{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T13:44:15Z","timestamp":1782999855013,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":98,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,7,5]],"date-time":"2026-07-05T00:00:00Z","timestamp":1783209600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2243775"],"award-info":[{"award-number":["2243775"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000015","name":"U.S. Department of Energy","doi-asserted-by":"publisher","award":["LAB-25-3560"],"award-info":[{"award-number":["LAB-25-3560"]}],"id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000015","name":"U.S. Department of Energy","doi-asserted-by":"publisher","award":["DOE-ERCAP 0036600"],"award-info":[{"award-number":["DOE-ERCAP 0036600"]}],"id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,6]]},"DOI":"10.1145\/3797905.3800542","type":"proceedings-article","created":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T11:50:37Z","timestamp":1782993037000},"page":"353-366","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Rudder: Steering Prefetching in Distributed GNN Training using LLM Agents"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2575-1241","authenticated-orcid":false,"given":"Aishwarya","family":"Sarkar","sequence":"first","affiliation":[{"name":"Iowa State University, Ames, Iowa, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8758-7657","authenticated-orcid":false,"given":"Sayan","family":"Ghosh","sequence":"additional","affiliation":[{"name":"Pacific Northwest National Laboratory, Richland, Washington, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4297-3057","authenticated-orcid":false,"given":"Nathan","family":"Tallent","sequence":"additional","affiliation":[{"name":"Pacific Northwest National Laboratory, Richland, Washington, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6621-9003","authenticated-orcid":false,"given":"Aman","family":"Chadha","sequence":"additional","affiliation":[{"name":"Amazon GenAI, Cupertino, California, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-1235-3006","authenticated-orcid":false,"given":"Tanya G.","family":"Roosta","sequence":"additional","affiliation":[{"name":"University of California, Berkeley, Berkeley, California, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8672-5317","authenticated-orcid":false,"given":"Ali","family":"Jannesari","sequence":"additional","affiliation":[{"name":"Iowa State University, Ames, Iowa, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,5]]},"reference":[{"key":"e_1_3_3_1_2_2","unstructured":"2025. https:\/\/docs.python.org\/3\/library\/concurrent.futures.html."},{"key":"e_1_3_3_1_3_2","unstructured":"2025. https:\/\/docs.python.org\/3\/library\/threading.html."},{"key":"e_1_3_3_1_4_2","unstructured":"2025. https:\/\/ollama.com\/."},{"key":"e_1_3_3_1_5_2","unstructured":"2025. https:\/\/github.com\/ggml-org\/llama.cpp."},{"key":"e_1_3_3_1_6_2","unstructured":"2025. https:\/\/docs.python.org\/3\/library\/threading.html#threading.Condition.wait."},{"key":"e_1_3_3_1_7_2","unstructured":"2025. https:\/\/ollama.com\/library\/gemma3:4b."},{"key":"e_1_3_3_1_8_2","unstructured":"2025. https:\/\/ollama.com\/library\/gemma3:1b."},{"key":"e_1_3_3_1_9_2","unstructured":"2025. https:\/\/ollama.com\/library\/llama3.2."},{"key":"e_1_3_3_1_10_2","unstructured":"2025. https:\/\/hf.co\/HuggingFaceTB\/SmolLM2-360M-Instruct-GGUF."},{"key":"e_1_3_3_1_11_2","unstructured":"2025. https:\/\/huggingface.co\/HuggingFaceTB\/SmolLM2-1.7B-Instruct-GGUF."},{"key":"e_1_3_3_1_12_2","unstructured":"2025. https:\/\/huggingface.co\/bartowski\/Qwen2.5-Math-1.5B-Instruct-GGUF."},{"key":"e_1_3_3_1_13_2","unstructured":"2025. https:\/\/ollama.com\/library\/mixtral:8x7b-instruct-v0.1-q2_K."