{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T08:17:42Z","timestamp":1783153062745,"version":"3.54.6"},"publisher-location":"New York, NY, USA","reference-count":56,"publisher":"ACM","funder":[{"name":"Ministry of Education, Singapore","award":["RG18\/24"],"award-info":[{"award-number":["RG18\/24"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,13]]},"DOI":"10.1145\/3774904.3792202","type":"proceedings-article","created":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T13:28:36Z","timestamp":1777296516000},"page":"75-86","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["LBM: Hierarchical Large Auto-Bidding Model via Reasoning and Acting"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-0073-123X","authenticated-orcid":false,"given":"Yewen","family":"Li","sequence":"first","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-9227-7730","authenticated-orcid":false,"given":"Zhiyi","family":"Lyu","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8133-5010","authenticated-orcid":false,"given":"Peng","family":"Jiang","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6451-9299","authenticated-orcid":false,"given":"Qingpeng","family":"Cai","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1739-0868","authenticated-orcid":false,"given":"Fei","family":"Pan","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7064-7438","authenticated-orcid":false,"given":"Bo","family":"An","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9266-0780","authenticated-orcid":false,"given":"Peng","family":"Jiang","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,4,12]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"The Eleventh International Conference on Learning Representations, ICLR 2023","author":"Ajay Anurag","year":"2023","unstructured":"Anurag Ajay, Yilun Du, Abhi Gupta, Joshua B. Tenenbaum, Tommi S. Jaakkola, and Pulkit Agrawal. 2023. Is Conditional Generative Modeling all you need for Decision Making?. In The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023."},{"key":"e_1_3_2_1_2_1","volume-title":"Digi-Q: Learning VLM Q-Value Functions for Training Device-Control Agents. In The Thirteenth International Conference on Learning Representations, ICLR 2025","author":"Bai Hao","year":"2025","unstructured":"Hao Bai, Yifei Zhou, Li Erran Li, Sergey Levine, and Aviral Kumar. 2025. Digi-Q: Learning VLM Q-Value Functions for Training Device-Control Agents. In The Thirteenth International Conference on Learning Representations, ICLR 2025, Singapore, April 24-28, 2025. OpenReview.net."},{"key":"e_1_3_2_1_3_1","unstructured":"Jinze Bai Shuai Bai Yunfei Chu Zeyu Cui Kai Dang Xiaodong Deng Yang Fan Wenbin Ge Yu Han Fei Huang Binyuan Hui Luo Ji Mei Li Junyang Lin Runji Lin Dayiheng Liu Gao Liu Chengqiang Lu Keming Lu Jianxin Ma Rui Men Xingzhang Ren Xuancheng Ren Chuanqi Tan Sinan Tan Jianhong Tu Peng Wang Shijie Wang Wei Wang Shengguang Wu Benfeng Xu Jin Xu An Yang Hao Yang Jian Yang Shusheng Yang Yang Yao Bowen Yu Hongyi Yuan Zheng Yuan Jianwei Zhang Xingxuan Zhang Yichang Zhang Zhenru Zhang Chang Zhou Jingren Zhou Xiaohuan Zhou and Tianhang Zhu. 2023. Qwen Technical Report. arXiv preprint arXiv:2309.16609 (2023)."},{"key":"e_1_3_2_1_4_1","volume-title":"Proceedings of the 2017 ACM Conference on Economics and Computation, EC '17","author":"Santiago","year":"2017","unstructured":"Santiago R. Balseiro and Yonatan Gur. 2017. Learning in Repeated Auctions with Budgets: Regret Minimization and Equilibrium. In Proceedings of the 2017 ACM Conference on Economics and Computation, EC '17, Cambridge, MA, USA, June 26-30, 2017."},{"key":"e_1_3_2_1_5_1","first-page":"104","volume-title":"RTBAgent: A LLM-based Agent System for Real-Time Bidding. In Companion Proceedings of the ACM on Web Conference 2025, WWW 2025","author":"Cai Leng","year":"2025","unstructured":"Leng Cai, Junxuan He, Yikai Li, Junjie Liang, Yuanping Lin, Ziming Quan, Yawen Zeng, and Jin Xu. 2025. RTBAgent: A LLM-based Agent System for Real-Time Bidding. In Companion Proceedings of the ACM on Web Conference 2025, WWW 2025, Sydney, NSW, Australia, 28 April 2025 - 2 May 2025. ACM, 104-113."