{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T18:10:41Z","timestamp":1784139041613,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":42,"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"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,20]]},"DOI":"10.1145\/3805712.3809649","type":"proceedings-article","created":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T17:06:26Z","timestamp":1784135186000},"page":"2049-2060","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Exploration-and-Thinking: Agentic Reasoning over Knowledge Graphs via an LLM-RL Synergized Framework"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0048-9929","authenticated-orcid":false,"given":"Yi","family":"Xia","sequence":"first","affiliation":[{"name":"State Key Laboratory of Mathematical Engineering and Advanced Computing, Zhengzhou, Henan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4180-0986","authenticated-orcid":false,"given":"Gang","family":"Zhou","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Mathematical Engineering and Advanced Computing, Zhengzhou, Henan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-9433-1398","authenticated-orcid":false,"given":"Jing","family":"Chen","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Mathematical Engineering and Advanced Computing, Zhengzhou, Henan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8509-6790","authenticated-orcid":false,"given":"Xiaohui","family":"Chen","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Mathematical Engineering and Advanced Computing, Zhengzhou, Henan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-6147-399X","authenticated-orcid":false,"given":"Qinlong","family":"Fan","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Mathematical Engineering and Advanced Computing, Zhengzhou, Henan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5942-0928","authenticated-orcid":false,"given":"Shunhang","family":"Li","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Mathematical Engineering and Advanced Computing, Zhengzhou, Henan, China"}],"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\/3726302.3730068"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2410.23875"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3726302.3729932"},{"key":"e_1_3_2_1_4_1","volume-title":"QLoRA: Efficient Finetuning of Quantized LLMs. In Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023","author":"Dettmers Tim","year":"2023","unstructured":"Tim Dettmers, Artidoro Pagnoni, Ari Holtzman, and Luke Zettlemoyer. 2023. QLoRA: Efficient Finetuning of Quantized LLMs. In Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023, Alice Oh, Tristan Naumann, Amir Globerson, Kate Saenko, Moritz Hardt, and Sergey Levine (Eds.). http:\/\/papers.nips.cc\/paper_files\/paper\/2023\/hash\/1feb87871436031bdc0f2beaa62a049b-Abstract-Conference.html"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2406.01238"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.203"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00778-015-0394-1"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2021.EMNLP-MAIN.552"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449992"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2023.FINDINGS-ACL.67"},{"key":"e_1_3_2_1_11_1","volume-title":"Large Language Models Cannot Self-Correct Reasoning Yet. In The Twelfth International Conference on Learning Representations, ICLR 2024","author":"Huang Jie","year":"2024","unstructured":"Jie Huang, Xinyun Chen, Swaroop Mishra, Huaixiu Steven Zheng, Adams Wei Yu, Xinying Song, and Denny Zhou. 2024. Large Language Models Cannot Self-Correct Reasoning Yet. In The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024. OpenReview.net. https:\/\/openreview.net\/forum?id=IkmD3fKBPQ"},{"key":"e_1_3_2_1_12_1","volume-title":"UniKGQA: Unified Retrieval and Reasoning for Solving Multi-hop Question Answering Over Knowledge Graph. In The Eleventh International Conference on Learning Representations, ICLR 2023","author":"Jiang Jinhao","year":"2023","unstructured":"Jinhao Jiang, Kun Zhou, Xin Zhao, and Ji-Rong Wen. 2023. UniKGQA: Unified Retrieval and Reasoning for Solving Multi-hop Question Answering Over Knowledge Graph. In The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3696410.3714946"},{"key":"e_1_3_2_1_14_1","volume-title":"Correlated Proxies: A New Definition and Improved Mitigation for Reward Hacking. In The Thirteenth International Conference on Learning Representations, ICLR 2025","author":"Laidlaw Cassidy","year":"2025","unstructured":"Cassidy Laidlaw, Shivam Singhal, and Anca D. Dragan. 