{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T08:08:05Z","timestamp":1789373285140,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":48,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032372543","type":"print"},{"value":"9783032372550","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\/978-3-032-37255-0_14","type":"book-chapter","created":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T07:46:13Z","timestamp":1789371973000},"page":"251-268","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["VideoTIR: Accurate Understanding for\u00a0Long Videos with\u00a0Efficient Tool-Integrated Reasoning"],"prefix":"10.1007","author":[{"given":"Zhe","family":"Gao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shiyu","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Taifeng","family":"Chai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weinong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haotian","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xing","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenbin","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qi","family":"Fan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dacheng","family":"Tao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,15]]},"reference":[{"key":"14_CR1","doi-asserted-by":"crossref","unstructured":"Ahmed, I., Islam, S., Datta, P.P., Kabir, I., Chowdhury, N.U.R., Haque, A.: QWEN 2.5: a comprehensive review of the leading resource-efficient LLM with potential to surpass all competitors. Authorea Preprints (2025)","DOI":"10.36227\/techrxiv.174060306.65738406\/v1"},{"key":"14_CR2","doi-asserted-by":"crossref","unstructured":"Alayrac, J.B., et al.: Flamingo: a visual language model for few-shot learning. In: NeurIPS (2022)","DOI":"10.52202\/068431-1723"},{"key":"14_CR3","doi-asserted-by":"crossref","unstructured":"Chen, B., et al.: LVAgent: long video understanding by multi-round dynamical collaboration of MLLM agents. arXiv (2025)","DOI":"10.1109\/ICCV51701.2025.01882"},{"key":"14_CR4","doi-asserted-by":"crossref","unstructured":"Chen, Z., et\u00a0al.: InternVL: scaling up vision foundation models and aligning for generic visual-linguistic tasks. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.02283"},{"key":"14_CR5","unstructured":"Clark, C., et al.: MOLMO2: open weights and data for vision-language models with video understanding and grounding (2026)"},{"key":"14_CR6","doi-asserted-by":"crossref","unstructured":"Fan, Y., et al.: VideoAgent: a memory-augmented multimodal agent for video understanding. In: ECCV (2024)","DOI":"10.1007\/978-3-031-72670-5_5"},{"key":"14_CR7","doi-asserted-by":"crossref","unstructured":"Feng, K., et al.: Video-R1: reinforcing video reasoning in MLLMS. arXiv (2025)","DOI":"10.52202\/085713-3310"},{"key":"14_CR8","doi-asserted-by":"crossref","unstructured":"Fu, C., et\u00a0al.: Video-MME: the first-ever comprehensive evaluation benchmark of multi-modal LLMS in video analysis. In: CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.02245"},{"key":"14_CR9","unstructured":"GLM, T., et\u00a0al.: ChatGLM: a family of large language models from GLM-130b to GLM-4 all tools. arXiv (2024)"},{"key":"14_CR10","unstructured":"Grauman, K., et\u00a0al.: EGO4D: around the world in 3,000 hours of egocentric video. In: CVPR (2022)"},{"key":"14_CR11","doi-asserted-by":"crossref","unstructured":"Hu, K., et al.: M-LLM based video frame selection for efficient video understanding. In: CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.01279"},{"key":"14_CR12","unstructured":"Jeoung, S., Huybrechts, G., Ganesh, B., Galstyan, A., Bodapati, S.: Adaptive video understanding agent: enhancing efficiency with dynamic frame sampling and feedback-driven reasoning (2024). arXiv"},{"key":"14_CR13","unstructured":"Kugo, N., et\u00a0al.: VideoMultiAgents: a multi-agent framework for video question answering. arXiv (2025)"},{"key":"14_CR14","unstructured":"Lei, J., Berg, T.L., Bansal, M.: Detecting moments and highlights in videos via natural language queries. In: NeurIPS (2021)"},{"key":"14_CR15","doi-asserted-by":"crossref","unstructured":"Li, K., et\u00a0al.: MVBench: a comprehensive multi-modal video understanding benchmark. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.02095"},{"key":"14_CR16","doi-asserted-by":"crossref","unstructured":"Lin, B., et al.: Video-LLAVA: learning united visual representation by alignment before projection. In: EMNLP (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"14_CR17","volume-title":"VideoXUM: cross-modal visual and textural summarization of videos","author":"J Lin","year":"2023","unstructured":"Lin, J., et al.: VideoXUM: cross-modal visual and textural summarization of videos. IEEE Trans, Multimed (2023)"},{"key":"14_CR18","unstructured":"Liu, Y., Lin, K.Q., Chen, C.W., Shou, M.Z.: VideoMind: a chain-of-lora agent for long video reasoning. arXiv (2025)"},{"key":"14_CR19","unstructured":"Liu, Y., Cao, M., Shi, X., Liang, X.: Colt: enhancing video large language models with continual tool usage. arXiv (2026)"},{"key":"14_CR20","doi-asserted-by":"crossref","unstructured":"Ma, Z., et al.: DRvideo: document retrieval based long video understanding. In: CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.01764"},{"key":"14_CR21","doi-asserted-by":"crossref","unstructured":"Maaz, M., Rasheed, H., Khan, S., Khan, F.: Video-ChatGPT: towards detailed video understanding via large vision and language models. In: ACL (2024)","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"14_CR22","doi-asserted-by":"crossref","unstructured":"Mangalam, K., Akshulakov, R., Malik, J.: