{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T10:24:43Z","timestamp":1787653483735,"version":"build-2736575974"},"publisher-location":"Cham","reference-count":33,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032360229","type":"print"},{"value":"9783032360236","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T00:00:00Z","timestamp":1787702400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T00:00:00Z","timestamp":1787702400000},"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\/978-3-032-36023-6_20","type":"book-chapter","created":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T10:06:19Z","timestamp":1787652379000},"page":"341-358","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["CPAgent: A Tool-Augmented Agentic Framework for\u00a0Chart Parsing"],"prefix":"10.1007","author":[{"given":"Chen-Yu","family":"Xie","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiao-Hui","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Boran","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fei","family":"Yin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cheng-Lin","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,8,26]]},"reference":[{"issue":"7972","key":"20_CR1","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1038\/s41586-023-06221-2","volume":"620","author":"H Wang","year":"2023","unstructured":"Wang, H., et al.: Scientific discovery in the age of artificial intelligence. Nature 620(7972), 47\u201360 (2023)","journal-title":"Nature"},{"key":"20_CR2","unstructured":"Team, G., et al.: Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805 (2023)"},{"key":"20_CR3","doi-asserted-by":"publisher","first-page":"34892","DOI":"10.52202\/075280-1516","volume":"36","author":"H Liu","year":"2023","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. Adv. Neural. Inf. Process. Syst. 36, 34892\u201334916 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"20_CR4","unstructured":"Zhu, J., Wang, W., Chen, Z., Liu, Z., Ye, S.: InternVL3: exploring advanced training and test-time recipes for open-source multimodal models. arXiv preprint arXiv:2504.10479 (2025)"},{"key":"20_CR5","unstructured":"Bai, S., et\u00a0al.: Qwen3-VL technical report. arXiv preprint arXiv:2511.21631 (2025)"},{"key":"20_CR6","unstructured":"Xu, Z., Du, S., Qi, Y., Xu, C., Yuan, C., Guo, J.: ChartBench: a benchmark for complex visual reasoning in charts. arXiv preprint arXiv:2312.15915 (2023)"},{"key":"20_CR7","doi-asserted-by":"publisher","unstructured":"Yan, P., Ahmed, S., Doermann, D.: Context-aware chart element detection. In: International Conference on Document Analysis and Recognition. LNCS, vol. 14187, pp. 218\u2013233. Springer (2023). https:\/\/doi.org\/10.1007\/978-3-031-41676-7_13","DOI":"10.1007\/978-3-031-41676-7_13"},{"key":"20_CR8","doi-asserted-by":"crossref","unstructured":"Luo, J., Li, Z., Wang, J., Lin, C.Y.: ChartOCR: data extraction from charts images via a deep hybrid framework. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 1917\u20131925 (2021)","DOI":"10.1109\/WACV48630.2021.00196"},{"key":"20_CR9","doi-asserted-by":"crossref","unstructured":"Cheng, Z.Q., Dai, Q., Hauptmann, A.G.: ChartReader: a unified framework for chart derendering and comprehension without heuristic rules. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 22202\u201322213 (2023)","DOI":"10.1109\/ICCV51070.2023.02029"},{"key":"20_CR10","doi-asserted-by":"crossref","unstructured":"Liu, F., et al.: Matcha: enhancing visual language pretraining with math reasoning and chart derendering. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 12756\u201312770. Association for Computational Linguistics, Toronto, Canada (2023)","DOI":"10.18653\/v1\/2023.acl-long.714"},{"key":"20_CR11","doi-asserted-by":"crossref","unstructured":"Liu, F., et al.: DEPLOT: one-shot visual language reasoning by plot-to-table translation. In: Findings of the Association for Computational Linguistics: ACL 2023, pp. 10381\u201310399. Association for Computational Linguistics, Toronto, Canada (2023)","DOI":"10.18653\/v1\/2023.findings-acl.660"},{"key":"20_CR12","doi-asserted-by":"crossref","unstructured":"Masry, A., Kavehzadeh, P., Do, X.L., Hoque, E., Joty, S.: Unichart: a universal vision-language pretrained model for chart comprehension and reasoning. In: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pp. 14662\u201314684. Association for Computational Linguistics, Singapore (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.906"},{"key":"20_CR13","unstructured":"Yao, S., et al.: REACT: synergizing reasoning and acting in language models. In: International Conference on Learning Representations ICLR (2023)"},{"key":"20_CR14","doi-asserted-by":"publisher","first-page":"68539","DOI":"10.52202\/075280-2997","volume":"36","author":"T Schick","year":"2023","unstructured":"Schick, T., et al.: ToolFormer: language models can teach themselves to use tools. Adv. Neural. Inf. Process. Syst. 36, 68539\u201368551 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"20_CR15","unstructured":"Wang, B., et al.: ChartAgent: a chart understanding framework with tool integrated reasoning. arXiv preprint arXiv:2512.14040 (2025)"},{"key":"20_CR16","doi-asserted-by":"crossref","unstructured":"Kaur, R., Srishankar, N., Zeng, Z., Ganesh, S., Veloso, M.: ChartAgent: a multimodal agent for visually grounded reasoning in complex chart question answering. arXiv preprint arXiv:2510.04514 (2026)","DOI":"10.18653\/v1\/2026.acl-long.843"},{"key":"20_CR17","doi-asserted-by":"crossref","unstructured":"Masry, A., Long, D.X., Tan, J.Q., Joty, S., Hoque, E.: ChartQA: a benchmark for question answering about charts with visual and logical reasoning. In: Findings of the Association for Computational Linguistics: ACL 2022, pp. 2263\u20132279. Association for Computational Linguistics, Dublin, Ireland (2022)","DOI":"10.18653\/v1\/2022.findings-acl.177"},{"key":"20_CR18","doi-asserted-by":"crossref","unstructured":"Xie, C.Y., Li, X.H., Yin, F., Liu, C.L.: DeChart: a benchmark and text-enhanced chart-to-table conversion method with multimodal LLMs. In: 20th International Conference on Document Analysis and Recognition (ICDAR 2026). LNCS. Springer (2026)","DOI":"10.1007\/978-3-032-36033-5_32"},{"key":"20_CR19","doi-asserted-by":"crossref","unstructured":"Methani, N., Ganguly, P., Khapra, M.M., Kumar, P.: PLOTQA: reasoning over scientific plots. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 1527\u20131536 (2020)","DOI":"10.1109\/WACV45572.2020.9093523"},{"key":"20_CR20","doi-asserted-by":"crossref","unstructured":"Rane, C., Subramanya, S.M., Endluri, D.S., Wu, J., Giles, C.L.: ChartReader: automatic parsing of bar-plots. In: 2021 IEEE 22nd International Conference on Information Reuse and Integration for Data Science (IRI), pp. 318\u2013325. IEEE (2021)","DOI":"10.1109\/IRI51335.2021.00050"},{"key":"20_CR21","unstructured":"Xue, W., Chen, D., Yu, B., Chen, Y., Zhou, S., Peng, W.: ChartDETR: a multi-shape detection network for visual chart recognition. arXiv preprint arXiv:2308.07743 (2023)"},{"key":"20_CR22","doi-asserted-by":"crossref","unstructured":"Zhang, L., et al.: TinyChart: efficient chart understanding with program-of-thoughts learning and visual token merging. In: Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pp. 1882\u20131898. Association for Computational Linguistics, Miami, Florida, USA (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.112"},{"key":"20_CR23","unstructured":"Han, Y., et al.: ChartlLAMA: a multimodal LLM for chart understanding and generation. arXiv preprint arXiv:2311.16483 (2023)"},{"key":"20_CR24","doi-asserted-by":"crossref","unstructured":"Kim, W., Park, S., In, Y., Han, S., Park, C.: Simplot: enhancing chart question answering by distilling essentials. In: Findings of the Association for Computational Linguistics: NAACL 2025, pp. 573\u2013593. Association for Computational Linguistics, Albuquerque, New Mexico (2025)","DOI":"10.18653\/v1\/2025.findings-naacl.35"},{"key":"20_CR25","doi-asserted-by":"crossref","unstructured":"Masry, A., Shahmohammadi, M., Parvez, M.R., Hoque, E., Joty, S.: ChartinStruct: Instruction tuning for chart comprehension and reasoning. In: Findings of the Association for Computational Linguistics: ACL 2024, pp. 10387\u201310409. Association for Computational Linguistics, Bangkok, Thailand (2024)","DOI":"10.18653\/v1\/2024.findings-acl.619"},{"key":"20_CR26","unstructured":"Wu, Q., et al.: AutoGen: enabling next-gen LLM applications via multi-agent conversations. In: First Conference on Language Modeling (2024)"},{"key":"20_CR27","doi-asserted-by":"crossref","unstructured":"Huang, M., Zhang, L., Lai, H., Wu, W., Zhang, X., Liu, J.: VPROCHART: answering chart question through visual perception alignment agent and programmatic solution reasoning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a039, pp. 3689\u20133696 (2025)","DOI":"10.1609\/aaai.v39i4.32384"},{"key":"20_CR28","unstructured":"Cui, C., et\u00a0al.: PADDLEOCR 3.0 technical report. arXiv preprint arXiv:2507.05595 (2025)"},{"key":"20_CR29","unstructured":"Khanam, R., Hussain, M.: YOLOv11: an overview of the key architectural enhancements. arXiv preprint arXiv:2410.17725 (2024)"},{"key":"20_CR30","doi-asserted-by":"publisher","unstructured":"Newell, A., Yang, K., Deng, J.: Stacked hourglass networks for human pose estimation. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) European Conference on Computer Vision, pp. 483\u2013499. Springer (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_29","DOI":"10.1007\/978-3-319-46484-8_29"},{"key":"20_CR31","unstructured":"Cui, C., et\u00a0al.: PADDLEOCR-VL: boosting multilingual document parsing via a 0.9b ultra-compact vision-language model. arXiv preprint arXiv:2510.14528 (2025)"},{"key":"20_CR32","unstructured":"Masry, A., Thakkar, M., Bajaj, A., Kartha, A., Hoque, E., Joty, S.: Chartgemma: visual instruction-tuning for chart reasoning in the wild. In: Proceedings of the 31st International Conference on Computational Linguistics: Industry Track, pp. 625\u2013643 (2025)"},{"key":"20_CR33","doi-asserted-by":"crossref","unstructured":"Meng, F., et al.: ChartAssistant: a universal chart multimodal language model via chart-to-table pre-training and multitask instruction tuning. In: Findings of the Association for Computational Linguistics: ACL 2024, pp. 7775\u20137803. Association for Computational Linguistics, Bangkok, Thailand (2024)","DOI":"10.18653\/v1\/2024.findings-acl.463"}],"container-title":["Lecture Notes in Computer Science","Document Analysis and Recognition \u2013 ICDAR 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-36023-6_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T10:06:21Z","timestamp":1787652381000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-36023-6_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,26]]},"ISBN":["9783032360229","9783032360236"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-36023-6_20","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,26]]},"assertion":[{"value":"26 August 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICDAR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Document Analysis and Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vienna","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Austria","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":"31 August 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icdar2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icdar2026.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}