{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T18:04:24Z","timestamp":1784138664949,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":83,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T00:00:00Z","timestamp":1784419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"National Natural Science Foundation of China","award":["625B2178"],"award-info":[{"award-number":["625B2178"]}]},{"name":"National Natural Science Foundation of China","award":["62272467"],"award-info":[{"award-number":["62272467"]}]},{"name":"Beijing Major Science and Technology Project under Contract","award":["Z25110000842500"],"award-info":[{"award-number":["Z25110000842500"]}]},{"name":"Beijing Key Laboratory of Research on Large Models and Intelligent Governance and Engineering Research Center of Next-Generation Intelligent Search and Recommendation, MOE","award":["-"],"award-info":[{"award-number":["-"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,20]]},"DOI":"10.1145\/3805712.3809712","type":"proceedings-article","created":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T17:06:26Z","timestamp":1784135186000},"page":"301-312","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Tool-Star: Empowering Multi-Tool Collaborative Web Agent via Reinforcement Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2318-0281","authenticated-orcid":false,"given":"Guanting","family":"Dong","sequence":"first","affiliation":[{"name":"Renmin University of China, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-3142-5884","authenticated-orcid":false,"given":"Yifei","family":"Chen","sequence":"additional","affiliation":[{"name":"Renmin University of China, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-0708-418X","authenticated-orcid":false,"given":"Xiaoxi","family":"Li","sequence":"additional","affiliation":[{"name":"Renmin University of China, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4808-1534","authenticated-orcid":false,"given":"Jiajie","family":"Jin","sequence":"additional","affiliation":[{"name":"Renmin University of China, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4011-5673","authenticated-orcid":false,"given":"Hongjin","family":"Qian","sequence":"additional","affiliation":[{"name":"Beijing Academy of Artificial Intelligence, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9432-3251","authenticated-orcid":false,"given":"Yutao","family":"Zhu","sequence":"additional","affiliation":[{"name":"Renmin University of China, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4499-7581","authenticated-orcid":false,"given":"Hangyu","family":"Mao","sequence":"additional","affiliation":[{"name":"Institute of Microelectronics, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-8550-279X","authenticated-orcid":false,"given":"Guorui","family":"Zhou","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9781-948X","authenticated-orcid":false,"given":"Zhicheng","family":"Dou","sequence":"additional","affiliation":[{"name":"Renmin University of China, Beijing, Beijng, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9777-9676","authenticated-orcid":false,"given":"Ji-Rong","family":"Wen","sequence":"additional","affiliation":[{"name":"Renmin University of China, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,19]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Kaiyuan Chen Yixin Ren Yang Liu Xiaobo Hu Haotong Tian Tianbao Xie Fangfu Liu Haoye Zhang Hongzhang Liu Yuan Gong et al. 2025b. xbench: Tracking Agents Productivity Scaling with Profession-Aligned Real-World Evaluations. arXiv preprint arXiv:2506.13651 (2025)."},{"key":"e_1_3_2_1_2_1","unstructured":"Mingyang Chen Tianpeng Li Haoze Sun Yijie Zhou Chenzheng Zhu Haofen Wang Jeff Z. Pan Wen Zhang Huajun Chen Fan Yang Zenan Zhou and Weipeng Chen. 2025a. ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning. arXiv:2503.19470 [cs.AI] https:\/\/arxiv.org\/abs\/2503.19470"},{"key":"e_1_3_2_1_3_1","volume-title":"Cohen","author":"Chen Wenhu","year":"2023","unstructured":"Wenhu Chen, Xueguang Ma, Xinyi Wang, and William W. Cohen. 2023. Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks. Trans. Mach. Learn. Res., V2023 (2023). https:\/\/openreview.net\/forum?id=YfZ4ZPt8zd"},{"key":"e_1_3_2_1_4_1","volume-title":"Vabs\/2110.14168","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. CoRR, Vabs\/2110.14168 (2021). arXiv:2110.14168 https:\/\/arxiv.org\/abs\/2110.14168"},{"key":"e_1_3_2_1_5_1","volume-title":"FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning. CoRR","author":"Dao Tri","year":"2023","unstructured":"Tri Dao. 2023. FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning. CoRR (2023)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2508.12800"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2024.ACL-LONG.12"},{"key":"e_1_3_2_1_8_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_9_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2508.10874"},{"key":"e_1_3_2_1_10_1","unstructured":"Runnan Fang Shihao Cai Baixuan Li Jialong Wu Guangyu Li Wenbiao Yin Xinyu Wang Xiaobin Wang Liangcai Su Zhen Zhang et al. 2025. Towards General Agentic Intelligence via Environment Scaling. arXiv preprint arXiv:2509.13311 (2025)."},{"key":"e_1_3_2_1_11_1","unstructured":"Jiazhan Feng Shijue Huang Xingwei Qu Ge Zhang Yujia Qin Baoquan Zhong Chengquan Jiang Jinxin Chi and Wanjun Zhong. 2025. ReTool: Reinforcement Learning for Strategic Tool Use in LLMs. arXiv:2504.11536 [cs.CL] https:\/\/arxiv.org\/abs\/2504.11536"},{"key":"e_1_3_2_1_12_1","unstructured":"Jiaxuan Gao Wei Fu Minyang Xie Shusheng Xu Chuyi He Zhiyu Mei Banghua Zhu and Yi Wu. 2025. Beyond Ten Turns: Unlocking Long-Horizon Agentic Search with Large-Scale Asynchronous RL. arXiv:2508.07976 [cs.CL] https:\/\/arxiv.org\/abs\/2508.07976"},{"key":"e_1_3_2_1_13_1","volume-title":"ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving. In The Twelfth International Conference on Learning Representations, ICLR 2024","author":"Gou Zhibin","year":"2024","unstructured":"Zhibin Gou, Zhihong Shao, Yeyun Gong, Yelong Shen, Yujiu Yang, Minlie Huang, Nan Duan, and Weizhu Chen. 2024. ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving. In The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024. OpenReview.net. https:\/\/openreview.net\/forum?id=Ep0TtjVoap"},{"key":"e_1_3_2_1_14_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_15_1","volume-title":"Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks 1, NeurIPS Datasets and Benchmarks 2021","author":"Hendrycks Dan","year":"2021","unstructured":"Dan Hendrycks, Collin Burns, Saurav Kadavath, Akul Arora, Steven Basart, Eric Tang, Dawn Song, and Jacob Steinhardt. 2021. Measuring Mathematical Problem Solving With the MATH Dataset. In Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks 1, NeurIPS Datasets and Benchmarks 2021, December 2021, virtual, Joaquin Vanschoren and Sai-Kit Yeung (Eds.). https:\/\/datasets-benchmarks-proceedings.neurips.cc\/paper\/2021\/hash\/be83ab3ecd0db773eb2dc1b0a17836a1-Abstract-round2.html"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2020.COLING-MAIN.580"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2023.FINDINGS-ACL.67"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2505.07596"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2508.12790"},{"key":"e_1_3_2_1_20_1","unstructured":"Aaron Hurst Adam Lerer Adam P Goucher Adam Perelman Aditya Ramesh Aidan Clark AJ Ostrow Akila Welihinda Alan Hayes Alec Radford et al. 2024. Gpt-4o system card. arXiv preprint arXiv:2410.21276 (2024)."