{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T05:48:10Z","timestamp":1777873690784,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":72,"publisher":"ACM","funder":[{"name":"General Research Funds from the Hong Kong Research Grants Council","award":["project no. PolyU 15207322, 15200023, 15206024, and 15224524"],"award-info":[{"award-number":["project no. PolyU 15207322, 15200023, 15206024, and 15224524"]}]},{"name":"internal research funds from The Hong Kong Polytechnic University","award":["project no. P0042693, P0048625, P0051361, P0052406, and P0052986"],"award-info":[{"award-number":["project no. P0042693, P0048625, P0051361, P0052406, and P0052986"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,8,3]]},"DOI":"10.1145\/3711896.3737378","type":"proceedings-article","created":{"date-parts":[[2025,8,3]],"date-time":"2025-08-03T21:04:26Z","timestamp":1754255066000},"page":"5505-5515","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["HiBench: Benchmarking LLMs Capability on Hierarchical Structure Reasoning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-0746-5015","authenticated-orcid":false,"given":"Zhuohang","family":"Jiang","sequence":"first","affiliation":[{"name":"The Hong Kong Polytechnic University, Hong Kong SAR, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0290-4594","authenticated-orcid":false,"given":"Pangjing","family":"Wu","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University, Hong Kong SAR, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1483-5810","authenticated-orcid":false,"given":"Ziran","family":"Liang","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University, Hong Kong SAR, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9055-4239","authenticated-orcid":false,"given":"Peter Q.","family":"Chen","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University, Hong Kong SAR, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2822-9443","authenticated-orcid":false,"given":"Xu","family":"Yuan","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University, Hong Kong SAR, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0457-8083","authenticated-orcid":false,"given":"Ye","family":"Jia","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University, Hong Kong SAR, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2121-5524","authenticated-orcid":false,"given":"Jiancheng","family":"Tu","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University, Hong Kong SAR, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3782-0737","authenticated-orcid":false,"given":"Chen","family":"Li","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University, Hong Kong SAR, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9671-896X","authenticated-orcid":false,"given":"Peter H. F.","family":"Ng","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University, Hong Kong SAR, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3370-471X","authenticated-orcid":false,"given":"Qing","family":"Li","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University, Hong Kong SAR, China"}]}],"member":"320","published-online":{"date-parts":[[2025,8,3]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Nguyen Bach, Amit Bahree, Arash Bakhtiari, Jianmin Bao, Harkirat Behl, et al.","author":"Abdin Marah","year":"2024","unstructured":"Marah Abdin, Jyoti Aneja, Hany Awadalla, Ahmed Awadallah, Ammar Ahmad Awan, Nguyen Bach, Amit Bahree, Arash Bakhtiari, Jianmin Bao, Harkirat Behl, et al., 2024. Phi-3 technical report: A highly capable language model locally on your phone. arXiv preprint arXiv:2404.14219(2024)."},{"key":"e_1_3_2_2_2_1","volume-title":"Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al.","author":"Achiam Josh","year":"2023","unstructured":"Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al., 2023. Gpt-4 technical report. arXiv preprint arXiv:2303.08774(2023)."