{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,26]],"date-time":"2026-10-26T03:34:39Z","timestamp":1792985679733,"version":"4.5.0"},"publisher-location":"New York, NY, USA","reference-count":54,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,8,8]],"date-time":"2026-08-08T00:00:00Z","timestamp":1786147200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"National Natural Science Foundation of China","award":["U22B2060, 62276279, 62506075"],"award-info":[{"award-number":["U22B2060, 62276279, 62506075"]}]},{"name":"Key-Area Research and Development Program of Guangdong Province","award":["2024B0101050005, 2026B0101100004"],"award-info":[{"award-number":["2024B0101050005, 2026B0101100004"]}]},{"name":"Research Foundation of Science and Technology Plan Project of Guangzhou City","award":["2023B01J0001, 2024B01W0004"],"award-info":[{"award-number":["2023B01J0001, 2024B01W0004"]}]},{"name":"Guangdong Basic and Applied Basic Research Foundation","award":["2024B1515020032"],"award-info":[{"award-number":["2024B1515020032"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,9]]},"DOI":"10.1145\/3770855.3817763","type":"proceedings-article","created":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T17:15:37Z","timestamp":1786036537000},"page":"4592-4603","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["<i>SAKE:<\/i>\n                    Self-aware Knowledge Exploitation-Exploration for Grounded Multimodal Named Entity Recognition"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-8648-516X","authenticated-orcid":false,"given":"Jielong","family":"Tang","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, Sun Yat-Sen University, Zhuhai, China and Key Laboratory of Intelligent Assessment Technology for Sustainable Tourism, Zhuhai, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-2395-2802","authenticated-orcid":false,"given":"Xujie","family":"Yuan","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Sun Yat-Sen University, Zhuhai, China and Key Laboratory of Intelligent Assessment Technology for Sustainable Tourism, Zhuhai, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-6218-7631","authenticated-orcid":false,"given":"Jiayang","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Sun Yat-Sen University, Zhuhai, China and Key Laboratory of Intelligent Assessment Technology for Sustainable Tourism, Zhuhai, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1340-3995","authenticated-orcid":false,"given":"Jianxing","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Sun Yat-Sen University, Zhuhai, China and Key Laboratory of Intelligent Assessment Technology for Sustainable Tourism, Zhuhai, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9519-612X","authenticated-orcid":false,"given":"Xiao","family":"Dong","sequence":"additional","affiliation":[{"name":"School of Computer and Artificial Intelligence, Shandong Normal University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3081-6966","authenticated-orcid":false,"given":"Lin","family":"Chen","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-3750-9662","authenticated-orcid":false,"given":"Yunlai","family":"Teng","sequence":"additional","affiliation":[{"name":"China Mobile Jiutian Artificial Intelligence Technology (Beijing) Co., Ltd., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7394-0082","authenticated-orcid":false,"given":"Shimin","family":"Di","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1214-5384","authenticated-orcid":false,"given":"Jian","family":"Yin","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Sun Yat-Sen University, Zhuhai, China and Key Laboratory of Intelligent Assessment Technology for Sustainable Tourism, Zhuhai, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,8,8]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Shuai Bai Keqin Chen Xuejing Liu Jialin Wang Wenbin Ge Sibo Song Kai Dang Peng Wang Shijie Wang Jun Tang et al. 2025. Qwen2. 