{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T16:40:41Z","timestamp":1786120841363,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":37,"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":"the National Key Research & Development Plan","award":["2023YFF0725100"],"award-info":[{"award-number":["2023YFF0725100"]}]},{"name":"the National Natural Science Foundation of China","award":["92570121, 62322214, U23A20299, U24B20144"],"award-info":[{"award-number":["92570121, 62322214, U23A20299, U24B20144"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,9]]},"DOI":"10.1145\/3770855.3817505","type":"proceedings-article","created":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T17:15:37Z","timestamp":1786036537000},"page":"10302-10313","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["SurveyReview: A Reviewer-Aligned Benchmark for Survey Evaluators"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-5664-968X","authenticated-orcid":false,"given":"Yuheng","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Information, Renmin University of China, Beijing, China and Key Laboratory of Data Engineering and Knowledge Engineering, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-3708-1381","authenticated-orcid":false,"given":"Yuanchun","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Information, Renmin University of China, Beijing, China and Key Laboratory of Data Engineering and Knowledge Engineering, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8551-1966","authenticated-orcid":false,"given":"Fanjin","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Information, Renmin University of China, Beijing, China and Engineering Research Center of Database and Business Intelligence, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9426-4911","authenticated-orcid":false,"given":"Ruyu","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Information, Renmin University of China, Beijing, China and Key Laboratory of Data Engineering and Knowledge Engineering, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6244-0664","authenticated-orcid":false,"given":"Juanzi","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3487-4593","authenticated-orcid":false,"given":"Jie","family":"Tang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2019-225X","authenticated-orcid":false,"given":"Jing","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Information, Renmin University of China, Beijing, China and Engineering Research Center of Database and Business Intelligence, Beijing, 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":"2008-2026. GROBID. https:\/\/github.com\/kermitt2\/grobid.swh:1:dir:dab86b296e3c3216e2241968f0d63b68e8209d3c"},{"key":"e_1_3_2_1_2_1","unstructured":"Aradhye Agarwal Ayan Sengupta and Tanmoy Chakraborty. 2025. The Art of Scaling Test-Time Compute for Large Language Models. arXiv:2512.02008 [cs.CL] https:\/\/arxiv.org\/abs\/2512.02008"},{"key":"e_1_3_2_1_3_1","unstructured":"Anthropic. 2025. Introducing Claude Opus 4.5. https:\/\/www.anthropic.com\/news\/claude-opus-4-5"},{"key":"e_1_3_2_1_4_1","unstructured":"Jing Chen Zhiheng Yang Yixian Shen Jie Liu Adam Belloum Chrysa Papagainni and Paola Grosso. 2025. SurveyGen-I: Consistent Scientific Survey Generation with Evolving Plans and Memory-Guided Writing. arXiv:2508.14317 [cs.CL] https:\/\/arxiv.org\/abs\/2508.14317"},{"key":"e_1_3_2_1_5_1","unstructured":"DeepSeek-AI. 2025. DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models. arXiv:2512.02556 [cs.CL] https:\/\/arxiv.org\/abs\/2512.02556"},{"key":"e_1_3_2_1_6_1","unstructured":"Mingxuan Du Benfeng Xu Chiwei Zhu XiaoruiWang and Zhendong Mao. 2025. DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents. arXiv:2506.11763 [cs.CL] https:\/\/arxiv.org\/abs\/2506.11763"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"crossref","unstructured":"Kehua Feng Keyan Ding Hongzhi Tan Kede Ma ZhihuaWang Shuangquan Guo Yuzhou Cheng Ge Sun Guozhou Zheng Qiang Zhang and Huajun Chen. 2025. Sample-Efficient Human Evaluation of Large Language Models via Maximum Discrepancy Competition. arXiv:2404.08008 [cs.LG] https:\/\/arxiv.org\/abs\/2404.8008","DOI":"10.18653\/v1\/2025.acl-long.535"},{"key":"e_1_3_2_1_8_1","unstructured":"Google DeepMind. 