},{"key":"e_1_3_2_2_3_1","volume-title":"SciBERT: A Pretrained Language Model for Scientific Text. In Conference on Empirical Methods in Natural Language Processing. 3615-3620","author":"Beltagy Iz","year":"2019","unstructured":"Iz Beltagy, Kyle Lo, and Arman Cohan. 2019. SciBERT: A Pretrained Language Model for Scientific Text. In Conference on Empirical Methods in Natural Language Processing. 3615-3620."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.3389\/feduc.2024.1379796"},{"key":"e_1_3_2_2_5_1","volume-title":"Hierarchical models of behavior and prefrontal function. Trends in cognitive sciences","author":"Botvinick Matthew M","year":"2008","unstructured":"Matthew M Botvinick. 2008. Hierarchical models of behavior and prefrontal function. Trends in cognitive sciences, Vol. 12, 5 (2008), 201-208."},{"key":"e_1_3_2_2_6_1","unstructured":"Zheng Cai Maosong Cao Haojiong Chen Kai Chen Keyu Chen Xin Chen Xun Chen Zehui Chen Zhi Chen Pei Chu et al. 2024. Internlm2 technical report. arXiv preprint arXiv:2403.17297(2024)."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cosrev.2024.100632"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671847"},{"key":"e_1_3_2_2_9_1","first-page":"98","volume-title":"Nature","volume":"453","author":"Clauset Aaron","year":"2008","unstructured":"Aaron Clauset, Cristopher Moore, and Mark EJ Newman. 2008. Hierarchical structure and the prediction of missing links in networks. Nature, Vol. 453, 7191 (2008), 98-101."},{"key":"e_1_3_2_2_10_1","unstructured":"Karl Cobbe Vineet Kosaraju Mohammad Bavarian Mark Chen Heewoo Jun Lukasz Kaiser Matthias Plappert Jerry Tworek Jacob Hilton Reiichiro Nakano Christopher Hesse and John Schulman. 2021. Training Verifiers to Solve Math Word Problems. arXiv preprint arXiv:2110.14168(2021)."},{"key":"e_1_3_2_2_11_1","volume-title":"SPECTER: Document-level Representation Learning using Citationinformed Transformers. arXiv preprint arXiv:2004.07180(2020).","author":"Cohan Arman","year":"2020","unstructured":"Arman Cohan, Sergey Feldman, Iz Beltagy, Doug Downey, and Daniel S Weld. 2020. SPECTER: Document-level Representation Learning using Citationinformed Transformers. arXiv preprint arXiv:2004.07180(2020)."},{"key":"e_1_3_2_2_12_1","volume-title":"The Thirteenth International Conference on Learning Representations.","author":"Dai Xinnan","year":"2025","unstructured":"Xinnan Dai, Haohao Qu, Yifei Shen, Bohang Zhang, Qihao Wen, Wenqi Fan, Dongsheng Li, Jiliang Tang, and Caihua Shan. 2025. How Do Large Language Models Understand Graph Patterns? A Benchmark for Graph Pattern Comprehension. In The Thirteenth International Conference on Learning Representations."},{"key":"e_1_3_2_2_13_1","unstructured":"Xinnan Dai Qihao Wen Yifei Shen Hongzhi Wen Dongsheng Li Jiliang Tang and Caihua Shan. 2024. Revisiting the Graph Reasoning Ability of Large Language Models: Case Studies in Translation Connectivity and Shortest Path. arXiv preprint arXiv:2408.09529(2024)."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.365"},{"key":"e_1_3_2_2_15_1","unstructured":"Yuntian Deng Yejin Choi and Stuart Shieber. 2024. From Explicit CoT to Implicit CoT: Learning to Internalize CoT Step by Step. arxiv:2405.14838 [cs.CL] https:\/\/arxiv.org\/abs\/2405.14838"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.64"},{"key":"e_1_3_2_2_17_1","volume-title":"GLM: General Language Model Pretraining with Autoregressive Blank Infilling. arxiv:2103.10360 [cs.CL] https:\/\/arxiv.org\/abs\/2103.10360","author":"Du Zhengxiao","year":"2022","unstructured":"Zhengxiao Du, Yujie Qian, Xiao Liu, Ming Ding, Jiezhong Qiu, Zhilin Yang, and Jie Tang. 2022. GLM: General Language Model Pretraining with Autoregressive Blank Infilling. arxiv:2103.10360 [cs.CL] https:\/\/arxiv.org\/abs\/2103.10360"},{"key":"e_1_3_2_2_18_1","unstructured":"Abhimanyu Dubey Abhinav Jauhri Abhinav Pandey Abhishek Kadian Ahmad Al-Dahle Aiesha Letman Akhil Mathur Alan Schelten Amy Yang Angela Fan et al. 2024. The llama 3 herd of models. arXiv preprint arXiv:2407.21783(2024)."