5-vl technical report. arXiv preprint arXiv:2502.13923 (2025)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","unstructured":"Mingyang Chen Linzhuang Sun Tianpeng Li Haoze Sun Yijie Zhou Chenzheng Zhu Haofen Wang Jeff Z Pan Wen Zhang Huajun Chen et al. 2025. Learning to reason with search for llms via reinforcement learning. arXiv preprint arXiv:2503.19470 (2025).","DOI":"10.52202\/085713-2858"},{"key":"e_1_3_2_1_3_1","unstructured":"Gheorghe Comanici Eric Bieber Mike Schaekermann Ice Pasupat Noveen Sachdeva Inderjit Dhillon Marcel Blistein Ori Ram Dan Zhang Evan Rosen et al. 2025. Gemini 2.5: Pushing the frontier with advanced reasoning multimodality long context and next generation agentic capabilities. arXiv preprint arXiv:2507.06261 (2025)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"e_1_3_2_1_5_1","unstructured":"Daya Guo Dejian Yang Haowei Zhang Junxiao Song Ruoyu Zhang Runxin Xu Qihao Zhu Shirong Ma Peiyi Wang Xiao Bi et al. 2025a. Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning. arXiv preprint arXiv:2501.12948 (2025)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.148"},{"key":"e_1_3_2_1_7_1","volume-title":"DeepEyesV2: Toward Agentic Multimodal Model. arXiv preprint arXiv:2511.05271","author":"Hong Jack","year":"2025","unstructured":"Jack Hong, Chenxiao Zhao, ChengLin Zhu, Weiheng Lu, Guohai Xu, and Xing Yu. 2025. DeepEyesV2: Toward Agentic Multimodal Model. arXiv preprint arXiv:2511.05271 (2025)."},{"key":"e_1_3_2_1_8_1","unstructured":"Aaron Hurst Adam Lerer Adam P Goucher Adam Perelman Aditya Ramesh Aidan Clark AJ Ostrow Akila Welihinda Alan Hayes Alec Radford et al. 2024. Gpt-4o system card. arXiv preprint arXiv:2410.21276 (2024)."},{"key":"e_1_3_2_1_9_1","unstructured":"Aaron Jaech Adam Kalai Adam Lerer Adam Richardson Ahmed El-Kishky Aiden Low Alec Helyar Aleksander Madry Alex Beutel Alex Carney et al. 2024. Openai o1 system card. arXiv preprint arXiv:2412.16720 (2024)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.123"},{"key":"e_1_3_2_1_11_1","volume-title":"Search-r1: Training llms to reason and leverage search engines with reinforcement learning. arXiv preprint arXiv:2503.09516","author":"Jin Bowen","year":"2025","unstructured":"Bowen Jin, Hansi Zeng, Zhenrui Yue, Jinsung Yoon, Sercan Arik, Dong Wang, Hamed Zamani, and Jiawei Han. 2025. Search-r1: Training llms to reason and leverage search engines with reinforcement learning. arXiv preprint arXiv:2503.09516 (2025)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.1239"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.184"},{"key":"e_1_3_2_1_14_1","volume-title":"LLMs as Bridges: Reformulating Grounded Multimodal Named Entity Recognition. arXiv preprint arXiv:2402.09989","author":"Li Jinyuan","year":"2024","unstructured":"Jinyuan Li, Han Li, Di Sun, Jiahao Wang, Wenkun Zhang, Zan Wang, and Gang Pan. 2024b. LLMs as Bridges: Reformulating Grounded Multimodal Named Entity Recognition. arXiv preprint arXiv:2402.09989 (2024)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671769"},{"key":"e_1_3_2_1_16_1","volume-title":"Search-o1: Agentic search-enhanced large reasoning models. arXiv preprint arXiv:2501.05366","author":"Li Xiaoxi","year":"2025","unstructured":"Xiaoxi Li, Guanting Dong, Jiajie Jin, Yuyao Zhang, Yujia Zhou, Yutao Zhu, Peitian Zhang, and Zhicheng Dou. 2025a. Search-o1: Agentic search-enhanced large reasoning models. arXiv preprint arXiv:2501.05366 (2025)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681598"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.emnlp-main.311"},{"key":"e_1_3_2_1_19_1","volume-title":"Visual instruction tuning. Advances in neural information processing systems","author":"Liu Haotian","year":"2023","unstructured":"Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2023a. Visual instruction tuning. Advances in neural information processing systems, Vol. 36 (2023), 34892-34916."},{"key":"e_1_3_2_1_20_1","volume-title":"Tonghan Wang, Carl Kingsford, and Vincent Conitzer.","author":"Liu Jiayuan","year":"2026","unstructured":"Jiayuan Liu, Tianqin Li, Shiyi Du, Xin Luo, Haoxuan Zeng, Emanuel Tewolde, Tai Sing Lee, Tonghan Wang, Carl Kingsford, and Vincent Conitzer. 