unstructured":"H\u00f6llein, L., Cao, A., Owens, A., Johnson, J., Nie\u00dfner, M.: Text2room: extracting textured 3d meshes from 2d text-to-image models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7909\u20137920 (2023)","DOI":"10.1109\/ICCV51070.2023.00727"},{"issue":"2","key":"29_CR16","first-page":"3","volume":"1","author":"EJ Hu","year":"2022","unstructured":"Hu, E.J., et al.: Lora: Low-rank adaptation of large language models. Iclr 1(2), 3 (2022)","journal-title":"Iclr"},{"key":"29_CR17","unstructured":"Hu, Z., et al.: Scenecraft: an llm agent for synthesizing 3d scenes as blender code. In: Forty-first International Conference on Machine Learning (2024)"},{"key":"29_CR18","unstructured":"Jiang, D., et al.: Verltool: towards holistic agentic reinforcement learning with tool use. arXiv preprint arXiv:2509.01055 (2025)"},{"key":"29_CR19","unstructured":"Kostrikov, I., Nair, A., Levine, S.: Offline reinforcement learning with implicit q-learning. arXiv preprint arXiv:2110.06169 (2021)"},{"key":"29_CR20","first-page":"1179","volume":"33","author":"A Kumar","year":"2020","unstructured":"Kumar, A., Zhou, A., Tucker, G., Levine, S.: Conservative q-learning for offline reinforcement learning. Adv. Neural. Inf. Process. Syst. 33, 1179\u20131191 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"29_CR21","unstructured":"Levine, S., Kumar, A., Tucker, G., Fu, J.: Offline reinforcement learning: tutorial, review, and perspectives on open problems. arXiv preprint arXiv:2005.01643 (2020)"},{"key":"29_CR22","unstructured":"Li, Z., Yu, K., Cheng, S., Xu, D.: League++: empowering continual robot learning through guided skill acquisition with large language models. In: ICLR 2024 Workshop on Large Language Model (LLM) Agents (2024)"},{"key":"29_CR23","unstructured":"Ling, L., et al.: Scenethesis: a language and vision agentic framework for 3d scene generation. arXiv preprint arXiv:2505.02836 (2025)"},{"key":"29_CR24","unstructured":"Minaee, S., et al.: Large language models: a survey. arXiv preprint arXiv:2402.06196 (2024)"},{"key":"29_CR25","unstructured":"OpenAI: introducing gpt-4.1 in the api. https:\/\/openai.com\/index\/gpt-4-1\/ (2025). Accessed 22 Jun 2026"},{"key":"29_CR26","unstructured":"OpenAI: Introducing GPT-5.5. https:\/\/openai.com\/index\/introducing-gpt-5-5\/ (2026). Accessed 22 Jun 2026"},{"key":"29_CR27","doi-asserted-by":"publisher","first-page":"27730","DOI":"10.52202\/068431-2011","volume":"35","author":"L Ouyang","year":"2022","unstructured":"Ouyang, L., et al.: Training language models to follow instructions with human feedback. Adv. Neural. Inf. Process. Syst. 35, 27730\u201327744 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"29_CR28","first-page":"12013","volume":"34","author":"D Paschalidou","year":"2021","unstructured":"Paschalidou, D., Kar, A., Shugrina, M., Kreis, K., Geiger, A., Fidler, S.: Atiss: autoregressive transformers for indoor scene synthesis. Adv. Neural. Inf. Process. Syst. 34, 12013\u201312026 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"29_CR29","unstructured":"Pfaff, N., Cohn, T., Zakharov, S., Cory, R., Tedrake, R.: Scenesmith: agentic generation of simulation-ready indoor scenes. arXiv preprint arXiv:2602.09153 (2026)"},{"key":"29_CR30","doi-asserted-by":"publisher","first-page":"53728","DOI":"10.52202\/075280-2338","volume":"36","author":"R Rafailov","year":"2023","unstructured":"Rafailov, R., Sharma, A., Mitchell, E., Manning, C.D., Ermon, S., Finn, C.: Direct preference optimization: your language model is secretly a reward model. Adv. Neural. Inf. Process. Syst. 36, 53728\u201353741 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"29_CR31","doi-asserted-by":"crossref","unstructured":"Raistrick, A., et al.: Infinigen indoors: photorealistic indoor scenes using procedural generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21783\u201321794 (2024)","DOI":"10.1109\/CVPR52733.2024.02058"},{"issue":"7839","key":"29_CR32","doi-asserted-by":"publisher","first-page":"604","DOI":"10.1038\/s41586-020-03051-4","volume":"588","author":"J