{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T16:07:07Z","timestamp":1780675627559,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":59,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,13]]},"DOI":"10.1145\/3774904.3792240","type":"proceedings-article","created":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T13:28:36Z","timestamp":1777296516000},"page":"2060-2070","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Difficulty-Aware Agentic Orchestration for Query-Specific Multi-Agent Workflows"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-9208-3354","authenticated-orcid":false,"given":"Jinwei","family":"Su","sequence":"first","affiliation":[{"name":"South China Normal University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0496-5240","authenticated-orcid":false,"given":"Qizhen","family":"Lan","sequence":"additional","affiliation":[{"name":"The University of Texas Health Science Center, Houston, AL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-4494-6074","authenticated-orcid":false,"given":"Yinghui","family":"Xia","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3126-7196","authenticated-orcid":false,"given":"Lifan","family":"Sun","sequence":"additional","affiliation":[{"name":"University of California, San Diego, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4397-3897","authenticated-orcid":false,"given":"Weiyou","family":"Tian","sequence":"additional","affiliation":[{"name":"Peking University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-9119-778X","authenticated-orcid":false,"given":"Tianyu","family":"Shi","sequence":"additional","affiliation":[{"name":"University of Toronto, Toronto, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-0510-911X","authenticated-orcid":false,"given":"Lewei","family":"He","sequence":"additional","affiliation":[{"name":"South China Normal University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,4,12]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Jacob Austin Augustus Odena Maxwell Nye Maarten Bosma Henryk Michalewski David Dohan Ellen Jiang Carrie Cai Michael Terry Quoc Le et al. 2021. Program synthesis with large language models. arXiv preprint arXiv:2108.07732 (2021)."},{"key":"e_1_3_2_1_2_1","unstructured":"Simone Barandoni Filippo Chiarello Lorenzo Cascone Emiliano Marrale and Salvatore Puccio. 2024. Automating Customer Needs Analysis: A Comparative Study of Large Language Models in the Travel Industry. arXiv:2404.17975 [cs.CL] https:\/\/arxiv.org\/abs\/2404.17975"},{"key":"e_1_3_2_1_3_1","unstructured":"Mark Chen Jerry Tworek Heewoo Jun Qiming Yuan Henrique Ponde de Oliveira Pinto Jared Kaplan Harri Edwards Yuri Burda Nicholas Joseph Greg Brockman Alex Ray Raul Puri Gretchen Krueger Michael Petrov Heidy Khlaaf Girish Sastry Pamela Mishkin Brooke Chan Scott Gray Nick Ryder Mikhail Pavlov Alethea Power Lukasz Kaiser Mohammad Bavarian Clemens Winter Philippe Tillet Felipe Petroski Such Dave Cummings Matthias Plappert Fotios Chantzis Elizabeth Barnes Ariel Herbert-Voss William Hebgen Guss Alex Nichol Alex Paino Nikolas Tezak Jie Tang Igor Babuschkin Suchir Balaji Shantanu Jain William Saunders Christopher Hesse Andrew N. Carr Jan Leike Josh Achiam Vedant Misra Evan Morikawa Alec Radford Matthew Knight Miles Brundage Mira Murati Katie Mayer Peter Welinder Bob McGrew Dario Amodei Sam McCandlish Ilya Sutskever and Wojciech Zaremba. 2021. Evaluating Large Language Models Trained on Code. arXiv:2107.03374 pages."},{"key":"e_1_3_2_1_4_1","volume-title":"Training Verifiers to Solve Math Word Problems. arXiv prepring","author":"Cobbe Karl","year":"2021","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 prepring, Vol. abs\/2110.14168 (2021)."