},{"key":"e_1_3_2_1_6_1","volume-title":"Forty-first International Conference on Machine Learning, ICML 2024","author":"Castiglioni Matteo","year":"2024","unstructured":"Matteo Castiglioni, Andrea Celli, and Christian Kroer. 2024. Online Learning under Budget and ROI Constraints via Weak Adaptivity. In Forty-first International Conference on Machine Learning, ICML 2024, Vienna, Austria, July 21-27, 2024."},{"key":"e_1_3_2_1_7_1","first-page":"15084","volume-title":"Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021","author":"Chen Lili","year":"2021","unstructured":"Lili Chen, Kevin Lu, Aravind Rajeswaran, Kimin Lee, Aditya Grover, Michael Laskin, Pieter Abbeel, Aravind Srinivas, and Igor Mordatch. 2021. Decision Transformer: Reinforcement Learning via Sequence Modeling. In Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, December 6-14, 2021, virtual. 15084-15097."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/2020408.2020604"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.64"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1257\/jep.23.3.37"},{"key":"e_1_3_2_1_11_1","volume-title":"Group-in-Group Policy Optimization for LLM Agent Training. CoRR","author":"Feng Lang","year":"2025","unstructured":"Lang Feng, Zhenghai Xue, Tingcong Liu, and Bo An. 2025. Group-in-Group Policy Optimization for LLM Agent Training. CoRR, Vol. abs\/2505.10978 (2025)."},{"key":"e_1_3_2_1_12_1","volume-title":"Proceedings of the 36th International Conference on Machine Learning, ICML 2019","volume":"2062","author":"Fujimoto Scott","year":"2019","unstructured":"Scott Fujimoto, David Meger, and Doina Precup. 2019. Off-Policy Deep Reinforcement Learning without Exploration. In Proceedings of the 36th International Conference on Machine Learning, ICML 2019, 9-15 June 2019, Long Beach, California, USA (Proceedings of Machine Learning Research, Vol. 97). PMLR, 2052-2062."},{"key":"e_1_3_2_1_13_1","unstructured":"Jingtong Gao Yewen Li Shuai Mao Peng Jiang Nan Jiang Yejing Wang Qingpeng Cai Fei Pan Kun Gai Bo An et al. 2025. Generative Auto-Bidding with Value-Guided Explorations. arXiv preprint arXiv:2504.14587 (2025)."},{"key":"e_1_3_2_1_14_1","volume-title":"Retrieval-augmented generation for large language models: A survey. arXiv preprint arXiv:2312.10997","author":"Gao Yunfan","year":"2023","unstructured":"Yunfan Gao, Yun Xiong, Xinyu Gao, Kangxiang Jia, Jinliu Pan, Yuxi Bi, Yixin Dai, Jiawei Sun, Haofen Wang, and Haofen Wang. 2023. Retrieval-augmented generation for large language models: A survey. arXiv preprint arXiv:2312.10997, Vol. 2, 1 (2023)."},{"key":"e_1_3_2_1_15_1","volume-title":"International Conference on Artificial Intelligence and Statistics, 25-27 April 2023, Palau de Congressos","author":"Golrezaei Negin","year":"2023","unstructured":"Negin Golrezaei, Patrick Jaillet, Jason Cheuk Nam Liang, and Vahab Mirrokni. 2023. Pricing against a Budget and ROI Constrained Buyer. In International Conference on Artificial Intelligence and Statistics, 25-27 April 2023, Palau de Congressos, Valencia, Spain."},{"key":"e_1_3_2_1_16_1","unstructured":"Daya Guo Dejian Yang Haowei Zhang Junxiao Song Ruoyu Zhang Runxin Xu Qihao Zhu Shirong Ma Peiyi Wang Xiao Bi et al. 2025. Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning. arXiv preprint arXiv:2501.12948 (2025)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671526"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467199"},{"key":"e_1_3_2_1_19_1","volume-title":"Planning with Diffusion for Flexible Behavior Synthesis. In International Conference on Machine Learning, ICML 2022","volume":"9915","author":"Janner Michael","year":"2022","unstructured":"Michael Janner, Yilun Du, Joshua B. Tenenbaum, and Sergey Levine. 2022. Planning with Diffusion for Flexible Behavior Synthesis. In International Conference on Machine Learning, ICML 2022, 17-23 July 2022, Baltimore, Maryland, USA (Proceedings of Machine Learning Research, Vol. 162). PMLR, 9902-9915."},{"key":"e_1_3_2_1_20_1","volume-title":"Offline Reinforcement Learning with Implicit Q-Learning. In The Tenth International Conference on Learning Representations, ICLR 2022","author":"Kostrikov Ilya","year":"2022","unstructured":"Ilya Kostrikov, Ashvin Nair, and Sergey Levine. 