2026. The Memory Curse: How Expanded Recall Erodes Cooperative Intent in LLM Agents. arXiv preprint arXiv:2605.08060 (2026)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.3233\/FAIA240802"},{"key":"e_1_3_2_1_22_1","unstructured":"Shilong Liu Zhaoyang Zeng Tianhe Ren Feng Li Hao Zhang Jie Yang Chunyuan Li Jianwei Yang Hang Su Jun Zhu et al. 2023b. Grounding dino: Marrying dino with grounded pre-training for open-set object detection. arXiv preprint arXiv:2303.05499 (2023)."},{"key":"e_1_3_2_1_23_1","volume-title":"Rosenblum","author":"Liu Ye","year":"2019","unstructured":"Ye Liu, Hui Li, Alberto Garcia-Duran, Mathias Niepert, Daniel Onoro-Rubio, and David S. Rosenblum. 2019. MMKG: Multi-modal Knowledge Graphs. In The Semantic Web. Springer International Publishing, Cham, 459-474."},{"key":"e_1_3_2_1_24_1","first-page":"1990","article-title":"Visual Attention Model for Name Tagging in Multimodal Social Media","author":"Lu Di","year":"2018","unstructured":"Di Lu, Leonardo Neves, Vitor Carvalho, Ning Zhang, and Heng Ji. 2018. Visual Attention Model for Name Tagging in Multimodal Social Media. In ACL. 1990-1999.","journal-title":"ACL."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2019"},{"key":"e_1_3_2_1_26_1","volume-title":"Rethinking the role of demonstrations: What makes in-context learning work? arXiv preprint arXiv:2202.12837","author":"Min Sewon","year":"2022","unstructured":"Sewon Min, Xinxi Lyu, Ari Holtzman, Mikel Artetxe, Mike Lewis, Hannaneh Hajishirzi, and Luke Zettlemoyer. 2022. Rethinking the role of demonstrations: What makes in-context learning work? arXiv preprint arXiv:2202.12837 (2022)."},{"key":"e_1_3_2_1_27_1","volume-title":"SCANNER: Knowledge-Enhanced Approach for Robust Multi-modal Named Entity Recognition of Unseen Entities. arXiv preprint arXiv:2404.01914","author":"Ok Hyunjong","year":"2024","unstructured":"Hyunjong Ok, Taeho Kil, Sukmin Seo, and Jaeho Lee. 2024. SCANNER: Knowledge-Enhanced Approach for Robust Multi-modal Named Entity Recognition of Unseen Entities. arXiv preprint arXiv:2404.01914 (2024)."},{"key":"e_1_3_2_1_28_1","volume-title":"Deepseekmath: Pushing the limits of mathematical reasoning in open language models. arXiv preprint arXiv:2402.03300","author":"Shao Zhihong","year":"2024","unstructured":"Zhihong Shao, Peiyi Wang, Qihao Zhu, Runxin Xu, Junxiao Song, Xiao Bi, Haowei Zhang, Mingchuan Zhang, YK Li, Yang Wu, et al., 2024. Deepseekmath: Pushing the limits of mathematical reasoning in open language models. arXiv preprint arXiv:2402.03300 (2024)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3689031.3696075"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i24.34711"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.emnlp-main.388"},{"key":"e_1_3_2_1_32_1","unstructured":"Yicheng Tao Yuanhao Huang Yiqun Wang Xin Luo and Jie Liu. 2025. AutoPCR: Automated Phenotype Concept Recognition by Prompting. In arXiv preprint arXiv:2507.19315."},{"key":"e_1_3_2_1_33_1","unstructured":"Kimi Team Angang Du Bofei Gao Bowei Xing Changjiu Jiang Cheng Chen Cheng Li Chenjun Xiao Chenzhuang Du Chonghua Liao et al. 2025. Kimi k1. 5: Scaling reinforcement learning with llms. arXiv preprint arXiv:2501.12599 (2025)."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612322"},{"key":"e_1_3_2_1_35_1","volume-title":"International Conference on Machine Learning. PMLR, 23318-23340","author":"Wang Peng","year":"2022","unstructured":"Peng Wang, An Yang, Rui Men, Junyang Lin, Shuai Bai, Zhikang Li, Jianxin Ma, Chang Zhou, Jingren Zhou, and Hongxia Yang. 2022c. Ofa: Unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework. In International Conference on Machine Learning. PMLR, 23318-23340."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.437"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.232"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.183"},{"key":"e_1_3_2_1_39_1","volume-title":"Denny Zhou, et al.","author":"Wei Jason","year":"2022","unstructured":"Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, et al., 2022. Chain-of-thought prompting elicits reasoning in large language models. Advances in neural information processing systems, Vol. 35 (2022), 24824-24837."