},{"key":"e_1_3_2_2_19_1","unstructured":"Tao Feng Chuanyang Jin Jingyu Liu Kunlun Zhu Haoqin Tu Zirui Cheng Guanyu Lin and Jiaxuan You. 2024. How Far Are We From AGI. arXiv preprint arXiv:2405.10313(2024)."},{"key":"e_1_3_2_2_20_1","volume-title":"A theory of cognitive development: The control and construction of hierarchies of skills. Psychological review","author":"Fischer Kurt W","year":"1980","unstructured":"Kurt W Fischer. 1980. A theory of cognitive development: The control and construction of hierarchies of skills. Psychological review, Vol. 87, 6 (1980), 477."},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2015.00027"},{"key":"e_1_3_2_2_22_1","volume-title":"Chatglm: A family of large language models from glm-130b to glm-4 all tools. arXiv preprint arXiv:2406.12793(2024).","author":"Aohan Zeng Team GLM","year":"2024","unstructured":"Team GLM, Aohan Zeng, Bin Xu, Bowen Wang, Chenhui Zhang, Da Yin, Dan Zhang, Diego Rojas, Guanyu Feng, Hanlin Zhao, et al., 2024. Chatglm: A family of large language models from glm-130b to glm-4 all tools. arXiv preprint arXiv:2406.12793(2024)."},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01738"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3616855.3635739"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.262"},{"key":"e_1_3_2_2_26_1","volume-title":"Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lucile Saulnier, L\u00e9lio Renard Lavaud, et al.","author":"Jiang Albert Q.","year":"2023","unstructured":"Albert Q. Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lucile Saulnier, L\u00e9lio Renard Lavaud, et al., 2023. Mistral 7B. arxiv:2310.06825 [cs.CL] https:\/\/arxiv.org\/abs\/2310.06825"},{"key":"e_1_3_2_2_27_1","unstructured":"Hanlei Jin Yang Zhang Dan Meng Jun Wang and Jinghua Tan. 2024. A comprehensive survey on process-oriented automatic text summarization with exploration of llm-based methods. arXiv preprint arXiv:2403.02901(2024)."},{"key":"e_1_3_2_2_28_1","volume-title":"RAP: Retrieval-Augmented Planning with Contextual Memory for Multimodal LLM Agents. In NeurIPS 2024 Workshop on Open-World Agents.","author":"Kagaya Tomoyuki","year":"2024","unstructured":"Tomoyuki Kagaya, Thong Jing Yuan, Yuxuan Lou, Jayashree Karlekar, Sugiri Pranata, Akira Kinose, Koki Oguri, Felix Wick, and Yang You. 2024. RAP: Retrieval-Augmented Planning with Contextual Memory for Multimodal LLM Agents. In NeurIPS 2024 Workshop on Open-World Agents."},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.27"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611218"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i11.26536"},{"key":"e_1_3_2_2_32_1","volume-title":"Bosheng Ding, Shafiq Joty, Soujanya Poria, and Lidong Bing.","author":"Li Xingxuan","year":"2023","unstructured":"Xingxuan Li, Ruochen Zhao, Yew Ken Chia, Bosheng Ding, Shafiq Joty, Soujanya Poria, and Lidong Bing. 2023b. Chain-of-knowledge: Grounding large language models via dynamic knowledge adapting over heterogeneous sources. arXiv preprint arXiv:2305.13269(2023)."},{"key":"e_1_3_2_2_33_1","volume-title":"Dong Jae Kim, et al","author":"Lin Feng","year":"2024","unstructured":"Feng Lin, Dong Jae Kim, et al., 2024. When llm-based code generation meets the software development process. arXiv preprint arXiv:2403.15852(2024)."},{"key":"e_1_3_2_2_34_1","unstructured":"Aixin Liu Bei Feng Bing Xue Bingxuan Wang Bochao Wu Chengda Lu Chenggang Zhao Chengqi Deng Chenyu Zhang Chong Ruan et al. 2024a. Deepseek-v3 technical report. arXiv preprint arXiv:2412.19437(2024)."