2022. Offline Reinforcement Learning with Implicit Q-Learning. In The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25-29, 2022."},{"key":"e_1_3_2_1_21_1","volume-title":"Conservative Q-Learning for Offline Reinforcement Learning. In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020","author":"Kumar Aviral","year":"2020","unstructured":"Aviral Kumar, Aurick Zhou, George Tucker, and Sergey Levine. 2020. Conservative Q-Learning for Offline Reinforcement Learning. In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"e_1_3_2_1_23_1","article-title":"Long-context LLMs Struggle with Long In-context","volume":"2025","author":"Li Tianle","year":"2025","unstructured":"Tianle Li, Ge Zhang, Quy Duc Do, Xiang Yue, and Wenhu Chen. 2025b. Long-context LLMs Struggle with Long In-context Learning. Trans. Mach. Learn. Res., Vol. 2025 (2025).","journal-title":"Learning. Trans. Mach. Learn. Res."},{"key":"e_1_3_2_1_24_1","volume-title":"Generative Auto-Bidding in Large-Scale Competitive Auctions via Diffusion Completer-Aligner. arXiv preprint arXiv:2509.03348","author":"Li Yewen","year":"2025","unstructured":"Yewen Li, Jingtong Gao, Nan Jiang, Shuai Mao, Ruyi An, Fei Pan, Xiangyu Zhao, Bo An, Qingpeng Cai, and Peng Jiang. 2025a. Generative Auto-Bidding in Large-Scale Competitive Auctions via Diffusion Completer-Aligner. arXiv preprint arXiv:2509.03348 (2025)."},{"key":"e_1_3_2_1_25_1","volume-title":"GAS: Generative Auto-bidding with Post-training Search. CoRR","author":"Li Yewen","year":"2024","unstructured":"Yewen Li, Shuai Mao, Jingtong Gao, Nan Jiang, Yunjian Xu, Qingpeng Cai, Fei Pan, Peng Jiang, and Bo An. 2024. GAS: Generative Auto-bidding with Post-training Search. CoRR, Vol. abs\/2412.17018 (2024)."},{"key":"e_1_3_2_1_26_1","volume-title":"Constrained Decision Transformer for Offline Safe Reinforcement Learning. In International Conference on Machine Learning, ICML 2023","volume":"21630","author":"Liu Zuxin","year":"2023","unstructured":"Zuxin Liu, Zijian Guo, Yihang Yao, Zhepeng Cen, Wenhao Yu, Tingnan Zhang, and Ding Zhao. 2023. Constrained Decision Transformer for Offline Safe Reinforcement Learning. In International Conference on Machine Learning, ICML 2023, 23-29 July 2023, Honolulu, Hawaii, USA (Proceedings of Machine Learning Research, Vol. 202). PMLR, 21611-21630."},{"key":"e_1_3_2_1_27_1","volume-title":"Decoupled Weight Decay Regularization. In International Conference on Learning Representations.","author":"Loshchilov Ilya","unstructured":"Ilya Loshchilov and Frank Hutter. [n.d.]. Decoupled Weight Decay Regularization. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_28_1","volume-title":"Mcp-universe: Benchmarking large language models with real-world model context protocol servers. arXiv preprint arXiv:2508.14704","author":"Luo Ziyang","year":"2025","unstructured":"Ziyang Luo, Zhiqi Shen, Wenzhuo Yang, Zirui Zhao, Prathyusha Jwalapuram, Amrita Saha, Doyen Sahoo, Silvio Savarese, Caiming Xiong, and Junnan Li. 2025. Mcp-universe: Benchmarking large language models with real-world model context protocol servers. arXiv preprint arXiv:2508.14704 (2025)."},{"key":"e_1_3_2_1_29_1","volume-title":"Sustainable Online Reinforcement Learning for Auto-bidding. In Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022","author":"Mou Zhiyu","year":"2022","unstructured":"Zhiyu Mou, Yusen Huo, Rongquan Bai, Mingzhou Xie, Chuan Yu, Jian Xu, and Bo Zheng. 2022. Sustainable Online Reinforcement Learning for Auto-bidding. In Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans, LA, USA, November 28 - December 9, 2022."},{"key":"e_1_3_2_1_30_1","volume-title":"5th International Workshop, WINE 2009, Rome, Italy, December 14-18, 2009. Proceedings (Lecture Notes in Computer Science","volume":"12","author":"Muthukrishnan S.","year":"2009","unstructured":"S. Muthukrishnan. 2009. Ad Exchanges: Research Issues. In Internet and Network Economics, 5th International Workshop, WINE 2009, Rome, Italy, December 14-18, 2009. Proceedings (Lecture Notes in Computer Science, Vol. 5929). Springer, 1-12."