EgoSchema: a diagnostic benchmark for very long-form video language understanding. In: NeurIPS (2023)","DOI":"10.52202\/075280-2004"},{"key":"14_CR23","doi-asserted-by":"crossref","unstructured":"Shinn, N., Cassano, F., Gopinath, A., Narasimhan, K., Yao, S.: Reflexion: language agents with verbal reinforcement learning. In: NeurIPS (2023)","DOI":"10.52202\/075280-0377"},{"key":"14_CR24","doi-asserted-by":"crossref","unstructured":"Shu, Y., et al.: Video-XL: extra-long vision language model for hour-scale video understanding. In: CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.02436"},{"key":"14_CR25","doi-asserted-by":"crossref","unstructured":"Tong, Z., Song, Y., Wang, J., Wang, L.: Videomae: masked autoencoders are data-efficient learners for self-supervised video pre-training. In: NeurIPS (2022)","DOI":"10.52202\/068431-0732"},{"key":"14_CR26","unstructured":"Wang, P., et\u00a0al.: Qwen2-VL: enhancing vision-language model\u2019s perception of the world at any resolution. arXiv (2024)"},{"key":"14_CR27","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: LVBench: an extreme long video understanding benchmark. In: ICCV (2025)","DOI":"10.1109\/ICCV51701.2025.02131"},{"key":"14_CR28","doi-asserted-by":"crossref","unstructured":"Wang, X., Zhang, Y., Zohar, O., Yeung-Levy, S.: VideoAgent: long-form video understanding with large language model as agent. In: ECCV (2024)","DOI":"10.1007\/978-3-031-72989-8_4"},{"key":"14_CR29","doi-asserted-by":"crossref","unstructured":"Wang, Z., et al.: Paxion: patching action knowledge in video-language foundation models. In: NeurIPS (2023)","DOI":"10.52202\/075280-0910"},{"key":"14_CR30","doi-asserted-by":"crossref","unstructured":"Wang, Z., et al.: VideoChat-a1: thinking with long videos by chain-of-shot reasoning. arXiv (2025)","DOI":"10.1609\/aaai.v40i13.38018"},{"key":"14_CR31","doi-asserted-by":"crossref","unstructured":"Weng, Y., Han, M., He, H., Chang, X., Zhuang, B.: LongVLM: efficient long video understanding via large language models. In: ECCV (2024)","DOI":"10.1007\/978-3-031-73414-4_26"},{"key":"14_CR32","unstructured":"Wu, B., Yu, S., Chen, Z., Tenenbaum, J.B., Gan, C.: Star: a benchmark for situated reasoning in real-world videos. arXiv (2024)"},{"key":"14_CR33","doi-asserted-by":"crossref","unstructured":"Wu, C.Y., Feichtenhofer, C., Fan, H., He, K., Krahenbuhl, P., Girshick, R.: Long-term feature banks for detailed video understanding. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00037"},{"key":"14_CR34","doi-asserted-by":"crossref","unstructured":"Wu, C.Y., Krahenbuhl, P.: Towards long-form video understanding. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00192"},{"key":"14_CR35","doi-asserted-by":"crossref","unstructured":"Xiao, J., Shang, X., Yao, A., Chua, T.S.: Next-QA: next phase of question-answering to explaining temporal actions. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00965"},{"key":"14_CR36","doi-asserted-by":"crossref","unstructured":"Xiao, J., Yao, A., Li, Y., Chua, T.S.: Can i trust your answer? Visually grounded video question answering. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.01254"},{"key":"14_CR37","unstructured":"Xie, Y., Chen, T., Ge, Z., Ni, L.: Video-MTR: reinforced multi-turn reasoning for long video understanding. arXiv (2025)"},{"key":"14_CR38","unstructured":"Xu, Z., Zhang, J., Wang, Q., Liu, Y.: E-VRAG: enhancing long video understanding with resource-efficient retrieval augmented generation. arXiv (2025)"},{"key":"14_CR39","unstructured":"Xue, Z., et al.: SimpleTIR: end-to-end reinforcement learning for multi-turn tool-integrated reasoning. arXiv (2025)"},{"key":"14_CR40","unstructured":"Xue, Z., et al.: Omni-adavideorag: omni-contextual adaptive retrieval-augmented for efficient long video understanding. arXiv (2025)"},{"key":"14_CR41","unstructured":"Yang, Z., et al.: LongVT: incentivizing \u201cthinking with long videos\u201d via native tool calling (2025)"},{"key":"14_CR42","unstructured":"Yao, S., et al.: React: synergizing reasoning and acting in language models. In: ICLR (2022)"},{"key":"14_CR43","unstructured":"Yi, K., et al.: CLEVRER: collision events for video representation and reasoning. arXiv (2019)"},{"key":"14_CR44","doi-asserted-by":"crossref","unstructured":"Zhang, H., Li, X., Bing, L.: Video-llama: an instruction-tuned audio-visual language model for video understanding. arXiv (2023)","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"14_CR45","unstructured":"Zhang, Y.F., et\u00a0al.: Thyme: think beyond images. arXiv (2025)"},{"key":"14_CR46","doi-asserted-by":"crossref","unstructured":"Zheng, Y., et al.: LlamaFactory: unified efficient fine-tuning of 100+ language models. arXiv (2024)","DOI":"10.18653\/v1\/2024.acl-demos.38"},{"key":"14_CR47","unstructured":"Zheng, Z., et al.: DeepEyes: incentivizing \u201cthinking with images\u201d via reinforcement learning. arXiv (2025)"},{"key":"14_CR48","unstructured":"Zhong, Y., Hu, Z.Y., Li, Y., Wang, L.: Rethinking chain-of-thought reasoning for videos. Arxiv (2025)"}],"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\/978-3-032-37255-0_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T07:46:35Z","timestamp":1789371995000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37255-0_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032372543","9783032372550"],"references-count":48,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37255-0_14","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":"15 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"}}]}}