{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T13:12:15Z","timestamp":1783775535063,"version":"3.55.0"},"publisher-location":"Singapore","reference-count":22,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819228546","type":"print"},{"value":"9789819228522","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,7,12]],"date-time":"2026-07-12T00:00:00Z","timestamp":1783814400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,12]],"date-time":"2026-07-12T00:00:00Z","timestamp":1783814400000},"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":[[2027]]},"DOI":"10.1007\/978-981-92-2852-2_48","type":"book-chapter","created":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T12:29:04Z","timestamp":1783772944000},"page":"649-660","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["VTool: Benchmarking Tool Use Ability in\u00a0Multi-modal Context"],"prefix":"10.1007","author":[{"given":"Yicheng","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhi","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tao","family":"Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yue","family":"Deng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yin","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,12]]},"reference":[{"key":"48_CR1","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., et al.: Others: language models are few-shot learners. Advances in Neural Information Processing Systems (NeurIPS) 33, 1877\u20131901 (2020)","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"48_CR2","doi-asserted-by":"publisher","unstructured":"Dong, Y., Jiang, X., Jin, Z., Li, G.: Self-collaboration code generation via ChatGPT. ACM Trans. Softw. Eng. Methodol. 3672459 (2024). https:\/\/doi.org\/10.1145\/3672459","DOI":"10.1145\/3672459"},{"key":"48_CR3","doi-asserted-by":"publisher","unstructured":"Gupta, T., Kembhavi, A.: Visual programming: compositional visual reasoning without training. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023, Vancouver, BC, Canada, June 17-24, 2023, pp. 14953\u201314962. IEEE (2023). https:\/\/doi.org\/10.1109\/CVPR52729.2023.01436","DOI":"10.1109\/CVPR52729.2023.01436"},{"key":"48_CR4","unstructured":"Han, X., et al.: InfiMM-Eval: Complex Open-ended Reasoning Evaluation for Multi-modal Large Language Models (2023)"},{"key":"48_CR5","unstructured":"Huang, Y., et alL.: MetaTool benchmark for large language models: deciding whether to use tools and which to use. In: Proceedings of the Twelfth International Conference on Learning Representations (2023)"},{"key":"48_CR6","doi-asserted-by":"publisher","unstructured":"Li, B., Ge, Y., Chen, Y., Ge, Y., Zhang, R., Shan, Y.: Seed-bench-2-plus: benchmarking multimodal large language models with text-rich visual comprehension. CoRR abs\/2404.16790 (2024). https:\/\/doi.org\/10.48550\/ARXIV.2404.16790","DOI":"10.48550\/ARXIV.2404.16790"},{"key":"48_CR7","doi-asserted-by":"publisher","unstructured":"Li, M., et al.: API-bank: a comprehensive benchmark for tool-augmented LLMs. In: Bouamor, H., Pino, J., Bali, K., (eds.) Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, EMNLP 2023, Singapore, December 6-10, 2023, pp. 3102\u20133116. Association for Computational Linguistics (2023). https:\/\/doi.org\/10.18653\/V1\/2023.EMNLP-MAIN.187","DOI":"10.18653\/V1\/2023.EMNLP-MAIN.187"},{"key":"48_CR8","doi-asserted-by":"publisher","unstructured":"Liu, J., Xia, C.S., Wang, Y., Zhang, L.: Is your code generated by ChatGPT really correct? Rigorous evaluation of large language models for code generation. CoRR (2023). https:\/\/doi.org\/10.48550\/ARXIV.2305.01210","DOI":"10.48550\/ARXIV.2305.01210"},{"key":"48_CR9","unstructured":"Lu, P., et al.: Mathvista: evaluating mathematical reasoning of foundation models in visual contexts. In: Proceedings of the Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024. OpenReview.net (2024). https:\/\/openreview.net\/forum?id=KUNzEQMWU7"},{"key":"48_CR10","unstructured":"Lu, P., et al.: Chameleon: plug-and-play compositional reasoning with large language models. In: Oh, A., et al., (eds.) Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023 (2023). http:\/\/papers.nips.cc\/paper_files\/paper\/2023\/hash\/871ed095b734818cfba48db6aeb25a62-Abstract-Conference.html"},{"key":"48_CR11","doi-asserted-by":"publisher","unstructured":"Lu, P., Qiu, L., Yu, W., Welleck, S., Chang, K.: A survey of deep learning for mathematical reasoning. In: Rogers, A., Boyd-Graber, J.L., Okazaki, N., (eds.) Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2023, Toronto, Canada, July 9-14, 2023, pp. 14605\u201314631. Association for Computational Linguistics (2023). https:\/\/doi.org\/10.18653\/V1\/2023.ACL-LONG.817","DOI":"10.18653\/V1\/2023.ACL-LONG.817"},{"key":"48_CR12","doi-asserted-by":"crossref","unstructured":"Ma, Z., Huang, W., Zhang, J., Gupta, T., Krishna, R.: M&m\u2019s: A Benchmark to Evaluate Tool-Use for Multi-step Multi-modal Tasks (2024)","DOI":"10.1007\/978-3-031-72684-2_2"},{"key":"48_CR13","doi-asserted-by":"publisher","unstructured":"OpenAI: GPT-4 Technical Report (2024). https:\/\/doi.org\/10.48550\/arxiv.2303.08774","DOI":"10.48550\/arxiv.2303.08774"},{"key":"48_CR14","doi-asserted-by":"publisher","unstructured":"Patil, S.G., Zhang, T., Wang, X., Gonzalez, J.E.: Gorilla: large language model connected with massive APIs. CoRR abs\/2305.15334 (2023). https:\/\/doi.org\/10.48550\/ARXIV.2305.15334","DOI":"10.48550\/ARXIV.2305.15334"},{"key":"48_CR15","doi-asserted-by":"publisher","unstructured":"Qin, Y., et al.: Tool learning with foundation models. CoRR abs\/2304.08354 (2023). https:\/\/doi.org\/10.48550\/arXiv.2304.08354","DOI":"10.48550\/arXiv.2304.08354"},{"key":"48_CR16","unstructured":"Qin, Y., et al.: ToolLLM: facilitating large language models to master 16000+ real-world APIs. In: Proceedings of the Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024. OpenReview.net (2024). https:\/\/openreview.net\/forum?id=dHng2O0Jjr"},{"issue":"7995","key":"48_CR17","doi-asserted-by":"publisher","first-page":"468","DOI":"10.1038\/s41586-023-06924-6","volume":"625","author":"B Romera-Paredes","year":"2024","unstructured":"Romera-Paredes, B., et al.: Mathematical discoveries from program search with large language models. Nature 625(7995), 468\u2013475 (2024). https:\/\/doi.org\/10.1038\/s41586-023-06924-6","journal-title":"Nature"},{"key":"48_CR18","unstructured":"Shen, Y., et al.: HuggingGPT: solving AI tasks with ChatGPT and its friends in hugging face. In: Oh, A., et al., (eds.) Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023 (2023). http:\/\/papers.nips.cc\/paper_files\/paper\/2023\/hash\/77c33e6a367922d003ff102ffb92b658-Abstract-Conference.html"},{"key":"48_CR19","doi-asserted-by":"publisher","unstructured":"Song, Y., et al.: RestGPT: connecting large language models with real-world applications via restful APIs. CoRR abs\/2306.06624 (2023). https:\/\/doi.org\/10.48550\/arXiv.2306.06624","DOI":"10.48550\/arXiv.2306.06624"},{"key":"48_CR20","doi-asserted-by":"publisher","unstructured":"Sur\u00eds, D., Menon, S., Vondrick, C.: Vipergpt: visual inference via python execution for reasoning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, ICCV 2023, Paris, France, October 1-6, 2023, pp. 11854\u201311864. IEEE (2023). https:\/\/doi.org\/10.1109\/ICCV51070.2023.01092","DOI":"10.1109\/ICCV51070.2023.01092"},{"key":"48_CR21","doi-asserted-by":"publisher","unstructured":"Touvron, H., et al.: Llama: Open and Efficient Foundation Language Models (2023). https:\/\/doi.org\/10.48550\/arXiv.2302.13971","DOI":"10.48550\/arXiv.2302.13971"},{"key":"48_CR22","doi-asserted-by":"publisher","unstructured":"Wang, C., et al.: MLLM-tool: a multimodal large language model for tool agent learning. CoRR abs\/2401.10727 (2024). https:\/\/doi.org\/10.48550\/arXiv.2401.10727","DOI":"10.48550\/arXiv.2401.10727"}],"container-title":["Lecture Notes in Computer Science","Knowledge Science, Engineering and Management"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-92-2852-2_48","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T12:29:15Z","timestamp":1783772955000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-2852-2_48"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,12]]},"ISBN":["9789819228546","9789819228522"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-2852-2_48","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,12]]},"assertion":[{"value":"12 July 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"KSEM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Knowledge Science, Engineering and Management","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Beijing","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"17 July 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 July 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":"ksem2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ksem2026.rosc.org.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}