},{"key":"e_1_3_2_1_31_1","volume-title":"Accelerating Online Reinforcement Learning with Offline Datasets. CoRR","author":"Nair Ashvin","year":"2020","unstructured":"Ashvin Nair, Murtaza Dalal, Abhishek Gupta, and Sergey Levine. 2020. Accelerating Online Reinforcement Learning with Offline Datasets. CoRR, Vol. abs\/2006.09359 (2020)."},{"key":"e_1_3_2_1_32_1","volume-title":"Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning. CoRR","author":"Peng Xue Bin","year":"2019","unstructured":"Xue Bin Peng, Aviral Kumar, Grace Zhang, and Sergey Levine. 2019. Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning. CoRR, Vol. abs\/1910.00177 (2019)."},{"key":"e_1_3_2_1_33_1","volume-title":"Fast: Efficient action tokenization for vision-language-action models. arXiv preprint arXiv:2501.09747","author":"Pertsch Karl","year":"2025","unstructured":"Karl Pertsch, Kyle Stachowicz, Brian Ichter, Danny Driess, Suraj Nair, Quan Vuong, Oier Mees, Chelsea Finn, and Sergey Levine. 2025. Fast: Efficient action tokenization for vision-language-action models. arXiv preprint arXiv:2501.09747 (2025)."},{"key":"e_1_3_2_1_34_1","volume-title":"Proceedings of the Twenty-Fourth International Conference (ICML 2007), Corvallis, Oregon, USA, June 20-24, 2007 (ACM International Conference Proceeding Series","volume":"750","author":"Peters Jan","year":"2007","unstructured":"Jan Peters and Stefan Schaal. 2007. Reinforcement learning by reward-weighted regression for operational space control. In Machine Learning, Proceedings of the Twenty-Fourth International Conference (ICML 2007), Corvallis, Oregon, USA, June 20-24, 2007 (ACM International Conference Proceeding Series, Vol. 227). ACM, 745-750."},{"key":"e_1_3_2_1_35_1","volume-title":"Juan Carlos Niebles, et al","author":"Prabhakar Akshara","year":"2025","unstructured":"Akshara Prabhakar, Zuxin Liu, Ming Zhu, Jianguo Zhang, Tulika Awalgaonkar, Shiyu Wang, Zhiwei Liu, Haolin Chen, Thai Hoang, Juan Carlos Niebles, et al., 2025. Apigen-mt: Agentic pipeline for multi-turn data generation via simulated agent-human interplay. arXiv preprint arXiv:2504.03601 (2025)."},{"key":"e_1_3_2_1_36_1","unstructured":"Alec Radford Jeffrey Wu Rewon Child David Luan Dario Amodei Ilya Sutskever et al. 2019. Language models are unsupervised multitask learners. OpenAI blog Vol. 1 8 (2019) 9."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2609"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2017.2775228"},{"key":"e_1_3_2_1_39_1","volume-title":"Proximal Policy Optimization Algorithms. CoRR","author":"Schulman John","year":"2017","unstructured":"John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, and Oleg Klimov. 2017. Proximal Policy Optimization Algorithms. CoRR, Vol. abs\/1707.06347 (2017)."},{"key":"e_1_3_2_1_40_1","volume-title":"Unleashing the Power of Pre-trained Language Models for Offline Reinforcement Learning. In The Twelfth International Conference on Learning Representations, ICLR 2024","author":"Shi Ruizhe","year":"2024","unstructured":"Ruizhe Shi, Yuyao Liu, Yanjie Ze, Simon Shaolei Du, and Huazhe Xu. 2024. Unleashing the Power of Pre-trained Language Models for Offline Reinforcement Learning. In The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024. OpenReview.net."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0377"},{"key":"e_1_3_2_1_42_1","volume-title":"AuctionNet: A Novel Benchmark for Decision-Making in Large-Scale Games. In The Thirty-eight Conference on Neural Information Processing Systems Datasets and Benchmarks Track.","author":"Su Kefan","year":"2024","unstructured":"Kefan Su, Yusen Huo, Zhilin Zhang, Shuai Dou, Chuan Yu, Jian Xu, Zongqing Lu, and Bo Zheng. 2024. AuctionNet: A Novel Benchmark for Decision-Making in Large-Scale Games. In The Thirty-eight Conference on Neural Information Processing Systems Datasets and Benchmarks Track."