{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T09:50:13Z","timestamp":1774000213129,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":29,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,12,12]]},"DOI":"10.1145\/3788149.3788171","type":"proceedings-article","created":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T06:35:19Z","timestamp":1773988519000},"page":"649-654","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["CORTEX: A Capability-Driven Reasoning Framework for Zero-Shot Large Language Model Selection"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8048-5145","authenticated-orcid":false,"given":"Kaikai","family":"Zhao","sequence":"first","affiliation":[{"name":"Unicom Data Intelligence, China Unicom, Beijing, China and Data Science & Artificial Intelligence Research Institute, China Unicom, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1267-0277","authenticated-orcid":false,"given":"Zhaoxiang","family":"Liu","sequence":"additional","affiliation":[{"name":"Unicom Data Intelligence, China Unicom, Beijing, China and Data Science & Artificial Intelligence Research Institute, China Unicom, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9720-7156","authenticated-orcid":false,"given":"Zipeng","family":"Wang","sequence":"additional","affiliation":[{"name":"Unicom Data Intelligence, China Unicom, Beijing, China and Data Science & Artificial Intelligence Research Institute, China Unicom, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1944-1530","authenticated-orcid":false,"given":"Xin","family":"Wang","sequence":"additional","affiliation":[{"name":"Unicom Data Intelligence, China Unicom, Beijing, China and Data Science & Artificial Intelligence Research Institute, China Unicom, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8078-3401","authenticated-orcid":false,"given":"Heng","family":"Yang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3755-1150","authenticated-orcid":false,"given":"Ning","family":"Wang","sequence":"additional","affiliation":[{"name":"Unicom Data Intelligence, China Unicom, Beijing, China and Data Science & Artificial Intelligence Research Institute, China Unicom, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1171-0281","authenticated-orcid":false,"given":"Kai","family":"Wang","sequence":"additional","affiliation":[{"name":"Unicom Data Intelligence, China Unicom, Beijing, China and Data Science & Artificial Intelligence Research Institute, China Unicom, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4308-7049","authenticated-orcid":false,"given":"Shiguo","family":"Lian","sequence":"additional","affiliation":[{"name":"Unicom Data Intelligence, China Unicom, Beijing, China and Data Science & Artificial Intelligence Research Institute, China Unicom, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,3,19]]},"reference":[{"key":"e_1_3_3_1_2_2","unstructured":"Rohan Asthana Joschua Conrad Maurits Ortmanns and Vasileios Belagiannis. 2025. Dextr: Zero-Shot Neural Architecture Search with Singular Value Decomposition and Extrinsic Curvature. arxiv:https:\/\/arXiv.org\/abs\/2508.12977\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2508.12977"},{"key":"e_1_3_3_1_3_2","unstructured":"Thomas Carta Cl\u00e9ment Romac Loris Gaven Pierre-Yves Oudeyer Olivier Sigaud and Sylvain Lamprier. 2025. HERAKLES: Hierarchical Skill Compilation for Open-ended LLM Agents. arxiv:https:\/\/arXiv.org\/abs\/2508.14751\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2508.14751"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"crossref","unstructured":"Krishna\u00a0Teja Chitty-Venkata Murali Emani and Venkatram Vishwanath. 2025. LangVision-LoRA-NAS: Neural Architecture Search for Variable LoRA Rank in Vision Language Models. arxiv:https:\/\/arXiv.org\/abs\/2508.12512\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2508.12512","DOI":"10.1109\/ICIP55913.2025.11084278"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"crossref","unstructured":"Krishna\u00a0Teja Chitty-Venkata Murali Emani Venkatram Vishwanath and Arun\u00a0K Somani. 2022. Neural architecture search for transformers: A survey. IEEE Access 10 (2022) 108374\u2013108412.","DOI":"10.1109\/ACCESS.2022.3212767"},{"key":"e_1_3_3_1_6_2","unstructured":"Jo\u00e3o\u00a0Vitor de Carvalho\u00a0Silva and Douglas\u00a0G. Macharet. 2025. Can LLM Agents Solve Collaborative Tasks? A Study on Urgency-Aware Planning and Coordination. arxiv:https:\/\/arXiv.org\/abs\/2508.14635\u00a0[cs.RO] https:\/\/arxiv.org\/abs\/2508.14635"},{"key":"e_1_3_3_1_7_2","unstructured":"et\u00a0al. DeepSeek-AI. 2024. DeepSeek-V3 Technical Report. arxiv:https:\/\/arXiv.org\/abs\/2412.19437\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2412.19437"},{"key":"e_1_3_3_1_8_2","unstructured":"et\u00a0al. DeepSeek-AI. 2025. DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning. arxiv:https:\/\/arXiv.org\/abs\/2501.12948\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2501.12948"},{"key":"e_1_3_3_1_9_2","unstructured":"Abhimanyu Dubey Abhinav Jauhri Abhinav Pandey Abhishek Kadian Ahmad Al-Dahle Aiesha Letman Akhil Mathur Alan Schelten Amy Yang Angela Fan et\u00a0al. 2024. The llama 3 herd of models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2407.21783 (2024)."},{"key":"e_1_3_3_1_10_2","unstructured":"Dan Hendrycks Collin Burns Steven Basart Andy Zou Mantas Mazeika Dawn Song and Jacob Steinhardt. 