},{"key":"e_1_3_2_1_40_1","volume-title":"MMSearch-R1: Incentivizing LMMs to Search. arXiv preprint arXiv:2506.20670","author":"Wu Jinming","year":"2025","unstructured":"Jinming Wu, Zihao Deng, Wei Li, Yiding Liu, Bo You, Bo Li, Zejun Ma, and Ziwei Liu. 2025. MMSearch-R1: Incentivizing LMMs to Search. arXiv preprint arXiv:2506.20670 (2025)."},{"key":"e_1_3_2_1_41_1","volume-title":"React: Synergizing reasoning and acting in language models. In The eleventh international conference on learning representations.","author":"Yao Shunyu","year":"2022","unstructured":"Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik R Narasimhan, and Yuan Cao. 2022. React: Synergizing reasoning and acting in language models. In The eleventh international conference on learning representations."},{"key":"e_1_3_2_1_42_1","first-page":"3342","article-title":"Improving Multimodal Named Entity Recognition via Entity Span Detection with Unified Multimodal Transformer","author":"Yu Jianfei","year":"2020","unstructured":"Jianfei Yu, Jing Jiang, Li Yang, and Rui Xia. 2020. Improving Multimodal Named Entity Recognition via Entity Span Detection with Unified Multimodal Transformer. In ACL. 3342-3352.","journal-title":"ACL."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.508"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.1483"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLPRO.2026.3651977"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3770854.3780156"},{"key":"e_1_3_2_1_47_1","volume-title":"Database Systems for Advanced Applications, Hyungsoo Jung, Tianzheng Wang, Masashi Toyoda, Hyuk-Yoon Kwon, and Jae-woong Lee (Eds.)","author":"Yuan Xujie","unstructured":"Xujie Yuan, Yongxu Liu, Shimin Di, Shiwen Wu, Libin Zheng, Rui Meng, Lei Chen, Xiaofang Zhou, and Jian Yin. 2026 c. A Pilot Empirical Study on When and How to Use Knowledge Graphs as Retrieval Augmented Generation. In Database Systems for Advanced Applications, Hyungsoo Jung, Tianzheng Wang, Masashi Toyoda, Hyuk-Yoon Kwon, and Jae-woong Lee (Eds.). Springer Nature Singapore, Singapore, 471-488."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i16.17687"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11962"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i28.35383"},{"key":"e_1_3_2_1_52_1","volume-title":"Deepresearcher: Scaling deep research via reinforcement learning in real-world environments. arXiv preprint arXiv:2504.03160","author":"Zheng Yuxiang","year":"2025","unstructured":"Yuxiang Zheng, Dayuan Fu, Xiangkun Hu, Xiaojie Cai, Lyumanshan Ye, Pengrui Lu, and Pengfei Liu. 2025a. Deepresearcher: Scaling deep research via reinforcement learning in real-world environments. arXiv preprint arXiv:2504.03160 (2025)."},{"key":"e_1_3_2_1_53_1","volume-title":"DeepEyes: Incentivizing'' Thinking with Images'' via Reinforcement Learning. arXiv preprint arXiv:2505.14362","author":"Zheng Ziwei","year":"2025","unstructured":"Ziwei Zheng, Michael Yang, Jack Hong, Chenxiao Zhao, Guohai Xu, Le Yang, Chao Shen, and Xing Yu. 2025b. DeepEyes: Incentivizing'' Thinking with Images'' via Reinforcement Learning. arXiv preprint arXiv:2505.14362 (2025)."},{"key":"e_1_3_2_1_54_1","unstructured":"Yizhang Zhu Liangwei Wang Chenyu Yang Xiaotian Lin Boyan Li Wei Zhou Xinyu Liu Zhangyang Peng Tianqi Luo Yu Li et al. 2025. A Survey of Data Agents: Emerging Paradigm or Overstated Hype? arXiv preprint arXiv:2510.23587 (2025)."}],"event":{"name":"KDD '26: The 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Jeju Island Republic of Korea","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2"],"original-title":[],"deposited":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T01:24:29Z","timestamp":1786065869000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770855.3817763"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,8]]},"references-count":54,"alternative-id":["10.1145\/3770855.3817763","10.1145\/3770855"],"URL":"https:\/\/doi.org\/10.1145\/3770855.3817763","relation":{},"subject":[],"published":{"date-parts":[[2026,8,8]]},"assertion":[{"value":"2026-08-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}