},{"key":"e_1_3_3_1_14_2","unstructured":"2025. https:\/\/ollama.com\/library\/mixtral:8x22b-instruct-v0.1-q2_K."},{"key":"e_1_3_3_1_15_2","unstructured":"2025. https:\/\/ollama.com\/library\/granite3-moe:3b-instruct-fp16."},{"key":"e_1_3_3_1_16_2","unstructured":"2025. ThreadPoolExecutor. https:\/\/huggingface.co\/models."},{"key":"e_1_3_3_1_17_2","unstructured":"Michael Ahn Anthony Brohan Noah Brown Yevgen Chebotar Omar Cortes Byron David Chelsea Finn Chuyuan Fu Keerthana Gopalakrishnan Karol Hausman et\u00a0al. 2022. Do as i can not as i say: Grounding language in robotic affordances. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2204.01691 (2022)."},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i8.16826"},{"key":"e_1_3_3_1_19_2","unstructured":"Peter Belcak Greg Heinrich Shizhe Diao Yonggan Fu Xin Dong Saurav Muralidharan Yingyan\u00a0Celine Lin and Pavlo Molchanov. 2025. Small Language Models are the Future of Agentic AI. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2506.02153 (2025)."},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480114"},{"key":"e_1_3_3_1_21_2","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared\u00a0D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et\u00a0al. 2020. Language models are few-shot learners. Advances in neural information processing systems 33 (2020) 1877\u20131901."},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"crossref","unstructured":"S\u00e9bastien Bubeck Nicolo Cesa-Bianchi et\u00a0al. 2012. Regret analysis of stochastic and nonstochastic multi-armed bandit problems. Foundations and Trends\u00ae in Machine Learning 5 1 (2012) 1\u2013122.","DOI":"10.1561\/2200000024"},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"crossref","unstructured":"Yupeng Chang Xu Wang Jindong Wang Yuan Wu Linyi Yang Kaijie Zhu Hao Chen Xiaoyuan Yi Cunxiang Wang Yidong Wang et\u00a0al. 2024. A survey on evaluation of large language models. ACM transactions on intelligent systems and technology 15 3 (2024) 1\u201345.","DOI":"10.1145\/3641289"},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"crossref","unstructured":"Angelica Chen David Dohan and David So. 2023. Evoprompting: Language models for code-level neural architecture search. Advances in neural information processing systems 36 (2023) 7787\u20137817.","DOI":"10.52202\/075280-0342"},{"key":"e_1_3_3_1_25_2","unstructured":"Mark Chen Jerry Tworek Heewoo Jun Qiming Yuan Henrique Ponde De\u00a0Oliveira Pinto Jared Kaplan Harri Edwards Yuri Burda Nicholas Joseph Greg Brockman et\u00a0al. 2021. Evaluating large language models trained on code. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2107.03374 (2021)."},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"crossref","unstructured":"Tianqi Chen. 2016. XGBoost: A Scalable Tree Boosting System. Cornell University (2016).","DOI":"10.1145\/2939672.2939785"},{"key":"e_1_3_3_1_27_2","unstructured":"Chris Cummins Volker Seeker Dejan Grubisic Mostafa Elhoushi Youwei Liang Baptiste Roziere Jonas Gehring Fabian Gloeckle Kim Hazelwood Gabriel Synnaeve et\u00a0al. 2023. Large language models for compiler optimization. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2309.07062 (2023)."},{"key":"e_1_3_3_1_28_2","unstructured":"Juncheng Dong Yang Yang Tao Liu Yang Wang Feng Qi Vahid Tarokh Kaushik Rangadurai and Shuang Yang. 2025. STARK: Strategic Team of Agents for Refining Kernels. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2510.16996 (2025)."},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"crossref","unstructured":"Ruihao Gong Yifu Ding Zining Wang Chengtao Lv Xingyu Zheng Jinyang Du Haotong Qin Jinyang Guo Michele Magno and Xianglong Liu. 2024. A survey of low-bit large language models: Basics systems and algorithms. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2409.16694 (2024).","DOI":"10.2139\/ssrn.4996660"},{"key":"e_1_3_3_1_30_2","unstructured":"IBM Granite\u00a0Team. 2024. Granite 3.0 Language Models."},{"key":"e_1_3_3_1_31_2","unstructured":"Aditya Grover and Jure Leskovec. 2016. node2vec: Scalable Feature Learning for Networks. arxiv:https:\/\/arXiv.org\/abs\/1607.00653\u00a0[cs.SI] https:\/\/arxiv.org\/abs\/1607.00653"},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/3627673.3680021"},{"key":"e_1_3_3_1_33_2","first-page":"1919","volume-title":"International Conference on Machine Learning","author":"Hashemi Milad","year":"2018","unstructured":"Milad Hashemi, Kevin Swersky, Jamie Smith, Grant Ayers, Heiner Litz, Jichuan Chang, Christos Kozyrakis, and Parthasarathy Ranganathan. 2018. Learning memory access patterns. In International Conference on Machine Learning. PMLR, 1919\u20131928."},{"key":"e_1_3_3_1_34_2","series-title":"(NIPS \u201920)","volume-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems","author":"Hu Weihua","year":"2020","unstructured":"Weihua Hu, Matthias Fey, Marinka Zitnik, Yuxiao Dong, Hongyu Ren, Bowen Liu, Michele Catasta, and Jure Leskovec. 2020. Open graph benchmark: datasets for machine learning on graphs. In Proceedings of the 34th International Conference on Neural Information Processing Systems (Vancouver, BC, Canada) (NIPS \u201920). Curran Associates Inc., Red Hook, NY, USA, Article 1855, 16\u00a0pages."},{"key":"e_1_3_3_1_35_2","unstructured":"Yelp Inc.2023. Yelp Open Dataset. https:\/\/www.yelp.com\/dataset. Accessed: Aug. 28 2025."},{"key":"e_1_3_3_1_36_2","unstructured":"Albert\u00a0Q Jiang Alexandre Sablayrolles Antoine Roux Arthur Mensch Blanche Savary Chris Bamford Devendra\u00a0Singh Chaplot Diego de\u00a0las Casas Emma\u00a0Bou Hanna Florian Bressand et\u00a0al. 2024. Mixtral of experts. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2401.04088 (2024)."},{"key":"e_1_3_3_1_37_2","doi-asserted-by":"crossref","unstructured":"Weiwei Jiang and Jiayun Luo. 2022. Graph neural network for traffic forecasting: A survey. Expert Systems with Applications 207 (2022) 117921.","DOI":"10.1016\/j.eswa.2022.117921"},{"key":"e_1_3_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC41406.2024.00098"},{"key":"e_1_3_3_1_39_2","unstructured":"Tim Kaler Alexandros Iliopoulos Philip Murzynowski Tao Schardl Charles\u00a0E Leiserson and Jie Chen. 2023. Communication-efficient graph neural networks with probabilistic neighborhood expansion analysis and caching. Proceedings of Machine Learning and Systems 5 (2023) 477\u2013494."},{"key":"e_1_3_3_1_40_2","volume-title":"Proceedings of Machine Learning and Systems 5","author":"Kaler Tim","year":"2023","unstructured":"Tim Kaler, Alexandros-Stavros Iliopoulos, Philip Murzynowski, Tao\u00a0B. Schardl, Charles\u00a0E. Leiserson, and Jie Chen. 2023. Communication-Efficient Graph Neural Networks with Probabilistic Neighborhood Expansion Analysis and Caching. In Proceedings of Machine Learning and Systems 5."},{"key":"e_1_3_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802322"},{"key":"e_1_3_3_1_42_2","doi-asserted-by":"crossref","unstructured":"George Karypis and Vipin Kumar. 1998. A fast and high quality multilevel scheme for partitioning irregular graphs. SIAM Journal on scientific Computing 20 1 (1998) 359\u2013392.","DOI":"10.1137\/S1064827595287997"},{"key":"e_1_3_3_1_43_2","doi-asserted-by":"publisher","DOI":"10.1145\/2833157.2833162"},{"key":"e_1_3_3_1_44_2","doi-asserted-by":"crossref","unstructured":"Jure Leskovec Jon Kleinberg and Christos Faloutsos. 