},{"key":"e_1_3_2_1_5_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Deng Xiang","year":"2024","unstructured":"Xiang Deng, Yu Gu, Boyuan Zheng, Shijie Chen, Sam Stevens, Boshi Wang, Huan Sun, and Yu Su. 2024. Mind2web: Towards a generalist agent for the web. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_6_1","volume-title":"Improving Factuality and Reasoning in Language Models through Multiagent Debate. CoRR","author":"Du Yilun","year":"2023","unstructured":"Yilun Du, Shuang Li, Antonio Torralba, Joshua B. Tenenbaum, and Igor Mordatch. 2023. Improving Factuality and Reasoning in Language Models through Multiagent Debate. CoRR, Vol. abs\/2305.14325 (2023)."},{"key":"e_1_3_2_1_7_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_1_8_1","unstructured":"Tao Feng Yanzhen Shen and Jiaxuan You. 2024. GraphRouter: A Graph-based Router for LLM Selections. arXiv:2410.03834 [cs.AI] https:\/\/arxiv.org\/abs\/2410.03834"},{"key":"e_1_3_2_1_9_1","volume-title":"The Eleventh International Conference on Learning Representations.","author":"Fu Yao","year":"2022","unstructured":"Yao Fu, Hao Peng, Ashish Sabharwal, Peter Clark, and Tushar Khot. 2022. Complexity-based prompting for multi-step reasoning. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_3_2_1_10_1","volume-title":"Connecting large language models with evolutionary algorithms yields powerful prompt optimizers. arXiv preprint arXiv:2309.08532","author":"Guo Qingyan","year":"2023","unstructured":"Qingyan Guo, Rui Wang, Junliang Guo, Bei Li, Kaitao Song, Xu Tan, Guoqing Liu, Jiang Bian, and Yujiu Yang. 2023. Connecting large language models with evolutionary algorithms yields powerful prompt optimizers. arXiv preprint arXiv:2309.08532 (2023)."},{"key":"e_1_3_2_1_11_1","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Hendrycks Dan","year":"2021","unstructured":"Dan Hendrycks, Collin Burns, Steven Basart, Andy Zou, Mantas Mazeika, Dawn Song, and Jacob Steinhardt. 2021a. Measuring Massive Multitask Language Understanding. Proceedings of the International Conference on Learning Representations (ICLR) (2021)."},{"key":"e_1_3_2_1_12_1","volume-title":"Measuring Mathematical Problem Solving With the MATH Dataset. NeurIPS","author":"Hendrycks Dan","year":"2021","unstructured":"Dan Hendrycks, Collin Burns, Saurav Kadavath, Akul Arora, Steven Basart, Eric Tang, Dawn Song, and Jacob Steinhardt. 2021b. Measuring Mathematical Problem Solving With the MATH Dataset. NeurIPS (2021)."},{"key":"e_1_3_2_1_13_1","unstructured":"Sirui Hong Yizhang Lin Bang Liu Bangbang Liu Binhao Wu Ceyao Zhang Chenxing Wei Danyang Li Jiaqi Chen Jiayi Zhang et al. 2024. Data interpreter: An llm agent for data science. arXiv preprint arXiv:2402.18679 (2024)."},{"key":"e_1_3_2_1_14_1","volume-title":"Automated design of agentic systems. arXiv preprint arXiv:2408.08435","author":"Hu Shengran","year":"2024","unstructured":"Shengran Hu, Cong Lu, and Jeff Clune. 2024. Automated design of agentic systems. arXiv preprint arXiv:2408.08435 (2024)."},{"key":"e_1_3_2_1_15_1","volume-title":"Agentcoder: Multi-agent-based code generation with iterative testing and optimisation. arXiv preprint arXiv:2312.13010","author":"Huang Dong","year":"2023","unstructured":"Dong Huang, Qingwen Bu, Jie M Zhang, Michael Luck, and Heming Cui. 2023. Agentcoder: Multi-agent-based code generation with iterative testing and optimisation. arXiv preprint arXiv:2312.13010 (2023)."