Schrittwieser","year":"2020","unstructured":"Schrittwieser, J., et al.: Mastering atari, go, chess and shogi by planning with a learned model. Nature 588(7839), 604\u2013609 (2020)","journal-title":"Nature"},{"key":"29_CR33","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"key":"29_CR34","unstructured":"Shao, Z., et\u00a0al.: Deepseekmath: pushing the limits of mathematical reasoning in open language models. arXiv preprint arXiv:2402.03300 (2024)"},{"key":"29_CR35","doi-asserted-by":"crossref","unstructured":"Sun, F.Y., et al.: Layoutvlm: differentiable optimization of 3d layout via vision-language models. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 29469\u201329478 (2025)","DOI":"10.1109\/CVPR52734.2025.02744"},{"key":"29_CR36","doi-asserted-by":"crossref","unstructured":"Tang, J., Nie, Y., Markhasin, L., Dai, A., Thies, J., Nie\u00dfner, M.: Diffuscene: denoising diffusion models for generative indoor scene synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20507\u201320518 (2024)","DOI":"10.1109\/CVPR52733.2024.01938"},{"key":"29_CR37","unstructured":"Wen, B., Xie, H., Chen, Z., Hong, F., Liu, Z.: 3d scene generation: a survey. arXiv preprint arXiv:2505.05474 (2025)"},{"key":"29_CR38","unstructured":"Xia, H., et\u00a0al.: Sage: scalable agentic 3d scene generation for embodied ai. arXiv preprint arXiv:2602.10116 (2026)"},{"key":"29_CR39","unstructured":"Yang, A., et\u00a0al.: Qwen3 technical report. arXiv preprint arXiv:2505.09388 (2025)"},{"key":"29_CR40","doi-asserted-by":"crossref","unstructured":"Yang, Y., Jia, B., Zhang, S., Huang, S.: Sceneweaver: all-in-one 3d scene synthesis with an extensible and self-reflective agent. arXiv preprint arXiv:2509.20414 (2025)","DOI":"10.52202\/085713-4689"},{"key":"29_CR41","doi-asserted-by":"crossref","unstructured":"Yang, Y., Jia, B., Zhi, P., Huang, S.: Physcene: physically interactable 3d scene synthesis for embodied ai. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16262\u201316272 (2024)","DOI":"10.1109\/CVPR52733.2024.01539"},{"key":"29_CR42","doi-asserted-by":"crossref","unstructured":"Yang, Y., et\u00a0al.: Holodeck: Language guided generation of 3d embodied ai environments. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16227\u201316237 (2024)","DOI":"10.1109\/CVPR52733.2024.01536"},{"key":"29_CR43","unstructured":"Yao, S., et al.: React: synergizing reasoning and acting in language models. arXiv preprint arXiv:2210.03629 (2022)"},{"key":"29_CR44","unstructured":"Yin, S., et al.: Vision-as-inverse-graphics agent via interleaved multimodal reasoning. arXiv preprint arXiv:2601.11109 (2026)"},{"key":"29_CR45","unstructured":"Zhang, G., et\u00a0al.: The landscape of agentic reinforcement learning for llms: a survey. arXiv preprint arXiv:2509.02547 (2025)"},{"issue":"3","key":"29_CR46","doi-asserted-by":"publisher","first-page":"594","DOI":"10.1007\/s11390-019-1929-5","volume":"34","author":"SH Zhang","year":"2019","unstructured":"Zhang, S.H., Zhang, S.K., Liang, Y., Hall, P.: A survey of 3d indoor scene synthesis. J. Comput. Sci. Technol. 34(3), 594\u2013608 (2019)","journal-title":"J. Comput. Sci. Technol."},{"key":"29_CR47","doi-asserted-by":"crossref","unstructured":"Zheng, Y., Zhang, R., Zhang, J., Ye, Y., Luo, Z.: Llamafactory: unified efficient fine-tuning of 100+ language models. In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations), pp. 400\u2013410 (2024)","DOI":"10.18653\/v1\/2024.acl-demos.38"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37359-5_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T06:09:54Z","timestamp":1788934194000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37359-5_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032373588","9783032373595"],"references-count":47,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37359-5_29","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"10 September 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}