2025. Gemini 3 Pro Model Card. https:\/\/deepmind.google\/models\/model-cards\/gemini-3-pro\/"},{"key":"e_1_3_2_1_9_1","unstructured":"Edward J. Hu Yelong Shen Phillip Wallis Zeyuan Allen-Zhu Yuanzhi Li Shean Wang Lu Wang and Weizhu Chen. 2021. LoRA: Low-Rank Adaptation of Large Language Models. arXiv:2106.09685 [cs.CL] https:\/\/arxiv.org\/abs\/2106.09685"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"crossref","unstructured":"Aleksi Huotala Miikka Kuutila Olli-Pekka Turtio and Mika M\u00e4ntyl\u00e4. 2025. AISysRev - LLM-based Tool for Title-abstract Screening. arXiv:2510.06708 [cs.SE] https:\/\/arxiv.org\/abs\/2510.06708","DOI":"10.1145\/3803437.3806408"},{"key":"e_1_3_2_1_11_1","unstructured":"Minghao Li Ying Zeng Zhihao Cheng Cong Ma and Kai Jia. 2025. ReportBench: Evaluating Deep Research Agents via Academic Survey Tasks. arXiv:2508.15804 [cs.CL] https:\/\/arxiv.org\/abs\/2508.15804"},{"key":"e_1_3_2_1_12_1","unstructured":"Xun Liang Jiawei Yang YezhaohuiWang Chen Tang Zifan Zheng Shichao Song Zehao Lin Yebin Yang Simin Niu Hanyu Wang Bo Tang Feiyu Xiong Keming Mao and Zhiyu li. 2025. SurveyX: Academic Survey Automation via Large Language Models. arXiv:2502.14776 [cs.CL] https:\/\/arxiv.org\/abs\/2502.14776"},{"key":"e_1_3_2_1_13_1","volume-title":"ROUGE: A Package for Automatic Evaluation of Summaries. In Text Summarization Branches Out","author":"Lin Chin-Yew","year":"2004","unstructured":"Chin-Yew Lin. 2004. ROUGE: A Package for Automatic Evaluation of Summaries. In Text Summarization Branches Out. Association for Computational Linguistics, Barcelona, Spain, 74-81. https:\/\/aclanthology.org\/W04-1013\/"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-023-08891-5"},{"key":"e_1_3_2_1_15_1","unstructured":"OpenAI. 2025. Introducing GPT-5.2. https:\/\/openai.com\/index\/introducing-gpt-5-2\/"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"e_1_3_2_1_17_1","unstructured":"Vik Paruchuri. 2025. Marker. https:\/\/github.com\/VikParuchuri\/marker. GitHub repository."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"crossref","unstructured":"Rafael Rafailov Archit Sharma Eric Mitchell Stefano Ermon Christopher D. Manning and Chelsea Finn. 2024. Direct Preference Optimization: Your Language Model is Secretly a Reward Model. arXiv:2305.18290 [cs.LG] https:\/\/arxiv.org\/abs\/2305.18290","DOI":"10.52202\/075280-2338"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"crossref","unstructured":"Patr\u00edcia Schmidtov\u00e1 Saad Mahamood Simone Balloccu Ond\u0159ej Du\u0161ek Albert Gatt Dimitra Gkatzia David M. Howcroft Ond\u0159ej Pl\u00e1tek and Adarsa Sivaprasad. 2024. Automatic Metrics in Natural Language Generation: A Survey of Current Evaluation Practices. arXiv:2408.09169 [cs.CL] https:\/\/arxiv.org\/abs\/2408.09169","DOI":"10.18653\/v1\/2024.inlg-main.44"},{"key":"e_1_3_2_1_20_1","unstructured":"Xiaofeng Shi Qian Kou Yuduo Li Ning Tang Jinxin Xie Longbin Yu Songjing Wang and Hua Zhou. 2025. SciSage: A Multi-Agent Framework for High-Quality Scientific Survey Generation. arXiv:2506.12689 [cs.AI] https:\/\/arxiv.org\/abs\/2506.12689"},{"key":"e_1_3_2_1_21_1","unstructured":"Weihang Su Anzhe Xie Qingyao Ai Jianming Long Xuanyi Chen Jiaxin Mao Ziyi Ye and Yiqun Liu. 2026. SurGE: A Benchmark and Evaluation Framework for Scientific Survey Generation. arXiv:2508.15658 [cs.CL] https:\/\/arxiv.org\/abs\/2508.15658"},{"key":"e_1_3_2_1_22_1","unstructured":"Hao Sun Yunyi Shen and Mihaela van der Schaar. 2025. OpenReview Should be Protected and Leveraged as a Community Asset for Research in the Era of Large Language Models. arXiv:2505.21537 [cs.CY] https:\/\/arxiv.org\/abs\/2505.21537"},{"key":"e_1_3_2_1_23_1","unstructured":"Zhaojun Sun Xuzhou Zhu Xuanhe Zhou Xin Tong ShuoWang Jie Fu Guoliang Li Zhiyuan Liu and Fan Wu. 2025. SurveyBench: Can LLM(-Agents) Write Academic Surveys that Align with Reader Needs? arXiv:2510.03120 [cs.CL] https:\/\/arxiv.org\/abs\/2510.03120"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/2835776.2835849"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"crossref","unstructured":"Mike Thelwall Verena Weigert Liz Allen Zena Nyakoojo and Eleanor-Rose Papas. 