{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T18:06:51Z","timestamp":1784138811236,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":52,"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":"Ministry of Education, Singapore","award":["MOE-MOET32022-0001"],"award-info":[{"award-number":["MOE-MOET32022-0001"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,20]]},"DOI":"10.1145\/3805712.3809601","type":"proceedings-article","created":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T14:28:19Z","timestamp":1783693699000},"page":"1473-1484","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["R\n                    <sup>3<\/sup>\n                    Check: Reinforcement Learning for Iterative Retrieval and Structured Reasoning in Complex Fact Checking"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6458-8320","authenticated-orcid":false,"given":"Peng","family":"Qi","sequence":"first","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4754-0325","authenticated-orcid":false,"given":"Yuyang","family":"Zhao","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4142-8893","authenticated-orcid":false,"given":"Wynne","family":"Hsu","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9636-388X","authenticated-orcid":false,"given":"Mong Li","family":"Lee","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,19]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3726302.3730339"},{"key":"e_1_3_2_1_2_1","first-page":"23514","article-title":"Enhancing Multi-Hop Fact Verification with Structured Knowledge-Augmented Large Language Models. In AAAI-25, Sponsored by the Association for the Advancement of Artificial Intelligence, February 25 - March 4, 2025, Philadelphia","author":"Cao Han","year":"2025","unstructured":"Han Cao, Lingwei Wei, Wei Zhou, and Songlin Hu. 2025. Enhancing Multi-Hop Fact Verification with Structured Knowledge-Augmented Large Language Models. In AAAI-25, Sponsored by the Association for the Advancement of Artificial Intelligence, February 25 - March 4, 2025, Philadelphia, PA, USA. 23514-23522.","journal-title":"PA, USA."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.729"},{"key":"e_1_3_2_1_4_1","volume-title":"Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017","author":"Christiano Paul F.","year":"2017","unstructured":"Paul F. Christiano, Jan Leike, Tom B. Brown, Miljan Martic, Shane Legg, and Dario Amodei. 2017. Deep Reinforcement Learning from Human Preferences. In Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4-9, 2017, Long Beach, CA, USA. 4299-4307."},{"key":"e_1_3_2_1_5_1","unstructured":"DeepSeek-AI. 2025. DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning. arXiv:2501.12948 [cs.AI] https:\/\/arxiv.org\/abs\/2501.12948"},{"key":"e_1_3_2_1_6_1","unstructured":"Guanting Dong Yifei Chen Xiaoxi Li Jiajie Jin Hongjin Qian Yutao Zhu Hangyu Mao Guorui Zhou Zhicheng Dou and Ji-Rong Wen. 2025. Tool-Star: Empowering LLM-Brained Multi-Tool Reasoner via Reinforcement Learning. arXiv:2505.16410 [cs.CL] https:\/\/arxiv.org\/abs\/2505.16410"},{"key":"e_1_3_2_1_7_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_8_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00454"},{"key":"e_1_3_2_1_9_1","unstructured":"Qisheng Hu Quanyu Long and Wenya Wang. 2025. Coordinating Search-Informed Reasoning and Reasoning-Guided Search in Claim Verification. arXiv:2506.07528 [cs.AI] https:\/\/arxiv.org\/abs\/2506.07528"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3703155"},{"key":"e_1_3_2_1_11_1","unstructured":"Dongfu Jiang Yi Lu Zhuofeng Li Zhiheng Lyu Ping Nie Haozhe Wang Alex Su Hui Chen Kai Zou Chao Du Tianyu Pang and Wenhu Chen. 2025. VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use. arXiv:2509.01055 [cs.AI] https:\/\/arxiv.org\/abs\/2509.01055"},{"key":"e_1_3_2_1_12_1","first-page":"3441","volume-title":"HoVer: A Dataset for Many-Hop Fact Extraction And Claim Verification. In Findings of the Association for Computational Linguistics: EMNLP 2020","author":"Jiang Yichen","year":"2020","unstructured":"Yichen Jiang, Shikha Bordia, Zheng Zhong, Charles Dognin, Maneesh Kumar Singh, and Mohit Bansal. 