2020. Measuring massive multitask language understanding. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2009.03300 (2020)."},{"key":"e_1_3_3_1_11_2","unstructured":"Yuzhen Huang Yuzhuo Bai Zhihao Zhu Junlei Zhang Jinghan Zhang Tangjun Su Junteng Liu Chuancheng Lv Yikai Zhang Yao Fu et\u00a0al. 2024. C-eval: A multi-level multi-discipline chinese evaluation suite for foundation models. Advances in Neural Information Processing Systems 36 (2024)."},{"key":"e_1_3_3_1_12_2","unstructured":"Naman Jain King Han Alex Gu Wen-Ding Li Fanjia Yan Tianjun Zhang Sida Wang Armando Solar-Lezama Koushik Sen and Ion Stoica. 2024. Livecodebench: Holistic and contamination free evaluation of large language models for code. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2403.07974 (2024)."},{"key":"e_1_3_3_1_13_2","first-page":"67","volume-title":"CCF International Conference on Natural Language Processing and Chinese Computing","author":"Lian Shiguo","year":"2024","unstructured":"Shiguo Lian, Kaikai Zhao, Xinhui Liu, Xuejiao Lei, Bikun Yang, Wenjing Zhang, Kai Wang, and Zhaoxiang Liu. 2024. What is the best model? Application-driven Evaluation for Large Language Models. In CCF International Conference on Natural Language Processing and Chinese Computing. Springer, 67\u201379."},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/3709026.3709030"},{"key":"e_1_3_3_1_15_2","unstructured":"OpenAI. 2023. Math-500. https:\/\/github.com\/openai\/prm800k\/tree\/main\/prm800k\/math_splits"},{"key":"e_1_3_3_1_16_2","unstructured":"OpenAI. 2024. Hello GPT-4o. https:\/\/openai.com\/index\/hello-gpt-4o\/"},{"key":"e_1_3_3_1_17_2","unstructured":"OpenAI. 2024. Introducing SimpleQA. https:\/\/openai.com\/index\/introducing-simpleqa\/"},{"key":"e_1_3_3_1_18_2","unstructured":"OpenAI. 2024. Learning to reason with llms. https:\/\/openai.com\/index\/learning-to-reason-with-llms\/"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/3709026.3709070"},{"key":"e_1_3_3_1_20_2","unstructured":"Qwen-Team. 2024. Qwen2.5: A Party of Foundation Models. https:\/\/qwenlm.github.io\/blog\/qwen2.5\/"},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/3709026.3709090"},{"key":"e_1_3_3_1_22_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_23_2","doi-asserted-by":"publisher","unstructured":"Zijun Sun and Yanning Shen. 2025. Learn to Explore: Meta NAS via Bayesian Optimization Guided Graph Generation. arXiv e-prints Article arXiv:2508.09467 (Aug. 2025) arXiv:2508.09467\u00a0pages. 10.48550\/arXiv.2508.09467 arxiv:https:\/\/arXiv.org\/abs\/2508.09467\u00a0[stat.ML]","DOI":"10.48550\/arXiv.2508.09467"},{"key":"e_1_3_3_1_24_2","unstructured":"Qwen Team. 2025. QwQ-32B: Embracing the Power of Reinforcement Learning. https:\/\/qwenlm.github.io\/blog\/qwq-32b\/"},{"key":"e_1_3_3_1_25_2","unstructured":"Lei Wang Wanyu Xu Yihuai Lan Zhiqiang Hu Yunshi Lan Roy Ka-Wei Lee and Ee-Peng Lim. 2023. Plan-and-solve prompting: Improving zero-shot chain-of-thought reasoning by large language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2305.04091 (2023)."},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/3709026.3709068"},{"key":"e_1_3_3_1_27_2","volume-title":"International Conference on Learning Representations (ICLR)","author":"Yao Shunyu","year":"2023","unstructured":"Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik Narasimhan, and Yuan Cao. 2023. React: Synergizing reasoning and acting in language models. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_3_1_28_2","unstructured":"Yanzhao Zhang Mingxin Li Dingkun Long Xin Zhang Huan Lin Baosong Yang Pengjun Xie An Yang Dayiheng Liu Junyang Lin Fei Huang and Jingren Zhou. 2025. Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2506.05176 (2025)."},{"key":"e_1_3_3_1_29_2","unstructured":"Kaikai Zhao Zhaoxiang Liu Xuejiao Lei Jiaojiao Zhao Zhenhong Long Zipeng Wang Ning Wang Meijuan An Qingliang Meng Peijun Yang et\u00a0al. 2025. Quantifying the Capability Boundary of DeepSeek Models: An Application-Driven Performance Analysis. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2502.11164 (2025)."},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"crossref","unstructured":"Kaikai Zhao Zhaoxiang Liu Peng Wang Xin Wang Zhicheng Ma Yajun Xu Wenjing Zhang Yibing Nan Kai Wang and Shiguo Lian. 2025. MITS: A large-scale multimodal benchmark dataset for Intelligent Traffic Surveillance. Image and Vision Computing (2025) 105736.","DOI":"10.1016\/j.imavis.2025.105736"}],"event":{"name":"CSAI 2025: 2025 The 9th International Conference on Computer Science and Artificial Intelligence","location":"Beijing China","acronym":"CSAI 2025"},"container-title":["Proceedings of the 2025 9th International Conference on Computer Science and Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3788149.3788171","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T06:40:01Z","timestamp":1773988801000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3788149.3788171"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,12]]},"references-count":29,"alternative-id":["10.1145\/3788149.3788171","10.1145\/3788149"],"URL":"https:\/\/doi.org\/10.1145\/3788149.3788171","relation":{},"subject":[],"published":{"date-parts":[[2025,12,12]]},"assertion":[{"value":"2026-03-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}