{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T16:40:15Z","timestamp":1786120815455,"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":"China Postdoctoral Science Foundation","award":["BX20240186"],"award-info":[{"award-number":["BX20240186"]}]},{"name":"China Postdoctoral Science Foundation","award":["2024M761616"],"award-info":[{"award-number":["2024M761616"]}]},{"name":"NUS Artificial Intelligence Institute (NAII) Seed Grant","award":["A-8003158-00-00"],"award-info":[{"award-number":["A-8003158-00-00"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,9]]},"DOI":"10.1145\/3770855.3817545","type":"proceedings-article","created":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T17:15:37Z","timestamp":1786036537000},"page":"10174-10185","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Can Large Language Models Derive New Knowledge? A Dynamic Benchmark for Biological Knowledge Discovery"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-3501-491X","authenticated-orcid":false,"given":"Chaoqun","family":"Yang","sequence":"first","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6931-3182","authenticated-orcid":false,"given":"Xinyu","family":"Lin","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0218-6921","authenticated-orcid":false,"given":"Shulin","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5199-1428","authenticated-orcid":false,"given":"Wenjie","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-6451-8914","authenticated-orcid":false,"given":"Ruihan","family":"Guo","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5828-9842","authenticated-orcid":false,"given":"Fuli","family":"Feng","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6097-7807","authenticated-orcid":false,"given":"Tat-Seng","family":"Chua","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,8,8]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"V246","author":"Arslan Muhammad","year":"2024","unstructured":"Muhammad Arslan, Hussam Ghanem, Saba Munawar, and Christophe Cruz. 2024. A Survey on RAG with LLMs. Procedia Computer Science, V246 (2024), 3781-3790."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.782"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.emnlp-main.511"},{"key":"e_1_3_2_1_4_1","volume-title":"Auto-Bench: An Automated Benchmark for Scientific Discovery in LLMs. arXiv preprint arXiv:2502.15224","author":"Chen Tingting","year":"2025","unstructured":"Tingting Chen, Srinivas Anumasa, Beibei Lin, Vedant Shah, Anirudh Goyal, and Dianbo Liu. 2025a. Auto-Bench: An Automated Benchmark for Scientific Discovery in LLMs. arXiv preprint arXiv:2502.15224 (2025)."},{"key":"e_1_3_2_1_5_1","volume-title":"How scientists really reason: Scientific reasoning in real-world laboratories","author":"Dunbar Kevin","unstructured":"Kevin Dunbar. 1995. How scientists really reason: Scientific reasoning in real-world laboratories., The MIT Press."},{"key":"e_1_3_2_1_6_1","volume-title":"Yasha Ektefaie, Jovana Kondic, and Marinka Zitnik.","author":"Gao Shanghua","year":"2024","unstructured":"Shanghua Gao, Ada Fang, Yepeng Huang, Valentina Giunchiglia, Ayush Noori, Jonathan Richard Schwarz, Yasha Ektefaie, Jovana Kondic, and Marinka Zitnik. 2024. Empowering Biomedical Discovery with AI Agents. Cell, V187, 22 (2024), 6125-6151."},{"key":"e_1_3_2_1_7_1","unstructured":"Juraj Gottweis Wei-Hung Weng Alexander Daryin Tao Tu Anil Palepu Petar Sirkovic Artiom Myaskovsky Felix Weissenberger Keran Rong Ryutaro Tanno et al. 2025. Towards an AI Co-scientist. arXiv preprint arXiv:2502.18864 (2025)."},{"key":"e_1_3_2_1_8_1","unstructured":"Jiawei Gu Xuhui Jiang Zhichao Shi Hexiang Tan Xuehao Zhai Chengjin Xu Wei Li Yinghan Shen Shengjie Ma Honghao Liu et al. 2024a. A Survey on LLM-as-a-judge. The Innovation (2024)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29767"},{"key":"e_1_3_2_1_10_1","unstructured":"Norwood Russell Hanson. 1979. Patterns of discovery: An inquiry into the conceptual foundations of science. Cup archive."},{"key":"e_1_3_2_1_11_1","volume-title":"Measuring Massive Multitask Language Understanding. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=d7KBjmI3GmQ","author":"Hendrycks Dan","year":"2021","unstructured":"Dan Hendrycks, Collin Burns, Steven Basart, Andy Zou, Mantas Mazeika, Dawn Song, and Jacob Steinhardt. 2021. Measuring Massive Multitask Language Understanding. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=d7KBjmI3GmQ"},{"key":"e_1_3_2_1_12_1","volume-title":"Biomni: A General-purpose Biomedical AI Agent. biorxiv","author":"Huang Kexin","year":"2025","unstructured":"Kexin Huang, Serena Zhang, Hanchen Wang, Yuanhao Qu, Yingzhou Lu, Yusuf Roohani, Ryan Li, Lin Qiu, Gavin Li, Junze Zhang, et al., 2025. Biomni: A General-purpose Biomedical AI Agent. biorxiv (2025)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","unstructured":"Yuzhen Huang Yuzhuo Bai Zhihao Zhu Junlei Zhang Jinghan Zhang Tangjun Su Junteng Liu Chuancheng Lv Yikai Zhang Yao Fu et al. 2023. C-Eval: A Multi-level Multi-discipline Chinese Evaluation Suite for Foundation Models. Advances in Neural Information Processing Systems V36 (2023) 62991-63010.","DOI":"10.52202\/075280-2749"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"crossref","unstructured":"Zhen Huang Zengzhi Wang Shijie Xia Xuefeng Li Haoyang Zou Ruijie Xu Run-Ze Fan Lyumanshan Ye Ethan Chern Yixin Ye et al. 2024. OlympicArena: Benchmarking Multi-discipline Cognitive Reasoning for Superintelligent AI. Advances in Neural Information Processing Systems V37 (2024) 19209-19253.","DOI":"10.52202\/079017-0607"},{"key":"e_1_3_2_1_15_1","volume-title":"LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code. In The Thirteenth International Conference on Learning Representations.","author":"Jain Naman","year":"2025","unstructured":"Naman Jain, King Han, Alex Gu, Wen-Ding Li, Fanjia Yan, Tianjun Zhang, Sida Wang, Armando Solar-Lezama, Koushik Sen, and Ion Stoica. 2025. LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code. In The Thirteenth International Conference on Learning Representations."},{"key":"e_1_3_2_1_16_1","volume-title":"Domain Expansion, And Metric Optimization. arXiv preprint arXiv:2509.09321","author":"Jia Hangyi","year":"2025","unstructured":"Hangyi Jia, Yuxi Qian, Hanwen Tong, Xinhui Wu, Lin Chen, and Feng Wei. 2025. Towards Adaptive ML Benchmarks: Web-Agent-Driven Construction, Domain Expansion, And Metric Optimization. arXiv preprint arXiv:2509.09321 (2025)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1101\/2025.09.03.674085"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"crossref","unstructured":"John Jumper Richard Evans Alexander Pritzel Tim Green Michael Figurnov Olaf Ronneberger Kathryn Tunyasuvunakool Russ Bates Augustin \u017d\u00eddek Anna Potapenko et al. 2021. Highly Accurate Protein Structure Prediction with AlphaFold. Nature V596 7873 (2021) 583-589.","DOI":"10.1038\/s41586-021-03819-2"},{"key":"e_1_3_2_1_19_1","volume-title":"ForecastBench: A Dynamic Benchmark of AI Forecasting Capabilities. In The Thirteenth International Conference on Learning Representations.","author":"Karger Ezra","year":"2025","unstructured":"Ezra Karger, Houtan Bastani, Chen Yueh-Han, Zachary Jacobs, Danny Halawi, Fred Zhang, and Philip Tetlock. 2025. ForecastBench: A Dynamic Benchmark of AI Forecasting Capabilities. In The Thirteenth International Conference on Learning Representations."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.946"},{"key":"e_1_3_2_1_21_1","volume-title":"LLMs-as-judges: A Comprehensive Survey on LLM-Based Evaluation Methods. arXiv preprint arXiv:2412.05579","author":"Li Haitao","year":"2024","unstructured":"Haitao Li, Qian Dong, Junjie Chen, Huixue Su, Yujia Zhou, Qingyao Ai, Ziyi Ye, and Yiqun Liu. 2024. LLMs-as-judges: A Comprehensive Survey on LLM-Based Evaluation Methods. arXiv preprint arXiv:2412.05579 (2024)."},{"key":"e_1_3_2_1_22_1","volume-title":"ResearchBench: Benchmarking LLMs in Scientific Discovery via Inspiration-Based Task Decomposition. arXiv preprint arXiv:2503.21248","author":"Liu Yujie","year":"2025","unstructured":"Yujie Liu, Zonglin Yang, Tong Xie, Jinjie Ni, Ben Gao, Yuqiang Li, Shixiang Tang, Wanli Ouyang, Erik Cambria, and Dongzhan Zhou. 2025. ResearchBench: Benchmarking LLMs in Scientific Discovery via Inspiration-Based Task Decomposition. arXiv preprint arXiv:2503.21248 (2025)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"crossref","unstructured":"Lin Long Rui Wang Ruixuan Xiao Junbo Zhao Xiao Ding Gang Chen and Haobo Wang. 2024. On LLMs-Driven Synthetic Data Generation Curation and Evaluation: A Survey. In ACL (Findings).","DOI":"10.18653\/v1\/2024.findings-acl.658"},{"key":"e_1_3_2_1_24_1","volume-title":"GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models. In The Thirteenth International Conference on Learning Representations.","author":"Mirzadeh Seyed Iman","year":"2024","unstructured":"Seyed Iman Mirzadeh, Keivan Alizadeh, Hooman Shahrokhi, Oncel Tuzel, Samy Bengio, and Mehrdad Farajtabar. 