2020. HoVer: A Dataset for Many-Hop Fact Extraction And Claim Verification. In Findings of the Association for Computational Linguistics: EMNLP 2020, Online Event, 16-20 November 2020. 3441-3460."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.495"},{"key":"e_1_3_2_1_14_1","volume-title":"Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAG. In The Thirteenth International Conference on Learning Representations.","author":"Jin Bowen","year":"2025","unstructured":"Bowen Jin, Jinsung Yoon, Jiawei Han, and Sercan O Arik. 2025a. Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAG. In The Thirteenth International Conference on Learning Representations."},{"key":"e_1_3_2_1_15_1","volume-title":"An Empirical Study on Reinforcement Learning for Reasoning-Search Interleaved LLM Agents. arXiv preprint arXiv:2505.15117","author":"Jin Bowen","year":"2025","unstructured":"Bowen Jin, Jinsung Yoon, Priyanka Kargupta, Sercan O Arik, and Jiawei Han. 2025b. An Empirical Study on Reinforcement Learning for Reasoning-Search Interleaved LLM Agents. arXiv preprint arXiv:2505.15117 (2025)."},{"key":"e_1_3_2_1_16_1","volume-title":"Search-r1: Training llms to reason and leverage search engines with reinforcement learning. arXiv preprint arXiv:2503.09516","author":"Jin Bowen","year":"2025","unstructured":"Bowen Jin, Hansi Zeng, Zhenrui Yue, Jinsung Yoon, Sercan Arik, Dong Wang, Hamed Zamani, and Jiawei Han. 2025c. Search-r1: Training llms to reason and leverage search engines with reinforcement learning. arXiv preprint arXiv:2503.09516 (2025)."},{"key":"e_1_3_2_1_17_1","unstructured":"Kimi-Team. 2025. Kimi k1.5: Scaling Reinforcement Learning with LLMs. arXiv:2501.12599 [cs.CL] https:\/\/arxiv.org\/abs\/2501.12599"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1017\/XPS.2020.37"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"e_1_3_2_1_20_1","unstructured":"Xuefeng Li Haoyang Zou and Pengfei Liu. 2025. ToRL: Scaling Tool-Integrated RL. arXiv:2503.23383 [cs.CL] https:\/\/arxiv.org\/abs\/2503.23383"},{"key":"e_1_3_2_1_21_1","first-page":"9340","volume-title":"ACL 2024, Bangkok, Thailand and virtual meeting","author":"Ma Huanhuan","year":"2024","unstructured":"Huanhuan Ma, Weizhi Xu, Yifan Wei, Liuji Chen, Liang Wang, Qiang Liu, and Shu Wu. 2024. EX-FEVER: A Dataset for Multi-hop Explainable Fact Verification. In Findings of the Association for Computational Linguistics, ACL 2024, Bangkok, Thailand and virtual meeting, August 11-16, 2024. 9340-9353."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1244"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3696410.3714748"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889473"},{"key":"e_1_3_2_1_25_1","unstructured":"OpenAI. 2024a. GPT-4o System Card. arXiv:2410.21276 [cs.CL] https:\/\/arxiv.org\/abs\/2410.21276"},{"key":"e_1_3_2_1_26_1","unstructured":"OpenAI. 2024b. OpenAI o1 System Card. arXiv:2412.16720 [cs.AI] https:\/\/arxiv.org\/abs\/2412.16720"},{"key":"e_1_3_2_1_27_1","unstructured":"OpenAI. 2025. OpenAI o3 and o4-mini System Card. https:\/\/cdn.openai.com\/pdf\/2221c875-02dc-4789-800b-e7758f3722c1\/o3-and-o4-mini-system-card.pdf Accessed: 2025-05-14."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/536"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.386"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1003"},{"key":"e_1_3_2_1_31_1","unstructured":"Qwen Team. 2024. Qwen2.5: A Party of Foundation Models. https:\/\/qwenlm.github.io\/blog\/qwen2.5\/"},{"key":"e_1_3_2_1_32_1","volume-title":"Direct preference optimization: Your language model is secretly a reward model. Advances in neural information processing systems","author":"Rafailov Rafael","year":"2023","unstructured":"Rafael Rafailov, Archit Sharma, Eric Mitchell, Christopher D Manning, Stefano Ermon, and Chelsea Finn. 2023. Direct preference optimization: Your language model is secretly a reward model. Advances in neural information processing systems, Vol. 36 (2023), 53728-53741."