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0088"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/2684822.2697041"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1561\/1500000049"},{"key":"e_1_3_2_1_46_1","first-page":"6291","volume-title":"Exponentially Weighted Imitation Learning for Batched Historical Data. In Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018","author":"Wang Qing","year":"2018","unstructured":"Qing Wang, Jiechao Xiong, Lei Han, Peng Sun, Han Liu, and Tong Zhang. 2018. Exponentially Weighted Imitation Learning for Batched Historical Data. In Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, NeurIPS 2018, December 3-8, 2018, Montr\u00e9al, Canada. 6291-6300."},{"key":"e_1_3_2_1_47_1","volume-title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models. In Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022","author":"Wei Jason","year":"2022","unstructured":"Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Brian Ichter, Fei Xia, Ed H. Chi, Quoc V. Le, and Denny Zhou. 2022. Chain-of-Thought Prompting Elicits Reasoning in Large Language Models. In Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans, LA, USA, November 28 - December 9, 2022."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3488560.3498373"},{"key":"e_1_3_2_1_49_1","volume-title":"DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads. In The Thirteenth International Conference on Learning Representations, ICLR 2025","author":"Xiao Guangxuan","year":"2025","unstructured":"Guangxuan Xiao, Jiaming Tang, Jingwei Zuo, Junxian Guo, Shang Yang, Haotian Tang, Yao Fu, and Song Han. 2025. DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads. In The Thirteenth International Conference on Learning Representations, ICLR 2025, Singapore, April 24-28, 2025. OpenReview.net."},{"key":"e_1_3_2_1_50_1","volume-title":"A-mem: Agentic memory for llm agents. arXiv preprint arXiv:2502.12110","author":"Xu Wujiang","year":"2025","unstructured":"Wujiang Xu, Kai Mei, Hang Gao, Juntao Tan, Zujie Liang, and Yongfeng Zhang. 2025. A-mem: Agentic memory for llm agents. arXiv preprint arXiv:2502.12110 (2025)."},{"key":"e_1_3_2_1_51_1","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_2_1_52_1","volume-title":"Online Convex Optimization with Stochastic Constraints. In Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017","author":"Yu Hao","year":"2017","unstructured":"Hao Yu, Michael J. Neely, and Xiaohan Wei. 2017. Online Convex Optimization with Stochastic Constraints. In Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4-9, 2017, Long Beach, CA, USA. 1428-1438."},{"key":"e_1_3_2_1_53_1","volume-title":"Forty-second International Conference on Machine Learning.","author":"Zhao Wenhao","year":"2025","unstructured":"Wenhao Zhao, Qiushui Xu, Linjie Xu, Lei Song, Jinyu Wang, Chunlai Zhou, and Jiang Bian. 2025. Unveiling markov heads in pretrained language models for offline reinforcement learning. In Forty-second International Conference on Machine Learning."},{"key":"e_1_3_2_1_54_1","volume-title":"Group Sequence Policy Optimization. CoRR","author":"Zheng Chujie","year":"1807","unstructured":"Chujie Zheng, Shixuan Liu, Mingze Li, Xiong-Hui Chen, Bowen Yu, Chang Gao, Kai Dang, Yuqiong Liu, Rui Men, An Yang, Jingren Zhou, and Junyang Lin. 2025. Group Sequence Policy Optimization. CoRR, Vol. abs\/2507.18071 (2025)."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-demos.38"},{"key":"e_1_3_2_1_56_1","volume-title":"Webarena: A realistic web environment for building autonomous agents. arXiv preprint arXiv:2307.13854","author":"Zhou Shuyan","year":"2023","unstructured":"Shuyan Zhou, Frank F Xu, Hao Zhu, Xuhui Zhou, Robert Lo, Abishek Sridhar, Xianyi Cheng, Tianyue Ou, Yonatan Bisk, Daniel Fried, et al., 2023. Webarena: A realistic web environment for building autonomous agents. arXiv preprint arXiv:2307.13854 (2023)."}],"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\/3774904.3792202","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T07:41:59Z","timestamp":1783150919000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3774904.3792202"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,12]]},"references-count":56,"alternative-id":["10.1145\/3774904.3792202","10.1145\/3774904"],"URL":"https:\/\/doi.org\/10.1145\/3774904.3792202","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"}}]}}