},{"key":"e_1_3_2_1_21_1","unstructured":"Dongfu Jiang Yi Lu Zhuofeng Li Zhiheng Lyu Ping Nie Haozhe Wang Alex Su Hui Chen Kai Zou Chao Du et al. 2025. VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use. arXiv preprint arXiv:2509.01055 (2025)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2412.12881"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2503.09516"},{"key":"e_1_3_2_1_24_1","volume-title":"Ledell Wu, Sergey Edunov, Danqi Chen, and Wen-tau Yih.","author":"Karpukhin Vladimir","year":"2020","unstructured":"Vladimir Karpukhin, Barlas Oguz, Sewon Min, Patrick SH Lewis, Ledell Wu, Sergey Edunov, Danqi Chen, and Wen-tau Yih. 2020. Dense Passage Retrieval for Open-Domain Question Answering. In EMNLP (1). 6769-6781."},{"key":"e_1_3_2_1_25_1","volume-title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020","author":"Lewis Patrick","year":"2020","unstructured":"Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich K\u00fcttler, Mike Lewis, Wen-tau Yih, Tim Rockt\u00e4schel, Sebastian Riedel, and Douwe Kiela. 2020. Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual, Hugo Larochelle, Marc'Aurelio Ranzato, Raia Hadsell, Maria-Florina Balcan, and Hsuan-Tien Lin (Eds.). https:\/\/proceedings.neurips.cc\/paper\/2020\/hash\/6b493230205f780e1bc26945df7481e5-Abstract.html"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2407.04078"},{"key":"e_1_3_2_1_27_1","volume-title":"Forty-first International Conference on Machine Learning, ICML 2024","author":"Li Chengshu","year":"2024","unstructured":"Chengshu Li, Jacky Liang, Andy Zeng, Xinyun Chen, Karol Hausman, Dorsa Sadigh, Sergey Levine, Li Fei-Fei, Fei Xia, and Brian Ichter. 2024b. Chain of Code: Reasoning with a Language Model-Augmented Code Emulator. In Forty-first International Conference on Machine Learning, ICML 2024, Vienna, Austria, July 21-27, 2024. OpenReview.net. https:\/\/openreview.net\/forum?id=vKtomqlSxm"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2503.04625"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2503.04625"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2507.02592"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2508.13167"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2501.05366"},{"key":"e_1_3_2_1_33_1","volume-title":"WebThinker: Empowering Large Reasoning Models with Deep Research Capability. arXiv preprint arXiv:2504.21776","author":"Li Xiaoxi","year":"2025","unstructured":"Xiaoxi Li, Jiajie Jin, Guanting Dong, Hongjin Qian, Yutao Zhu, Yongkang Wu, Ji-Rong Wen, and Zhicheng Dou. 2025b. WebThinker: Empowering Large Reasoning Models with Deep Research Capability. arXiv preprint arXiv:2504.21776 (2025)."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2503.23383"},{"key":"e_1_3_2_1_35_1","volume-title":"The Twelfth International Conference on Learning Representations, ICLR 2024","author":"Lightman Hunter","year":"2024","unstructured":"Hunter Lightman, Vineet Kosaraju, Yuri Burda, Harrison Edwards, Bowen Baker, Teddy Lee, Jan Leike, John Schulman, Ilya Sutskever, and Karl Cobbe. 2024. Let's Verify Step by Step. In The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024. OpenReview.net. https:\/\/openreview.net\/forum?id=v8L0pN6EOi"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2502.11271"},{"key":"e_1_3_2_1_37_1","volume-title":"The Twelfth International Conference on Learning Representations, ICLR 2024","author":"Mialon Gr\u00e9goire","year":"2024","unstructured":"Gr\u00e9goire Mialon, Cl\u00e9mentine Fourrier, Thomas Wolf, Yann LeCun, and Thomas Scialom. 