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1561\/1500000019"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2842"},{"key":"e_1_3_2_1_35_1","volume-title":"Deepseekmath: Pushing the limits of mathematical reasoning in open language models. arXiv preprint arXiv:2402.03300","author":"Shao Zhihong","year":"2024","unstructured":"Zhihong Shao, Peiyi Wang, Qihao Zhu, Runxin Xu, Junxiao Song, Xiao Bi, Haowei Zhang, Mingchuan Zhang, YK Li, Yang Wu, et al., 2024. Deepseekmath: Pushing the limits of mathematical reasoning in open language models. arXiv preprint arXiv:2402.03300 (2024)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3689031.3696075"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.835"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i11.26591"},{"key":"e_1_3_2_1_39_1","volume-title":"Lei Fang, and Ji-Rong Wen.","author":"Song Huatong","year":"2025","unstructured":"Huatong Song, Jinhao Jiang, Yingqian Min, Jie Chen, Zhipeng Chen, Wayne Xin Zhao, Lei Fang, and Ji-Rong Wen. 2025. R1-searcher: Incentivizing the search capability in llms via reinforcement learning. arXiv preprint arXiv:2503.05592 (2025)."},{"key":"e_1_3_2_1_40_1","unstructured":"Dirk HR Spennemann. 2025. Delving into: the quantification of Ai-generated content on the internet (synthetic data). arXiv:2504.08755 [cs.IR] https:\/\/arxiv.org\/abs\/2504.08755"},{"key":"e_1_3_2_1_41_1","first-page":"3346","volume-title":"Proceedings of the 27th International Conference on Computational Linguistics, COLING 2018","author":"Thorne James","year":"2018","unstructured":"James Thorne and Andreas Vlachos. 2018. Automated Fact Checking: Task Formulations, Methods and Future Directions. In Proceedings of the 27th International Conference on Computational Linguistics, COLING 2018, Santa Fe, New Mexico, USA, August 20-26, 2018. 3346-3359."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1074"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.416"},{"key":"e_1_3_2_1_44_1","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:2212.03533 [cs.CL] https:\/\/arxiv.org\/abs\/2212.03533"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512122"},{"key":"e_1_3_2_1_46_1","volume-title":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. 2369-2380","author":"Yang Zhilin","unstructured":"Zhilin Yang, Peng Qi, Saizheng Zhang, Yoshua Bengio, William Cohen, Ruslan Salakhutdinov, and Christopher D. Manning. 2018. HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. 2369-2380."},{"key":"e_1_3_2_1_47_1","volume-title":"DAPO: An Open-Source LLM Reinforcement Learning System at Scale. arXiv preprint arXiv:2503.14476","author":"Yu Qiying","year":"2025","unstructured":"Qiying Yu, Zheng Zhang, Ruofei Zhu, Yufeng Yuan, Xiaochen Zuo, Yu Yue, Weinan Dai, Tiantian Fan, Gaohong Liu, Lingjun Liu, et al., 2025. DAPO: An Open-Source LLM Reinforcement Learning System at Scale. arXiv preprint arXiv:2503.14476 (2025)."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.ijcnlp-main.64"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.63317\/3pcdygr48ahs"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i24.34802"},{"key":"e_1_3_2_1_51_1","unstructured":"Zhi Zheng and Wee Sun Lee. 2025. Reasoning-CV: Fine-tuning Powerful Reasoning LLMs for Knowledge-Assisted Claim Verification. arXiv:2505.12348 [cs.AI] https:\/\/arxiv.org\/abs\/2505.12348"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581318"}],"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":"2026-07-15T17:23:31Z","timestamp":1784136211000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805712.3809601"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,19]]},"references-count":52,"alternative-id":["10.1145\/3805712.3809601","10.1145\/3805712"],"URL":"https:\/\/doi.org\/10.1145\/3805712.3809601","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"}}]}}