},{"key":"e_1_3_2_1_16_1","volume-title":"Harder Tasks Need More Experts: Dynamic Routing in MoE Models. arXiv preprint arXiv:2403.07652","author":"Huang Quzhe","year":"2024","unstructured":"Quzhe Huang, Zhenwei An, Nan Zhuang, Mingxu Tao, Chen Zhang, Yang Jin, Kun Xu, Liwei Chen, Songfang Huang, and Yansong Feng. 2024. Harder Tasks Need More Experts: Dynamic Routing in MoE Models. arXiv preprint arXiv:2403.07652 (2024)."},{"key":"e_1_3_2_1_17_1","volume-title":"How Difficulty-Aware Staged Reinforcement Learning Enhances LLMs' Reasoning Capabilities: A Preliminary Experimental Study. ArXiv","author":"Ji Yunjie","year":"2025","unstructured":"Yunjie Ji, Sitong Zhao, Xiaoyu Tian, Haotian Wang, Shuaiting Chen, Yiping Peng, Han Zhao, and Xiangang Li. 2025. How Difficulty-Aware Staged Reinforcement Learning Enhances LLMs' Reasoning Capabilities: A Preliminary Experimental Study. ArXiv, Vol. abs\/2504.00829 (2025). https:\/\/api.semanticscholar.org\/CorpusID:277468428"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.792"},{"key":"e_1_3_2_1_19_1","volume-title":"Dspy: Compiling declarative language model calls into self-improving pipelines. arXiv preprint arXiv:2310.03714","author":"Khattab Omar","year":"2023","unstructured":"Omar Khattab, Arnav Singhvi, Paridhi Maheshwari, Zhiyuan Zhang, Keshav Santhanam, Sri Vardhamanan, Saiful Haq, Ashutosh Sharma, Thomas T Joshi, Hanna Moazam, et al., 2023. Dspy: Compiling declarative language model calls into self-improving pipelines. arXiv preprint arXiv:2310.03714 (2023)."},{"key":"e_1_3_2_1_20_1","volume-title":"Auto-Encoding Variational Bayes. arXiv preprint arXiv:1312.6114","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Max Welling. 2014. Auto-Encoding Variational Bayes. arXiv preprint arXiv:1312.6114 (2014)."},{"key":"e_1_3_2_1_21_1","unstructured":"Ang Li Zhihang Yuan Yang Zhang Shouda Liu and Yisen Wang. 2025. Know When to Explore: Difficulty-Aware Certainty as a Guide for LLM Reinforcement Learning. https:\/\/api.semanticscholar.org\/CorpusID:281080364"},{"key":"e_1_3_2_1_22_1","unstructured":"Ziming Li Qianbo Zang David Ma Jiawei Guo Tuney Zheng Minghao Liu Xinyao Niu Yue Wang Jian Yang Jiaheng Liu et al. 2024. AutoKaggle: A Multi-Agent Framework for Autonomous Data Science Competitions. arXiv preprint arXiv:2410.20424 (2024)."},{"key":"e_1_3_2_1_23_1","volume-title":"Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate. CoRR","author":"Liang Tian","year":"1911","unstructured":"Tian Liang, Zhiwei He, Wenxiang Jiao, Xing Wang, Yan Wang, Rui Wang, Yujiu Yang, Zhaopeng Tu, and Shuming Shi. 2023. Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate. CoRR, Vol. abs\/2305.19118 (2023)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.3390\/computation14010022"},{"key":"e_1_3_2_1_25_1","volume-title":"DRF: LLM-AGENT Dynamic Reputation Filtering Framework. In International Conference on Neural Information Processing. Springer, 127-141","author":"Lou Yuwei","year":"2025","unstructured":"Yuwei Lou, Hao Hu, Shaocong Ma, Zongfei Zhang, Liang Wang, Jidong Ge, and Xianping Tao. 2025. DRF: LLM-AGENT Dynamic Reputation Filtering Framework. In International Conference on Neural Information Processing. Springer, 127-141."},{"key":"e_1_3_2_1_26_1","volume-title":"Katherine Hermann, Sean Welleck, Amir Yazdanbakhsh, and Peter Clark.","author":"Madaan Aman","year":"2023","unstructured":"Aman Madaan, Niket Tandon, Prakhar Gupta, Skyler Hallinan, Luyu Gao, Sarah Wiegreffe, Uri Alon, Nouha Dziri, Shrimai Prabhumoye, Yiming Yang, Shashank Gupta, Bodhisattwa Prasad Majumder, Katherine Hermann, Sean Welleck, Amir Yazdanbakhsh, and Peter Clark. 