2024. GAIA: a benchmark for General AI Assistants. In The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024. OpenReview.net. https:\/\/openreview.net\/forum?id=fibxvahvs3"},{"key":"e_1_3_2_1_38_1","unstructured":"Yingqian Min Zhipeng Chen Jinhao Jiang Jie Chen Jia Deng Yiwen Hu Yiru Tang Jiapeng Wang Xiaoxue Cheng Huatong Song et al. 2024. Imitate explore and self-improve: A reproduction report on slow-thinking reasoning systems. arXiv preprint arXiv:2412.09413 (2024)."},{"key":"e_1_3_2_1_39_1","unstructured":"OpenAI. 2024. Learning to Reason with LLMs. https:\/\/openai.com\/index\/learning-to-reason-with-llms"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2501.14249"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2023.FINDINGS-EMNLP.378"},{"key":"e_1_3_2_1_42_1","volume-title":"Qi He, Hongru Wang, Xiusi Chen, Dilek Hakkani-T\u00fcr, Gokhan Tur, and Heng Ji.","author":"Qian Cheng","year":"2025","unstructured":"Cheng Qian, Emre Can Acikgoz, Qi He, Hongru Wang, Xiusi Chen, Dilek Hakkani-T\u00fcr, Gokhan Tur, and Heng Ji. 2025a. Toolrl: Reward is all tool learning needs. arXiv preprint arXiv:2504.13958 (2025)."},{"key":"e_1_3_2_1_43_1","volume-title":"Qi He, Hongru Wang, Xiusi Chen, Dilek Hakkani-T\u00fcr, Gokhan Tur, and Heng Ji.","author":"Qian Cheng","year":"2025","unstructured":"Cheng Qian, Emre Can Acikgoz, Qi He, Hongru Wang, Xiusi Chen, Dilek Hakkani-T\u00fcr, Gokhan Tur, and Heng Ji. 2025b. ToolRL: Reward is All Tool Learning Needs. arXiv:2504.13958 [cs.LG] https:\/\/arxiv.org\/abs\/2504.13958"},{"key":"e_1_3_2_1_44_1","volume-title":"ACL 2025","author":"Qian Cheng","year":"2025","unstructured":"Cheng Qian, Emre Can Acikgoz, Hongru Wang, Xiusi Chen, Avirup Sil, Dilek Hakkani-T\u00fcr, Gokhan Tur, and Heng Ji. 2025c. SMART: Self-Aware Agent for Tool Overuse Mitigation. In Findings of the Association for Computational Linguistics, ACL 2025, Vienna, Austria, July 27 - August 1, 2025. 4604-4621. https:\/\/aclanthology.org\/2025.findings-acl.239\/"},{"key":"e_1_3_2_1_45_1","unstructured":"Zile Qiao Guoxin Chen Xuanzhong Chen Donglei Yu Wenbiao Yin Xinyu Wang Zhen Zhang Baixuan Li Huifeng Yin Kuan Li et al. 2025. WebResearcher: Unleashing unbounded reasoning capability in Long-Horizon Agents. arXiv preprint arXiv:2509.13309 (2025)."},{"key":"e_1_3_2_1_46_1","volume-title":"Replication Journey: A Strategic Progress Report-Part 1. arXiv preprint arXiv:2410.18982","author":"Qin Yiwei","year":"2024","unstructured":"Yiwei Qin, Xuefeng Li, Haoyang Zou, Yixiu Liu, Shijie Xia, Zhen Huang, Yixin Ye, Weizhe Yuan, Hector Liu, Yuanzhi Li, et al., 2024. O1 Replication Journey: A Strategic Progress Report-Part 1. arXiv preprint arXiv:2410.18982 (2024)."},{"key":"e_1_3_2_1_47_1","unstructured":"Qwen: An Yang Baosong Yang Beichen Zhang Binyuan Hui Bo Zheng Bowen Yu Chengyuan Li Dayiheng Liu Fei Huang Haoran Wei Huan Lin Jian Yang Jianhong Tu Jianwei Zhang Jianxin Yang Jiaxi Yang Jingren Zhou Junyang Lin Kai Dang Keming Lu Keqin Bao Kexin Yang Le Yu Mei Li Mingfeng Xue Pei Zhang Qin Zhu Rui Men Runji Lin Tianhao Li Tingyu Xia Xingzhang Ren Xuancheng Ren Yang Fan Yang Su Yichang Zhang Yu Wan Yuqiong Liu Zeyu Cui Zhenru Zhang and Zihan Qiu. 2024. Qwen2.5 Technical Report. arXiv:2412.15115 [cs.CL] https:\/\/arxiv.org\/abs\/2412.15115"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"crossref","unstructured":"Jeff Rasley Samyam Rajbhandari Olatunji Ruwase and Yuxiong He. 2020. DeepSpeed: System Optimizations Enable Training Deep Learning Models with Over 100 Billion Parameters (KDD '20).","DOI":"10.1145\/3394486.3406703"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2402.03300"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3689031.3696075"},{"key":"e_1_3_2_1_51_1","volume-title":"Agentic Reasoning and Tool Integration for LLMs via Reinforcement Learning. arXiv preprint arXiv:2505.01441","author":"Singh Joykirat","year":"2025","unstructured":"Joykirat Singh, Raghav Magazine, Yash Pandya, and Akshay Nambi. 