2007. Graph evolution: Densification and shrinking diameters. ACM transactions on Knowledge Discovery from Data (TKDD) 1 1 (2007) 2\u2013es.","DOI":"10.1145\/1217299.1217301"},{"key":"e_1_3_3_1_45_2","unstructured":"Jure Leskovec and Andrej Krevl. 2014. SNAP Datasets: Stanford Large Network Dataset Collection. http:\/\/snap.stanford.edu\/data."},{"key":"e_1_3_3_1_46_2","unstructured":"Kai Li Fei Liu Zhenkun Wang Xialiang Tong Xiongwei Han Mingxuan Yuan and Qingfu Zhang. 2025. ARS: Automatic Routing Solver with Large Language Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2502.15359 (2025)."},{"key":"e_1_3_3_1_47_2","doi-asserted-by":"crossref","unstructured":"Mufei Li Jinjing Zhou Jiajing Hu Wenxuan Fan Yangkang Zhang Yaxin Gu and George Karypis. 2021. Dgl-lifesci: An open-source toolkit for deep learning on graphs in life science. ACS omega 6 41 (2021) 27233\u201327238.","DOI":"10.1021\/acsomega.1c04017"},{"key":"e_1_3_3_1_48_2","unstructured":"Xiaobin Li Kai Wu Xiaoyu Zhang Handing Wang and Jing Liu. 2022. Optformer: Beyond transformer for black-box optimization. (2022)."},{"key":"e_1_3_3_1_49_2","unstructured":"Zhen Li Yupeng Su Runming Yang Congkai Xie Zheng Wang Zhongwei Xie Ngai Wong and Hongxia Yang. 2025. Quantization Meets Reasoning: Exploring LLM Low-Bit Quantization Degradation for Mathematical Reasoning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2501.03035 (2025)."},{"key":"e_1_3_3_1_50_2","doi-asserted-by":"publisher","DOI":"10.1109\/JCC62314.2024.00020"},{"key":"e_1_3_3_1_51_2","volume-title":"The Twelfth International Conference on Learning Representations","author":"Lightman Hunter","year":"2023","unstructured":"Hunter Lightman, Vineet Kosaraju, Yuri Burda, Harrison Edwards, Bowen Baker, Teddy Lee, Jan Leike, John Schulman, Ilya Sutskever, and Karl Cobbe. 2023. Let\u2019s verify step by step. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_3_1_52_2","doi-asserted-by":"crossref","unstructured":"Bill\u00a0Yuchen Lin Yicheng Fu Karina Yang Faeze Brahman Shiyu Huang Chandra Bhagavatula Prithviraj Ammanabrolu Yejin Choi and Xiang Ren. 2023. Swiftsage: A generative agent with fast and slow thinking for complex interactive tasks. Advances in Neural Information Processing Systems 36 (2023) 23813\u201323825.","DOI":"10.52202\/075280-1034"},{"key":"e_1_3_3_1_53_2","unstructured":"Matthieu Lin Jenny Sheng Andrew Zhao Shenzhi Wang Yang Yue Yiran Wu Huan Liu Jun Liu Gao Huang and Yong-Jin Liu. 2024. LLM-based Optimization of Compound AI Systems: A Survey. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2410.16392 (2024)."},{"key":"e_1_3_3_1_54_2","doi-asserted-by":"publisher","unstructured":"Ting-Ru Lin Yunfan Li Massoud Pedram and Lizhong Chen. 2019. Design Space Exploration of Memory Controller Placement in Throughput Processors with Deep Learning. IEEE Computer Architecture Letters 18 1 (2019) 51\u201354. 10.1109\/LCA.2019.2905587","DOI":"10.1109\/LCA.2019.2905587"},{"key":"e_1_3_3_1_55_2","doi-asserted-by":"publisher","DOI":"10.1145\/3419111.3421281"},{"key":"e_1_3_3_1_56_2","unstructured":"Peiyu Liu Zikang Liu Ze-Feng Gao Dawei Gao Wayne\u00a0Xin Zhao Yaliang Li Bolin Ding and Ji-Rong Wen. 2023. Do emergent abilities exist in quantized large language models: An empirical study. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2307.08072 (2023)."},{"key":"e_1_3_3_1_57_2","volume-title":"The Second Conference on Parsimony and Learning (Proceedings Track)","author":"Liu Siyi","year":"2025","unstructured":"Siyi Liu, Chen Gao, and Yong Li. 2025. AgentHPO: Large language model agent for hyper-parameter optimization. In The Second Conference on Parsimony and Learning (Proceedings Track)."