2019. Does the use of open non-anonymous peer review in scholarly publishing introduce bias? Evidence from the F1000 post-publication open peer review publishing model. arXiv:1911.03379 [cs.DL] https:\/\/arxiv.org\/abs\/1911.03379","DOI":"10.1177\/0165551520938678"},{"key":"e_1_3_2_1_26_1","unstructured":"HaoyuWang Yujia Fu Zhu Zhang Shuo Wang Zirui Ren XiaorongWang Zhili Li Chaoqun He Bo An Zhiyuan Liu and Maosong Sun. 2025. LLM\u00d7MapReduce- V2: Entropy-Driven Convolutional Test-Time Scaling for Generating Long-Form Articles from Extremely Long Resources. arXiv:2504.05732 [cs.CL] https:\/\/arxiv.org\/abs\/2504.05732"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"crossref","unstructured":"YidongWang Qi Guo Wenjin Yao Hongbo Zhang Xin Zhang ZhenWu Meishan Zhang Xinyu Dai Min Zhang Qingsong Wen Wei Ye Shikun Zhang and Yue Zhang. 2024. AutoSurvey: Large Language Models Can Automatically Write Surveys. arXiv:2406.10252 [cs.IR] https:\/\/arxiv.org\/abs\/2406.10252","DOI":"10.52202\/079017-3655"},{"key":"e_1_3_2_1_28_1","unstructured":"YixuanWeng Minjun Zhu Guangsheng Bao Hongbo Zhang JindongWang Yue Zhang and Linyi Yang. 2025. CycleResearcher: Improving Automated Research via Automated Review. arXiv:2411.00816 [cs.CL] https:\/\/arxiv.org\/abs\/2411.00816"},{"key":"e_1_3_2_1_29_1","unstructured":"An Yang Anfeng Li Baosong Yang Beichen Zhang Binyuan Hui Bo Zheng Bowen Yu Chang Gao Chengen Huang Chenxu Lv Chujie Zheng Dayiheng Liu Fan Zhou Fei Huang Feng Hu Hao Ge Haoran Wei Huan Lin Jialong Tang Jian Yang Jianhong Tu Jianwei Zhang Jianxin Yang Jiaxi Yang Jing Zhou Jingren Zhou Junyang Lin Kai Dang Keqin Bao Kexin Yang Le Yu Lianghao Deng Mei Li Mingfeng Xue Mingze Li Pei Zhang Peng Wang Qin Zhu Rui Men Ruize Gao Shixuan Liu Shuang Luo Tianhao Li Tianyi Tang Wenbiao Yin Xingzhang Ren Xinyu Wang Xinyu Zhang Xuancheng Ren Yang Fan Yang Su Yichang Zhang Yinger Zhang Yu Wan Yuqiong Liu Zekun Wang Zeyu Cui Zhenru Zhang Zhipeng Zhou and Zihan Qiu. 2025. Qwen3 Technical Report. arXiv:2505.09388 [cs.CL] https:\/\/arxiv.org\/abs\/2505.09388"},{"key":"e_1_3_2_1_30_1","unstructured":"Z.ai. 2025. GLM-4.7: Advancing the Coding Capability. https:\/\/z.ai\/blog\/glm-4.7"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330785"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3672354"},{"key":"e_1_3_2_1_33_1","unstructured":"Guo-Biao Zhang Ding-Yuan Liu Da-Yi Wu Tian Lan Heyan Huang Zhijing Wu and Xian-Ling Mao. 2026. DeepSurvey-Bench: Evaluating Academic Value of Automatically Generated Scientific Survey. arXiv:2601.15307 [cs.AI] https:\/\/arxiv.org\/abs\/2601.15307"},{"key":"e_1_3_2_1_34_1","unstructured":"Tianyi Zhang Varsha Kishore Felix Wu Kilian Q. Weinberger and Yoav Artzi. 2020. BERTScore: Evaluating Text Generation with BERT. arXiv:1904.09675 [cs.CL] https:\/\/arxiv.org\/abs\/1904.09675"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"crossref","unstructured":"Lianmin Zheng Wei-Lin Chiang Ying Sheng Siyuan Zhuang Zhanghao Wu Yonghao Zhuang Zi Lin Zhuohan Li Dacheng Li Eric P. Xing Hao Zhang Joseph E. Gonzalez and Ion Stoica. 2023. Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena. arXiv:2306.05685 [cs.CL] https:\/\/arxiv.org\/abs\/2306.05685","DOI":"10.52202\/075280-2020"},{"key":"e_1_3_2_1_36_1","volume-title":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 15627-15645","author":"Zhu Kun","year":"2025","unstructured":"Kun Zhu, Lizi Liao, Yuxuan Gu, Lei Huang, Xiaocheng Feng, and Bing Qin. 2025. Context-aware hierarchical taxonomy generation for scientific papers via llmguided multi-aspect clustering. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 15627-15645."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"crossref","unstructured":"Jun Zhuang and Casey Kennington. 2024. Understanding Survey Paper Taxonomy about Large Language Models via Graph Representation Learning. arXiv:2402.10409 [cs.CL] https:\/\/arxiv.org\/abs\/2402.10409","DOI":"10.18653\/v1\/2024.sdp-1.6"}],"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":"2026-08-07T01:19:52Z","timestamp":1786065592000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770855.3817505"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,8]]},"references-count":37,"alternative-id":["10.1145\/3770855.3817505","10.1145\/3770855"],"URL":"https:\/\/doi.org\/10.1145\/3770855.3817505","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"}}]}}