2025. Agentic Reasoning and Tool Integration for LLMs via Reinforcement Learning. arXiv preprint arXiv:2505.01441 (2025)."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2503.05592"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2505.17005"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1007\/S11263-022-01611-X"},{"key":"e_1_3_2_1_55_1","unstructured":"Liangcai Su Zhen Zhang Guangyu Li Zhuo Chen Chenxi Wang Maojia Song Xinyu Wang Kuan Li Jialong Wu Xuanzhong Chen et al. 2025. Scaling agents via continual pre-training. arXiv preprint arXiv:2509.13310 (2025)."},{"key":"e_1_3_2_1_56_1","unstructured":"Hao Sun Zile Qiao Jiayan Guo Xuanbo Fan Yingyan Hou Yong Jiang Pengjun Xie Yan Zhang Fei Huang and Jingren Zhou. 2025. ZeroSearch: Incentivize the Search Capability of LLMs without Searching. arXiv:2505.04588 [cs.CL] https:\/\/arxiv.org\/abs\/2505.04588"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2312.11562"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2507.15061"},{"key":"e_1_3_2_1_59_1","unstructured":"Kimi Team Angang Du Bofei Gao Bowei Xing Changjiu Jiang Cheng Chen Cheng Li Chenjun Xiao Chenzhuang Du Chonghua Liao et al. 2025. Kimi k1. 5: Scaling reinforcement learning with llms. arXiv preprint arXiv:2501.12599 (2025)."},{"key":"e_1_3_2_1_60_1","volume-title":"Qwq: Reflect deeply on the boundaries of the unknown. Hugging Face","author":"Team Qwen","year":"2024","unstructured":"Qwen Team. 2024. Qwq: Reflect deeply on the boundaries of the unknown. Hugging Face (2024)."},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2302.13971"},{"key":"e_1_3_2_1_62_1","volume-title":"Interleaving retrieval with chain-of-thought reasoning for knowledge-intensive multi-step questions. arXiv preprint arXiv:2212.10509","author":"Trivedi Harsh","year":"2022","unstructured":"Harsh Trivedi, Niranjan Balasubramanian, Tushar Khot, and Ashish Sabharwal. 2022a. Interleaving retrieval with chain-of-thought reasoning for knowledge-intensive multi-step questions. arXiv preprint arXiv:2212.10509 (2022)."},{"key":"e_1_3_2_1_63_1","volume-title":"V10","author":"Trivedi Harsh","year":"2022","unstructured":"Harsh Trivedi, Niranjan Balasubramanian, Tushar Khot, and Ashish Sabharwal. 2022b. MuSiQue: Multihop Questions via Single-hop Question Composition. Transactions of the Association for Computational Linguistics, V10 (2022), 539-554."},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2506.00886"},{"key":"e_1_3_2_1_65_1","volume-title":"OTC: Optimal Tool Calls via Reinforcement Learning. arXiv preprint arXiv:2504.14870","author":"Wang Hongru","year":"2025","unstructured":"Hongru Wang, Cheng Qian, Wanjun Zhong, Xiusi Chen, Jiahao Qiu, Shijue Huang, Bowen Jin, Mengdi Wang, Kam-Fai Wong, and Heng Ji. 2025b. OTC: Optimal Tool Calls via Reinforcement Learning. arXiv preprint arXiv:2504.14870 (2025)."},{"key":"e_1_3_2_1_66_1","volume-title":"Text embeddings by weakly-supervised contrastive pre-training. arXiv preprint arXiv:2212.03533","author":"Wang Liang","year":"2022","unstructured":"Liang Wang, Nan Yang, Xiaolong Huang, Binxing Jiao, Linjun Yang, Daxin Jiang, Rangan Majumder, and Furu Wei. 2022. Text embeddings by weakly-supervised contrastive pre-training. arXiv preprint arXiv:2212.03533 (2022)."