},{"key":"e_1_3_2_2_35_1","unstructured":"Fang Liu Yang Liu Lin Shi Houkun Huang Ruifeng Wang Zhen Yang Li Zhang Zhongqi Li and Yuchi Ma. 2024b. Exploring and evaluating hallucinations in llm-powered code generation. arXiv preprint arXiv:2404.00971(2024)."},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.631"},{"key":"e_1_3_2_2_37_1","volume-title":"Chatrule: Mining logical rules with large language models for knowledge graph reasoning. arXiv preprint arXiv:2309.01538(2023).","author":"Luo Linhao","year":"2023","unstructured":"Linhao Luo, Jiaxin Ju, Bo Xiong, Yuan-Fang Li, Gholamreza Haffari, and Shirui Pan. 2023. Chatrule: Mining logical rules with large language models for knowledge graph reasoning. arXiv preprint arXiv:2309.01538(2023)."},{"key":"e_1_3_2_2_38_1","unstructured":"Zihan Luo Xiran Song Hong Huang Jianxun Lian Chenhao Zhang Jinqi Jiang Xing Xie and Hai Jin. 2024. GraphInstruct: Empowering Large Language Models with Graph Understanding and Reasoning Capability. arXiv preprint arXiv:2403.04483(2024)."},{"key":"e_1_3_2_2_39_1","first-page":"892","article-title":"An autonomous multi-agent llm framework for agile software development","volume":"8","author":"Manish Sanwal","year":"2024","unstructured":"Sanwal Manish. 2024. An autonomous multi-agent llm framework for agile software development. International Journal of Trend in Scientific Research and Development, Vol. 8, 5 (2024), 892-898.","journal-title":"International Journal of Trend in Scientific Research and Development"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CONIT51480.2021.9498508"},{"key":"e_1_3_2_2_41_1","volume-title":"Hierarchical structure and search in complex organizations. Management science","author":"Mihm J\u00fcrgen","year":"2010","unstructured":"J\u00fcrgen Mihm, Christoph H Loch, Dennis Wilkinson, and Bernardo A Huberman. 2010. Hierarchical structure and search in complex organizations. Management science, Vol. 56, 5 (2010), 831-848."},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-024-02656-3"},{"key":"e_1_3_2_2_43_1","series-title":"Series B: Biological Sciences","volume-title":"Hierarchical organization of cognitive memory. Philosophical Transactions of the Royal Society of London","author":"Mishkin Mortimer","year":"1997","unstructured":"Mortimer Mishkin, Wendy A Suzuki, David G Gadian, and Faraneh Vargha-Khadem. 1997. Hierarchical organization of cognitive memory. Philosophical Transactions of the Royal Society of London. Series B: Biological Sciences, Vol. 352, 1360 (1997), 1461-1467."},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"crossref","unstructured":"Sam Musker Alex Duchnowski Rapha\u00ebl Milli\u00e8re and Ellie Pavlick. 2024. Semantic Structure-Mapping in LLM and Human Analogical Reasoning. arXiv preprint arXiv:2406.13803(2024).","DOI":"10.1016\/j.jml.2025.104676"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3597503.3639187"},{"key":"e_1_3_2_2_46_1","volume-title":"Chatgpt: Optimizing language models for dialogue. https:\/\/openai.com\/blog\/chatgpt","author":"AI.","year":"2022","unstructured":"OpenAI. 2022. Chatgpt: Optimizing language models for dialogue. https:\/\/openai.com\/blog\/chatgpt"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.vardial-1.19"},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2311.05596"},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1524685113"},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-024-00944-1"},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1037\/0096-3445.135.4.623"},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3616855.3635752"},{"key":"e_1_3_2_2_53_1","unstructured":"Qwen Team. 2024. QwQ: Reflect Deeply on the Boundaries of the Unknown. https:\/\/qwenlm.github.io\/blog\/qwq-32b-preview\/"},{"key":"e_1_3_2_2_54_1","unstructured":"Hugo Touvron Thibaut Lavril Gautier Izacard Xavier Martinet Marie-Anne Lachaux Timoth\u00e9e Lacroix Baptiste Rozi\u00e8re Naman Goyal Eric Hambro Faisal Azhar Aurelien Rodriguez Armand Joulin Edouard Grave and Guillaume Lample. 