},{"key":"e_1_3_3_1_58_2","first-page":"103","volume-title":"20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23)","author":"Liu Tianfeng","year":"2023","unstructured":"Tianfeng Liu, Yangrui Chen, Dan Li, Chuan Wu, Yibo Zhu, Jun He, Yanghua Peng, Hongzheng Chen, Hongzhi Chen, and Chuanxiong Guo. 2023. { BGL} :{ GPU-Efficient}{ GNN} training by optimizing graph data { I\/O} and preprocessing. In 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23). 103\u2013118."},{"key":"e_1_3_3_1_59_2","doi-asserted-by":"crossref","unstructured":"Wai-Xi Liu Jie Zhang Zhong-Wei Liang Ling-Xi Peng and Jun Cai. 2017. Content popularity prediction and caching for ICN: A deep learning approach with SDN. IEEE access 6 (2017) 5075\u20135089.","DOI":"10.1109\/ACCESS.2017.2781716"},{"key":"e_1_3_3_1_60_2","doi-asserted-by":"publisher","unstructured":"Martin Maas David\u00a0G. Andersen Michael Isard Mohammad\u00a0Mahdi Javanmard Kathryn\u00a0S. McKinley and Colin Raffel. 2024. Combining Machine Learning and Lifetime-Based Resource Management for Memory Allocation and Beyond. Commun. ACM 67 4 (March 2024) 87\u201396. 10.1145\/3611018","DOI":"10.1145\/3611018"},{"key":"e_1_3_3_1_61_2","doi-asserted-by":"publisher","DOI":"10.1145\/3229543.3229555"},{"key":"e_1_3_3_1_62_2","doi-asserted-by":"publisher","DOI":"10.1145\/3597503.3608136"},{"key":"e_1_3_3_1_63_2","unstructured":"Ollama. 2025. Ollama: Run large language models locally. https:\/\/ollama.com. Version 0.6.0."},{"key":"e_1_3_3_1_64_2","unstructured":"Jeongmin\u00a0Brian Park Kun Wu Vikram\u00a0Sharma Mailthody Zaid Quresh Scott Mahlke and Wen-mei Hwu. 2024. LSM-GNN: Large-scale Storage-based Multi-GPU GNN Training by Optimizing Data Transfer Scheme. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2407.15264 (2024)."},{"key":"e_1_3_3_1_65_2","doi-asserted-by":"publisher","DOI":"10.1145\/3586183.3606763"},{"key":"e_1_3_3_1_66_2","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER59578.2024.00013"},{"key":"e_1_3_3_1_67_2","doi-asserted-by":"crossref","unstructured":"Timo Schick Jane Dwivedi-Yu Roberto Dess\u00ec Roberta Raileanu Maria Lomeli Eric Hambro Luke Zettlemoyer Nicola Cancedda and Thomas Scialom. 2023. Toolformer: Language models can teach themselves to use tools. Advances in Neural Information Processing Systems 36 (2023) 68539\u201368551.","DOI":"10.52202\/075280-2997"},{"key":"e_1_3_3_1_68_2","doi-asserted-by":"crossref","unstructured":"Yingxia Shao Hongzheng Li Xizhi Gu Hongbo Yin Yawen Li Xupeng Miao Wentao Zhang Bin Cui and Lei Chen. 2024. Distributed graph neural network training: A survey. Comput. Surveys 56 8 (2024) 1\u201339.","DOI":"10.1145\/3648358"},{"key":"e_1_3_3_1_69_2","unstructured":"Noam Shazeer Azalia Mirhoseini Krzysztof Maziarz Andy Davis Quoc Le Geoffrey Hinton and Jeff Dean. 2017. Outrageously large neural networks: The sparsely-gated mixture-of-experts layer. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1701.06538 (2017)."},{"key":"e_1_3_3_1_70_2","doi-asserted-by":"crossref","unstructured":"Yongliang Shen Kaitao Song Xu Tan Dongsheng Li Weiming Lu and Yueting Zhuang. 2023. Hugginggpt: Solving ai tasks with chatgpt and its friends in hugging face. Advances in Neural Information Processing Systems 36 (2023) 38154\u201338180.","DOI":"10.52202\/075280-1657"},{"key":"e_1_3_3_1_71_2","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358319"},{"key":"e_1_3_3_1_72_2","doi-asserted-by":"publisher","DOI":"10.1145\/3445814.3446752"},{"key":"e_1_3_3_1_73_2","doi-asserted-by":"crossref","unstructured":"Noah Shinn Federico Cassano Ashwin Gopinath Karthik Narasimhan and Shunyu Yao. 2023. Reflexion: Language agents with verbal reinforcement learning. Advances in Neural Information Processing Systems 36 (2023) 8634\u20138652.","DOI":"10.52202\/075280-0377"},{"key":"e_1_3_3_1_74_2","unstructured":"Jaeyong Song Hongsun Jang Jaewon Jung Youngsok Kim and Jinho Lee. 2023. GraNNDis: Efficient Unified Distributed Training Framework for Deep GNNs on Large Clusters. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2311.06837 (2023)."},{"key":"e_1_3_3_1_75_2","first-page":"1149","volume-title":"20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23)","author":"Song Zhenyu","year":"2023","unstructured":"Zhenyu Song, Kevin Chen, Nikhil Sarda, Deniz Alt\u0131nb\u00fcken, Eugene Brevdo, Jimmy Coleman, Xiao Ju, Pawel Jurczyk, Richard Schooler, and Ramki Gummadi. 2023. { HALP} : Heuristic aided learned preference eviction policy for { YouTube} content delivery network. In 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23). 1149\u20131163."},{"key":"e_1_3_3_1_76_2","doi-asserted-by":"publisher","DOI":"10.5555\/551283"},{"key":"e_1_3_3_1_77_2","doi-asserted-by":"publisher","DOI":"10.1145\/3696443.3708929"},{"key":"e_1_3_3_1_78_2","unstructured":"Jingwen Tong Wei Guo Jiawei Shao Qiong Wu Zijian Li Zehong Lin and Jun Zhang. 2025. Wirelessagent: Large language model agents for intelligent wireless networks. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2505.01074 (2025)."},{"key":"e_1_3_3_1_79_2","unstructured":"Rahul Vadisetty Anand Polamarasetti et\u00a0al. 2025. AI-Driven Kubernetes Orchestration: Utilizing Intelligent Agents for Automated Cluster Management and Optimization. Cuestiones de Fisioterapia 54 5 (2025) 28\u201336."},{"key":"e_1_3_3_1_80_2","doi-asserted-by":"crossref","unstructured":"Kuansan Wang Zhihong Shen Chiyuan Huang Chieh-Han Wu Yuxiao Dong and Anshul Kanakia. 2020. Microsoft academic graph: When experts are not enough. Quantitative Science Studies 1 1 (2020) 396\u2013413.","DOI":"10.1162\/qss_a_00021"},{"key":"e_1_3_3_1_81_2","doi-asserted-by":"crossref","unstructured":"Lei Wang Chen Ma Xueyang Feng Zeyu Zhang Hao Yang Jingsen Zhang Zhiyuan Chen Jiakai Tang Xu Chen Yankai Lin et\u00a0al. 2024. A survey on large language model based autonomous agents. Frontiers of Computer Science 18 6 (2024) 186345.","DOI":"10.1007\/s11704-024-40231-1"},{"key":"e_1_3_3_1_82_2","doi-asserted-by":"crossref","unstructured":"Jason Wei Xuezhi Wang Dale Schuurmans Maarten Bosma Fei Xia Ed Chi Quoc\u00a0V Le Denny Zhou et\u00a0al. 2022. Chain-of-thought prompting elicits reasoning in large language models. Advances in neural information processing systems 35 (2022) 24824\u201324837.","DOI":"10.52202\/068431-1800"},{"key":"e_1_3_3_1_83_2","doi-asserted-by":"crossref","unstructured":"Nan Wu and Yuan Xie. 2022. A survey of machine learning for computer architecture and systems. ACM Computing Surveys (CSUR) 55 3 (2022) 1\u201339.","DOI":"10.1145\/3494523"},{"key":"e_1_3_3_1_84_2","doi-asserted-by":"crossref","unstructured":"Zonghan Wu Shirui Pan Fengwen Chen Guodong Long Chengqi Zhang and S\u00a0Yu Philip. 2020. A comprehensive survey on graph neural networks. IEEE transactions on neural networks and learning systems 32 1 (2020) 4\u201324.","DOI":"10.1109\/TNNLS.2020.2978386"},{"key":"e_1_3_3_1_85_2","unstructured":"Charlene Yang and Jack Deslippe. 2020. Accelerate science on perlmutter with nersc. Bulletin of the American Physical Society 65 (2020)."},{"key":"e_1_3_3_1_86_2","unstructured":"Chengrun Yang Xuezhi Wang Yifeng Lu Hanxiao Liu Quoc\u00a0V Le Denny Zhou and Xinyun Chen. 2023. Large language models as optimizers. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2309.03409 (2023)."},{"key":"e_1_3_3_1_87_2","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3340404"},{"key":"e_1_3_3_1_88_2","doi-asserted-by":"crossref","unstructured":"Huijing Yang Juan Fang Yumin Hou Xing Su and Neal\u00a0N Xiong. 