2024. GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models. In The Thirteenth International Conference on Learning Representations."},{"key":"e_1_3_2_1_25_1","unstructured":"OpenAI. 2025. Introducing GPT-5.2. https:\/\/openai.com\/index\/introducing-gpt-5-2\/"},{"key":"e_1_3_2_1_26_1","volume-title":"Mohamed Shaaban, John Ling, Sean Shi, et al.","author":"Phan Long","year":"2025","unstructured":"Long Phan, Alice Gatti, Ziwen Han, Nathaniel Li, Josephina Hu, Hugh Zhang, Chen Bo Calvin Zhang, Mohamed Shaaban, John Ling, Sean Shi, et al., 2025. Humanity's Last Exam. arXiv preprint arXiv:2501.14249 (2025)."},{"key":"e_1_3_2_1_27_1","volume-title":"First Conference on Language Modeling.","author":"Rein David","year":"2024","unstructured":"David Rein, Betty Li Hou, Asa Cooper Stickland, Jackson Petty, Richard Yuanzhe Pang, Julien Dirani, Julian Michael, and Samuel R Bowman. 2024. GPQA: A Graduate-Level Google-Proof Q&A Benchmark. In First Conference on Language Modeling."},{"key":"e_1_3_2_1_28_1","volume-title":"LLM-SRBench: A New Benchmark for Scientific Equation Discovery with Large Language Models. In Forty-second International Conference on Machine Learning. https:\/\/openreview.net\/forum?id=SyQPiZJVWY","author":"Shojaee Parshin","unstructured":"Parshin Shojaee, Ngoc-Hieu Nguyen, Kazem Meidani, Amir Barati Farimani, Khoa D Doan, and Chandan K. Reddy. 2025. LLM-SRBench: A New Benchmark for Scientific Equation Discovery with Large Language Models. In Forty-second International Conference on Machine Learning. https:\/\/openreview.net\/forum?id=SyQPiZJVWY"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29872"},{"key":"e_1_3_2_1_30_1","volume-title":"SciQAG: A Framework for Auto-Generated Science Question Answering Dataset with Fine-Grained Evaluation. arXiv preprint arXiv:2405.09939","author":"Wan Yuwei","year":"2024","unstructured":"Yuwei Wan, Yixuan Liu, Aswathy Ajith, Clara Grazian, Bram Hoex, Wenjie Zhang, Chunyu Kit, Tong Xie, and Ian Foster. 2024. SciQAG: A Framework for Auto-Generated Science Question Answering Dataset with Fine-Grained Evaluation. arXiv preprint arXiv:2405.09939 (2024)."},{"key":"e_1_3_2_1_31_1","volume-title":"V32","author":"Wang Alex","year":"2019","unstructured":"Alex Wang, Yada Pruksachatkun, Nikita Nangia, Amanpreet Singh, Julian Michael, Felix Hill, Omer Levy, and Samuel Bowman. 2019. SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems. Advances in neural information processing systems, V32 (2019)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"crossref","unstructured":"Yubo Wang Xueguang Ma Ge Zhang Yuansheng Ni Abhranil Chandra Shiguang Guo Weiming Ren Aaran Arulraj Xuan He Ziyan Jiang et al. 2024. MMLU-Pro: A More Robust and Challenging Multi-task Language Understanding Benchmark. Advances in Neural Information Processing Systems V37 (2024) 95266-95290.","DOI":"10.52202\/079017-3018"},{"key":"e_1_3_2_1_33_1","volume-title":"Contamination-Limited LLM Benchmark. In The Thirteenth International Conference on Learning Representations.","author":"White Colin","year":"2025","unstructured":"Colin White, Samuel Dooley, Manley Roberts, Arka Pal, Benjamin Feuer, Siddhartha Jain, Ravid Shwartz-Ziv, Neel Jain, Khalid Saifullah, Sreemanti Dey, et al., 2025. LiveBench: A Challenging, Contamination-Limited LLM Benchmark. In The Thirteenth International Conference on Learning Representations."},{"key":"e_1_3_2_1_34_1","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_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00913"},{"key":"e_1_3_2_1_36_1","unstructured":"Zhiyuan Zeng Jiashuo Liu Siyuan Chen Tianci He Yali Liao Yixiao Tian Jinpeng Wang Zaiyuan Wang Yang Yang Lingyue Yin et al. 2025. FutureX: An Advanced Live Benchmark for LLM Agents in Future Prediction. arXiv preprint arXiv:2508.11987 (2025)."},{"key":"e_1_3_2_1_37_1","unstructured":"Yaping Zhang Qixuan Zhang Xingquan Zhang Zhiyuan Chen Wenwen Zhuang Yupu Liang Lu Xiang Yang Zhao Jiajun Zhang Yu Zhou et al. 2025. HiSciBench: A Hierarchical Multi-disciplinary Benchmark for Scientific Intelligence from Reading to Discovery. arXiv preprint arXiv:2512.22899 (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":"2026-08-07T01:34:04Z","timestamp":1786066444000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770855.3817545"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,8]]},"references-count":37,"alternative-id":["10.1145\/3770855.3817545","10.1145\/3770855"],"URL":"https:\/\/doi.org\/10.1145\/3770855.3817545","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"}}]}}