2023. LLaMA: Open and Efficient Foundation Language Models. arxiv:2302.13971 [cs.CL] https:\/\/arxiv.org\/abs\/2302.13971"},{"key":"e_1_3_2_2_55_1","first-page":"30840","article-title":"Can language models solve graph problems in natural language","volume":"36","author":"Wang Heng","year":"2023","unstructured":"Heng Wang, Shangbin Feng, Tianxing He, Zhaoxuan Tan, Xiaochuang Han, and Yulia Tsvetkov. 2023. Can language models solve graph problems in natural language? Advances in Neural Information Processing Systems, Vol. 36 (2023), 30840-30861.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_56_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Wang Heng","year":"2024","unstructured":"Heng Wang, Shangbin Feng, Tianxing He, Zhaoxuan Tan, Xiaochuang Han, and Yulia Tsvetkov. 2024a. Can language models solve graph problems in natural language? Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_2_57_1","volume-title":"Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understanding. In The Twelfth International Conference on Learning Representations.","author":"Wang Zilong","year":"2024","unstructured":"Zilong Wang, Hao Zhang, Chun-Liang Li, Julian Martin Eisenschlos, Vincent Perot, Zifeng Wang, Lesly Miculicich, Yasuhisa Fujii, Jingbo Shang, Chen-Yu Lee, et al., 2024b. Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understanding. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_2_2_58_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_2_59_1","volume-title":"Agentless: Demystifying llm-based software engineering agents. arXiv preprint arXiv:2407.01489(2024).","author":"Xia Chunqiu Steven","year":"2024","unstructured":"Chunqiu Steven Xia, Yinlin Deng, Soren Dunn, and Lingming Zhang. 2024. Agentless: Demystifying llm-based software engineering agents. arXiv preprint arXiv:2407.01489(2024)."},{"key":"e_1_3_2_2_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/3688399"},{"key":"e_1_3_2_2_61_1","unstructured":"Aiyuan Yang Bin Xiao Bingning Wang Borong Zhang Ce Bian Chao Yin Chenxu Lv Da Pan Dian Wang Dong Yan et al. 2023. Baichuan 2: Open large-scale language models. arXiv preprint arXiv:2309.10305(2023)."},{"key":"e_1_3_2_2_62_1","unstructured":"An Yang Baosong Yang Binyuan Hui Bo Zheng Bowen Yu Chang Zhou Chengpeng Li Chengyuan Li Dayiheng Liu Fei Huang Guanting Dong Haoran Wei Huan Lin Jialong Tang Jialin Wang Jian Yang Jianhong Tu Jianwei Zhang Jianxin Ma Jianxin Yang Jin Xu Jingren Zhou Jinze Bai Jinzheng He Junyang Lin Kai Dang Keming Lu Keqin Chen Kexin Yang Mei Li Mingfeng Xue Na Ni Pei Zhang Peng Wang Ru Peng Rui Men Ruize Gao Runji Lin Shijie Wang Shuai Bai Sinan Tan Tianhang Zhu Tianhao Li Tianyu Liu Wenbin Ge Xiaodong Deng Xiaohuan Zhou Xingzhang Ren Xinyu Zhang Xipin Wei Xuancheng Ren Xuejing Liu Yang Fan Yang Yao Yichang Zhang Yu Wan Yunfei Chu Yuqiong Liu Zeyu Cui Zhenru Zhang Zhifang Guo and Zhihao Fan. 2024a. Qwen2 Technical Report. arxiv:2407.10671 [cs.CL] https:\/\/arxiv.org\/abs\/2407.10671"},{"key":"e_1_3_2_2_63_1","unstructured":"An Yang Baosong Yang Beichen Zhang Binyuan Hui Bo Zheng Bowen Yu Chengyuan Li Dayiheng Liu Fei Huang Haoran Wei et al. 2024b. Qwen2. 5 technical report. arXiv preprint arXiv:2412.15115(2024)."},{"key":"e_1_3_2_2_64_1","volume-title":"Tree of thoughts: Deliberate problem solving with large language models. Advances in neural information processing systems","author":"Yao Shunyu","year":"2023","unstructured":"Shunyu Yao, Dian Yu, Jeffrey Zhao, Izhak Shafran, Tom Griffiths, Yuan Cao, and Karthik Narasimhan. 2023. Tree of thoughts: Deliberate problem solving with large language models. Advances in neural information processing systems, Vol. 36 (2023), 11809-11822."