2025. Reinforcement learning-driven adaptive prefetch aggressiveness control for enhanced performance in parallel system architectures. IEEE Transactions on Parallel and Distributed Systems (2025).","DOI":"10.1109\/TPDS.2025.3550531"},{"key":"e_1_3_3_1_89_2","doi-asserted-by":"crossref","unstructured":"Huijing Yang Juan Fang Xing Su Zhi Cai and Yuening Wang. 2024. RL-CoPref: a reinforcement learning-based coordinated prefetching controller for multiple prefetchers. The Journal of Supercomputing 80 9 (2024) 13001\u201313026.","DOI":"10.1007\/s11227-024-05938-9"},{"key":"e_1_3_3_1_90_2","doi-asserted-by":"publisher","DOI":"10.1145\/3492321.3519557"},{"key":"e_1_3_3_1_91_2","volume-title":"The eleventh international conference on learning representations","author":"Yao Shunyu","year":"2022","unstructured":"Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik\u00a0R 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_3_1_92_2","doi-asserted-by":"crossref","unstructured":"Tong Zeng Srivathsan Badrinarayanan Janghoon Ock Cheng-Kai Lai and Amir Barati\u00a0Farimani. 2025. LLM-guided chemical process optimization with a multi-agent approach. Machine Learning: Science and Technology (2025).","DOI":"10.1088\/2632-2153\/ae2382"},{"key":"e_1_3_3_1_93_2","unstructured":"Bowen Zhang and Pengcheng Luo. 2025. Or-llm-agent: Automating modeling and solving of operations research optimization problem with reasoning large language model. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2503.10009 (2025)."},{"key":"e_1_3_3_1_94_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29936"},{"key":"e_1_3_3_1_95_2","doi-asserted-by":"publisher","DOI":"10.1109\/IA351965.2020.00011"},{"key":"e_1_3_3_1_96_2","unstructured":"Da Zheng Chao Ma Minjie Wang Jinjing Zhou Qidong Su Xiang Song Quan Gan Zheng Zhang and George Karypis. 2021. DistDGL: Distributed Graph Neural Network Training for Billion-Scale Graphs. arxiv:https:\/\/arXiv.org\/abs\/2010.05337\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2010.05337"},{"key":"e_1_3_3_1_97_2","doi-asserted-by":"crossref","unstructured":"Jie Zhou Ganqu Cui Shengding Hu Zhengyan Zhang Cheng Yang Zhiyuan Liu Lifeng Wang Changcheng Li and Maosong Sun. 2020. Graph neural networks: A review of methods and applications. AI open 1 (2020) 57\u201381.","DOI":"10.1016\/j.aiopen.2021.01.001"},{"key":"e_1_3_3_1_98_2","unstructured":"Jeffrey Zhou Tianjian Lu Swaroop Mishra Siddhartha Brahma Sujoy Basu Yi Luan Denny Zhou and Le Hou. 2023. Instruction-following evaluation for large language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2311.07911 (2023)."},{"key":"e_1_3_3_1_99_2","unstructured":"Rong Zhu Kun Zhao Hongxia Yang Wei Lin Chang Zhou Baole Ai Yong Li and Jingren Zhou. 2019. Aligraph: A comprehensive graph neural network platform. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1902.08730 (2019)."}],"event":{"name":"ICS '26: 2026 International Conference on Supercomputing","location":"Belfast United Kingdom","acronym":"ICS '26","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing","SIGARCH ACM Special Interest Group on Computer Architecture"]},"container-title":["Proceedings of the 40th ACM International Conference on Supercomputing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/abs\/10.1145\/3797905.3800542","content-type":"text\/html","content-version":"vor","intended-application":"syndication"}],"deposited":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T12:58:18Z","timestamp":1782997098000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3797905.3800542"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,5]]},"references-count":98,"alternative-id":["10.1145\/3797905.3800542","10.1145\/3797905"],"URL":"https:\/\/doi.org\/10.1145\/3797905.3800542","relation":{},"subject":[],"published":{"date-parts":[[2026,7,5]]},"assertion":[{"value":"2026-07-05","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}