2023. Self-Refine: Iterative Refinement with Self-Feedback. In NeurIPS. http:\/\/papers.nips.cc\/paper_files\/paper\/2023\/hash\/91edff07232fb1b55a505a9e9f6c0ff3-Abstract-Conference.html"},{"key":"e_1_3_2_1_27_1","volume-title":"Gaia: a benchmark for general ai assistants. arXiv preprint arXiv:2311.12983","author":"Mialon Gr\u00e9goire","year":"2023","unstructured":"Gr\u00e9goire Mialon, Cl\u00e9mentine Fourrier, Craig Swift, Thomas Wolf, Yann LeCun, and Thomas Scialom. 2023. Gaia: a benchmark for general ai assistants. arXiv preprint arXiv:2311.12983 (2023)."},{"key":"e_1_3_2_1_28_1","unstructured":"Yohei Nakajima. 2023. BabyAGI. https:\/\/github.com\/yoheinakajima\/babyagi."},{"key":"e_1_3_2_1_29_1","unstructured":"Isaac Ong Amjad Almahairi Vincent Wu Wei-Lin Chiang Tianhao Wu Joseph E. Gonzalez M Waleed Kadous and Ion Stoica. 2024. RouteLLM: Learning to Route LLMs with Preference Data. arXiv:2406.18665 [cs.LG] https:\/\/arxiv.org\/abs\/2406.18665"},{"key":"e_1_3_2_1_30_1","unstructured":"OpenAI. 2024. GPT-4O Mini: Advancing cost-efficient intelligence. https:\/\/openai.com\/index\/gpt-4o-mini-advancing-cost-efficient-intelligence"},{"key":"e_1_3_2_1_31_1","volume-title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks. arXiv preprint arXiv:1908.10084","author":"Reimers N","year":"2019","unstructured":"N Reimers. 2019. Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks. arXiv preprint arXiv:1908.10084 (2019)."},{"key":"e_1_3_2_1_32_1","unstructured":"Reworkd. 2023. AgentGPT. https:\/\/github.com\/reworkd\/AgentGPT."},{"key":"e_1_3_2_1_33_1","unstructured":"Toran Bruce Richards and et al. 2023. Auto-GPT: An Autonomous GPT-4 Experiment. https:\/\/github.com\/Significant-Gravitas\/Auto-GPT."},{"key":"e_1_3_2_1_34_1","volume-title":"Shlok Natarajan, Nahum Maru, Hristo Todorov, Etash Guha, E Kelly Buchanan, Mayee Chen, Neel Guha, Christopher R\u00e9, et al.","author":"Saad-Falcon Jon","year":"2024","unstructured":"Jon Saad-Falcon, Adrian Gamarra Lafuente, Shlok Natarajan, Nahum Maru, Hristo Todorov, Etash Guha, E Kelly Buchanan, Mayee Chen, Neel Guha, Christopher R\u00e9, et al., 2024. Archon: An architecture search framework for inference-time techniques. arXiv preprint arXiv:2409.15254 (2024)."},{"key":"e_1_3_2_1_35_1","volume-title":"Outrageously large neural networks: The sparsely-gated mixture-of-experts layer. arXiv preprint arXiv:1701.06538","author":"Shazeer Noam","year":"2017","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:1701.06538 (2017)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.21203\/rs.3.rs-8437180\/v1"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2303.11366"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00280"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.3390\/computation13120290"},{"key":"e_1_3_2_1_40_1","volume-title":"Ryan Burnell, Libin Bai, Anmol Gulati, Garrett Tanzer, Damien Vincent, Zhufeng Pan, Shibo Wang, et al.","author":"Team Gemini","year":"2024","unstructured":"Gemini Team, Petko Georgiev, Ving Ian Lei, Ryan Burnell, Libin Bai, Anmol Gulati, Garrett Tanzer, Damien Vincent, Zhufeng Pan, Shibo Wang, et al., 2024. Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context. arXiv:2403.05530 [cs.CL] https:\/\/arxiv.org\/abs\/2403.05530"},{"key":"e_1_3_2_1_41_1","volume-title":"Rui Min Wu, and Junxian He","author":"Tong Yuxuan","year":"2024","unstructured":"Yuxuan Tong, Xiwen Zhang, Rui Wang, Rui Min Wu, and Junxian He. 2024. DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving. ArXiv, Vol. abs\/2407.13690 (2024). https:\/\/api.semanticscholar.org\/CorpusID:271270574"},{"key":"e_1_3_2_1_42_1","first-page":"5776","article-title":"Minilm: Deep self-attention distillation for task-agnostic compression of pre-trained transformers","volume":"33","author":"Wang Wenhui","year":"2020","unstructured":"Wenhui Wang, Furu Wei, Li Dong, Hangbo Bao, Nan Yang, and Ming Zhou. 2020. Minilm: Deep self-attention distillation for task-agnostic compression of pre-trained transformers. Advances in Neural Information Processing Systems, Vol. 33 (2020), 5776-5788.