},{"key":"e_1_3_2_2_65_1","volume-title":"Yi: Open foundation models by 01. ai. arXiv preprint arXiv:2403.04652(2024).","author":"Young Alex","year":"2024","unstructured":"Alex Young, Bei Chen, Chao Li, Chengen Huang, Ge Zhang, Guanwei Zhang, Guoyin Wang, Heng Li, Jiangcheng Zhu, Jianqun Chen, et al., 2024. Yi: Open foundation models by 01. ai. arXiv preprint arXiv:2403.04652(2024)."},{"key":"e_1_3_2_2_66_1","first-page":"137010","article-title":"Fincon: A synthesized llm multi-agent system with conceptual verbal reinforcement for enhanced financial decision making","volume":"37","author":"Yu Yangyang","year":"2025","unstructured":"Yangyang Yu, Zhiyuan Yao, Haohang Li, Zhiyang Deng, Yuechen Jiang, Yupeng Cao, Zhi Chen, Jordan Suchow, Zhenyu Cui, Rong Liu, et al., 2025. Fincon: A synthesized llm multi-agent system with conceptual verbal reinforcement for enhanced financial decision making. Advances in Neural Information Processing Systems, Vol. 37 (2025), 137010-137045.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_67_1","volume-title":"Graph transformer networks. Advances in neural information processing systems","author":"Yun Seongjun","year":"2019","unstructured":"Seongjun Yun, Minbyul Jeong, Raehyun Kim, Jaewoo Kang, and Hyunwoo J Kim. 2019. Graph transformer networks. Advances in neural information processing systems, Vol. 32 (2019)."},{"key":"e_1_3_2_2_68_1","doi-asserted-by":"crossref","unstructured":"Haopeng Zhang Philip S Yu and Jiawei Zhang. 2024. A Systematic Survey of Text Summarization: From Statistical Methods to Large Language Models. arXiv preprint arXiv:2406.11289(2024).","DOI":"10.1145\/3731445"},{"key":"e_1_3_2_2_69_1","unstructured":"Jiawei Zhang Haopeng Zhang Congying Xia and Li Sun. 2020. Graph-Bert: Only Attention is Needed for Learning Graph Representations. arxiv:2001.05140 [cs.LG] https:\/\/arxiv.org\/abs\/2001.05140"},{"key":"e_1_3_2_2_70_1","volume-title":"Automatic Chain of Thought Prompting in Large Language Models. In The Eleventh International Conference on Learning Representations.","author":"Zhang Zhuosheng","year":"2023","unstructured":"Zhuosheng Zhang, Aston Zhang, Mu Li, and Alex Smola. 2023. Automatic Chain of Thought Prompting in Large Language Models. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_3_2_2_71_1","unstructured":"Tianyang Zhong Zhengliang Liu Yi Pan Yutong Zhang Yifan Zhou Shizhe Liang Zihao Wu Yanjun Lyu Peng Shu Xiaowei Yu et al. 2024. Evaluation of openai o1: Opportunities and challenges of agi. arXiv preprint arXiv:2409.18486(2024)."},{"key":"e_1_3_2_2_72_1","first-page":"126032","article-title":"Self-discover: Large language models self-compose reasoning structures","volume":"37","author":"Zhou Pei","year":"2025","unstructured":"Pei Zhou, Jay Pujara, Xiang Ren, Xinyun Chen, Heng-Tze Cheng, Quoc V Le, Ed Chi, Denny Zhou, Swaroop Mishra, and Huaixiu Steven Zheng. 2025. Self-discover: Large language models self-compose reasoning structures. Advances in Neural Information Processing Systems, Vol. 37 (2025), 126032-126058.","journal-title":"Advances in Neural Information Processing Systems"}],"event":{"name":"KDD '25: The 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Toronto ON Canada","acronym":"KDD '25","sponsor":["SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGMOD ACM Special Interest Group on Management of Data"]},"container-title":["Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3711896.3737378","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T18:13:10Z","timestamp":1777572790000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3711896.3737378"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,3]]},"references-count":72,"alternative-id":["10.1145\/3711896.3737378","10.1145\/3711896"],"URL":"https:\/\/doi.org\/10.1145\/3711896.3737378","relation":{},"subject":[],"published":{"date-parts":[[2025,8,3]]},"assertion":[{"value":"2025-08-03","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}