},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2507.21836"},{"key":"e_1_3_2_1_68_1","unstructured":"Jialong Wu Baixuan Li Runnan Fang Wenbiao Yin Liwen Zhang Zhengwei Tao Dingchu Zhang Zekun Xi Yong Jiang Pengjun Xie Fei Huang and Jingren Zhou. 2025a. WebDancer: Towards Autonomous Information Seeking Agency. arXiv:2505.22648 [cs.CL] https:\/\/arxiv.org\/abs\/2505.22648"},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2501.07572"},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2502.04644"},{"key":"e_1_3_2_1_71_1","volume-title":"ReSum: Unlocking Long-Horizon Search Intelligence via Context Summarization. arXiv preprint arXiv:2509.13313","author":"Wu Xixi","year":"2025","unstructured":"Xixi Wu, Kuan Li, Yida Zhao, Liwen Zhang, Litu Ou, Huifeng Yin, Zhongwang Zhang, Yong Jiang, Pengjun Xie, Fei Huang, Minhao Cheng, Shuai Wang, Hong Cheng, and Jingren Zhou. 2025b. ReSum: Unlocking Long-Horizon Search Intelligence via Context Summarization. arXiv preprint arXiv:2509.13313 (2025)."},{"key":"e_1_3_2_1_72_1","volume-title":"LIMI: Less is More for Agency. arXiv preprint arXiv:2509.17567","author":"Xiao Yang","year":"2025","unstructured":"Yang Xiao, Mohan Jiang, Jie Sun, Keyu Li, Jifan Lin, Yumin Zhuang, Ji Zeng, Shijie Xia, Qishuo Hua, Xuefeng Li, et al., 2025. LIMI: Less is More for Agency. arXiv preprint arXiv:2509.17567 (2025)."},{"key":"e_1_3_2_1_73_1","volume-title":"SimpleTIR: End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning. arXiv preprint arXiv:2509.02479","author":"Xue Zhenghai","year":"2025","unstructured":"Zhenghai Xue, Longtao Zheng, Qian Liu, Yingru Li, Xiaosen Zheng, Zejun Ma, and Bo An. 2025. SimpleTIR: End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning. arXiv preprint arXiv:2509.02479 (2025)."},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1259"},{"key":"e_1_3_2_1_75_1","volume-title":"React: Synergizing reasoning and acting in language models. In The eleventh international conference on learning representations.","author":"Yao Shunyu","year":"2022","unstructured":"Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik R 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_2_1_76_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2408.15565"},{"key":"e_1_3_2_1_77_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2308.01825"},{"key":"e_1_3_2_1_78_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2503.18892"},{"key":"e_1_3_2_1_79_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2505.22501"},{"key":"e_1_3_2_1_80_1","unstructured":"Guibin Zhang Hejia Geng Xiaohang Yu Zhenfei Yin Zaibin Zhang Zelin Tan Heng Zhou Zhongzhi Li Xiangyuan Xue Yijiang Li et al. 2025a. The landscape of agentic reinforcement learning for llms: A survey. arXiv preprint arXiv:2509.02547 (2025)."},{"key":"e_1_3_2_1_81_1","volume-title":"DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environments. arXiv preprint arXiv:2504.03160","author":"Zheng Yuxiang","year":"2025","unstructured":"Yuxiang Zheng, Dayuan Fu, Xiangkun Hu, Xiaojie Cai, Lyumanshan Ye, Pengrui Lu, and Pengfei Liu. 2025. DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environments. arXiv preprint arXiv:2504.03160 (2025)."},{"key":"e_1_3_2_1_82_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-demos.38"},{"key":"e_1_3_2_1_83_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2508.15202"}],"event":{"name":"SIGIR '26: The 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Melbourne VIC Australia","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"deposited":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T17:13:16Z","timestamp":1784135596000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805712.3809712"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,19]]},"references-count":83,"alternative-id":["10.1145\/3805712.3809712","10.1145\/3805712"],"URL":"https:\/\/doi.org\/10.1145\/3805712.3809712","relation":{},"subject":[],"published":{"date-parts":[[2026,7,19]]},"assertion":[{"value":"2026-07-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}