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_43_1","volume-title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models. In The Eleventh International Conference on Learning Representations.","author":"Wang Xuezhi","year":"2023","unstructured":"Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc V Le, Ed H. Chi, Sharan Narang, Aakanksha Chowdhery, and Denny Zhou. 2023b. Self-Consistency Improves Chain of Thought Reasoning in Language Models. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_3_2_1_44_1","unstructured":"Zhenhailong Wang Shaoguang Mao Wenshan Wu Tao Ge Furu Wei and Heng Ji. 2023a. Unleashing Cognitive Synergy in Large Language Models: A Task-Solving Agent through Multi-Persona Self-Collaboration. arXiv:2307.05300 pages. work in progress."},{"key":"e_1_3_2_1_45_1","volume-title":"Chi, Quoc Le, and Denny Zhou","author":"Wei Jason","year":"2022","unstructured":"Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Brian Ichter, Fei Xia, Ed Chi, Quoc Le, and Denny Zhou. 2022. Chain-of-Thought Prompting Elicits Reasoning in Large Language Models."},{"key":"e_1_3_2_1_46_1","unstructured":"Qingyun Wu Gagan Bansal Jieyu Zhang Yiran Wu Shaokun Zhang Erkang Zhu Beibin Li Li Jiang Xiaoyun Zhang and Chi Wang. 2023. AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation Framework."},{"key":"e_1_3_2_1_47_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 Jin Xu Jingren Zhou Jinze Bai Jinzheng He Junyang Lin Kai Dang Keming Lu Ke-Yang Chen Kexin Yang Mei Li Min 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 Yang Fan Yang Yao Yichang Zhang Yunyang Wan Yunfei Chu Zeyu Cui Zhenru Zhang and Zhi-Wei Fan. 2024. Qwen2 Technical Report. ArXiv Vol. abs\/2407.10671 (2024). https:\/\/api.semanticscholar.org\/CorpusID:271212307"},{"key":"e_1_3_2_1_48_1","volume-title":"ReAct: Synergizing Reasoning and Acting in Language Models. In The Eleventh International Conference on Learning Representations.","author":"Yao Shunyu","year":"2023","unstructured":"Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik R Narasimhan, and Yuan Cao. 2023. ReAct: Synergizing Reasoning and Acting in Language Models. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_3_2_1_49_1","volume-title":"X-MAS: Towards Building Multi-Agent Systems with Heterogeneous LLMs. ArXiv","author":"Ye Rui","year":"2025","unstructured":"Rui Ye, Xiangrui Liu, Qimin Wu, Xianghe Pang, Zhenfei Yin, Lei Bai, and Siheng Chen. 2025. X-MAS: Towards Building Multi-Agent Systems with Heterogeneous LLMs. ArXiv, Vol. abs\/2505.16997 (2025). https:\/\/api.semanticscholar.org\/CorpusID:278788601"},{"key":"e_1_3_2_1_50_1","volume-title":"EvoAgent: Towards Automatic Multi-Agent Generation via Evolutionary Algorithms. arXiv preprint arXiv:2406.14228","author":"Yuan Siyu","year":"2024","unstructured":"Siyu Yuan, Kaitao Song, Jiangjie Chen, Xu Tan, Dongsheng Li, and Deqing Yang. 2024. EvoAgent: Towards Automatic Multi-Agent Generation via Evolutionary Algorithms. arXiv preprint arXiv:2406.14228 (2024)."},{"key":"e_1_3_2_1_51_1","volume-title":"MasRouter: Learning to Route LLMs for Multi-Agent Systems. ArXiv","author":"Yue Yanwei","year":"2025","unstructured":"Yanwei Yue, Gui-Min Zhang, Boyang Liu, Guancheng Wan, Kun Wang, Dawei Cheng, and Yiyan Qi. 2025. MasRouter: Learning to Route LLMs for Multi-Agent Systems. ArXiv, Vol. abs\/2502.11133 (2025). https:\/\/api.semanticscholar.org\/CorpusID:276408048"},{"key":"e_1_3_2_1_52_1","volume-title":"Jeffrey Xu Yu, and Tianlong Chen","author":"Zhang Guibin","year":"2024","unstructured":"Guibin Zhang, Yanwei Yue, Zhixun Li, Sukwon Yun, Guancheng Wan, Kun Wang, Dawei Cheng, Jeffrey Xu Yu, and Tianlong Chen. 2024b. Cut the Crap: An Economical Communication Pipeline for LLM-based Multi-Agent Systems. arXiv preprint arXiv:2410.02506 (2024)."},{"key":"e_1_3_2_1_53_1","volume-title":"Multi-agent Architecture Search via Agentic Supernet. ArXiv","author":"Zhang Gui-Min","year":"2025","unstructured":"Gui-Min Zhang, Luyang Niu, Junfeng Fang, Kun Wang, Lei Bai, and Xiang Wang. 2025. Multi-agent Architecture Search via Agentic Supernet. ArXiv, Vol. abs\/2502.04180 (2025). https:\/\/api.semanticscholar.org\/CorpusID:276161505"},{"key":"e_1_3_2_1_54_1","volume-title":"Aflow: Automating agentic workflow generation. arXiv preprint arXiv:2410.10762","author":"Zhang Jiayi","year":"2024","unstructured":"Jiayi Zhang, Jinyu Xiang, Zhaoyang Yu, Fengwei Teng, Xionghui Chen, Jiaqi Chen, Mingchen Zhuge, Xin Cheng, Sirui Hong, Jinlin Wang, et al., 2024a. Aflow: Automating agentic workflow generation. arXiv preprint arXiv:2410.10762 (2024)."},{"key":"e_1_3_2_1_55_1","volume-title":"GRPO-LEAD: A Difficulty-Aware Reinforcement Learning Approach for Concise Mathematical Reasoning in Language Models. ArXiv","author":"Zhang Jixiao","year":"2025","unstructured":"Jixiao Zhang and Chunsheng Zuo. 2025. GRPO-LEAD: A Difficulty-Aware Reinforcement Learning Approach for Concise Mathematical Reasoning in Language Models. ArXiv, Vol. abs\/2504.09696 (2025). https:\/\/api.semanticscholar.org\/CorpusID:277780631"},{"key":"e_1_3_2_1_56_1","volume-title":"Competeai: Understanding the competition behaviors in large language model-based agents. arXiv preprint arXiv:2310.17512","author":"Zhao Qinlin","year":"2023","unstructured":"Qinlin Zhao, Jindong Wang, Yixuan Zhang, Yiqiao Jin, Kaijie Zhu, Hao Chen, and Xing Xie. 2023. Competeai: Understanding the competition behaviors in large language model-based agents. arXiv preprint arXiv:2310.17512 (2023)."},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.14778\/3685800.3685816"},{"key":"e_1_3_2_1_58_1","volume-title":"Forty-first International Conference on Machine Learning.","author":"Zhuge Mingchen","year":"2024","unstructured":"Mingchen Zhuge, Wenyi Wang, Louis Kirsch, Francesco Faccio, Dmitrii Khizbullin, and J\u00fcrgen Schmidhuber. 2024. GPTSwarm: Language Agents as Optimizable Graphs. In Forty-first International Conference on Machine Learning."},{"key":"e_1_3_2_1_59_1","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR).","author":"Zoph Barret","year":"2017","unstructured":"Barret Zoph and Quoc V Le. 2017. Neural Architecture Search with Reinforcement Learning. In Proceedings of the International Conference on Learning Representations (ICLR)."}],"event":{"name":"WWW '26: The ACM Web Conference 2026","location":"Dubai United Arab Emirates","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the ACM Web Conference 2026"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3774904.3792240","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T15:51:23Z","timestamp":1780674683000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3774904.3792240"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,12]]},"references-count":59,"alternative-id":["10.1145\/3774904.3792240","10.1145\/3774904"],"URL":"https:\/\/doi.org\/10.1145\/3774904.3792240","relation":{},"subject":[],"published":{"date-parts":[[2026,4,12]]},"assertion":[{"value":"2026-04-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}