2025. Correlated Proxies: A New Definition and Improved Mitigation for Reward Hacking. In The Thirteenth International Conference on Learning Representations, ICLR 2025, Singapore, April 24-28, 2025. OpenReview.net. https:\/\/openreview.net\/forum?id=msEr27EejF"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.688"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1362"},{"key":"e_1_3_2_1_17_1","volume-title":"PTuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks. CoRR abs\/2110.07602","author":"Liu Xiao","year":"2021","unstructured":"Xiao Liu, Kaixuan Ji, Yicheng Fu, Zhengxiao Du, Zhilin Yang, and Jie Tang. 2021. PTuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks. CoRR abs\/2110.07602 (2021). https:\/\/arxiv.org\/abs\/2110.07602"},{"key":"e_1_3_2_1_18_1","volume-title":"Proceedings of the 42th International Conference on Machine Learning, ICML 2025. PMLR.","author":"Luo Haoran","year":"2025","unstructured":"Haoran Luo, Haihong E, Yikai Guo, Qika Lin, XiaobaoWu, Xinyu Mu,Wenhao Liu, Meina Song, Yifan Zhu, and Luu Anh Tuan. 2025. KBQA-o1: Agentic Knowledge Base Question Answering with Monte Carlo Tree Search. In Proceedings of the 42th International Conference on Machine Learning, ICML 2025. PMLR."},{"key":"e_1_3_2_1_19_1","volume-title":"Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning. In The Twelfth International Conference on Learning Representations, ICLR 2024","author":"Luo Linhao","year":"2024","unstructured":"Linhao Luo, Yuan-Fang Li, Gholamreza Haffari, and Shirui Pan. 2024. Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning. In The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024. OpenReview.net. https:\/\/openreview.net\/forum?id=ZGNWW7xZ6Q"},{"key":"e_1_3_2_1_20_1","volume-title":"Proceedings of the 42th International Conference on Machine Learning, ICML 2025. PMLR.","author":"Luo Linhao","year":"2025","unstructured":"Linhao Luo, Zicheng Zhao, Chen Gong, Gholamreza Haffari, and Shirui Pan. 2025. Graph-constrained Reasoning: Faithful Reasoning on Knowledge Graphs with Large Language Models. In Proceedings of the 42th International Conference on Machine Learning, ICML 2025. PMLR."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2022.FINDINGS-EMNLP.181"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2405.20139"},{"key":"e_1_3_2_1_23_1","volume-title":"Manuel Fink, and Heiner Stuckenschmidt.","author":"Meilicke Christian","year":"2020","unstructured":"Christian Meilicke, Melisachew Wudage Chekol, Manuel Fink, and Heiner Stuckenschmidt. 2020. Reinforced anytime bottom up rule learning for knowledge graph completion. arXiv preprint arXiv:2004.04412 (2020)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29848"},{"key":"e_1_3_2_1_25_1","first-page":"2149","volume-title":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, IJCAI 2018","author":"Omran Pouya Ghiasnezhad","year":"2018","unstructured":"Pouya Ghiasnezhad Omran, Kewen Wang, and Zhe Wang. 2018. Scalable Rule Learning via Learning Representation. In Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, IJCAI 2018, July 13-19, 2018. Stockholm, Sweden, 2149-2155."},{"key":"e_1_3_2_1_26_1","unstructured":"OpenAI. 2024. Hello gpt-4o. (2024). https:\/\/openai.com\/index\/hello-gpt-4o"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2023.ACL-LONG.294"},{"key":"e_1_3_2_1_28_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, PeiyiWang, 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_29_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2403.07311"},{"key":"e_1_3_2_1_30_1","volume-title":"Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph. In The Twelfth International Conference on Learning Representations, ICLR 2024","author":"Sun Jiashuo","year":"2024","unstructured":"Jiashuo Sun, Chengjin Xu, Lumingyuan Tang, Saizhuo Wang, Chen Lin, Yeyun Gong, Lionel M. Ni, Heung-Yeung Shum, and Jian Guo. 2024. Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph. In The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024. OpenReview.net. https:\/\/openreview.net\/forum?id=nnVO1PvbTv"},{"key":"e_1_3_2_1_31_1","volume-title":"Barto","author":"Sutton Richard S.","year":"1998","unstructured":"Richard S. Sutton and Andrew G. Barto. 1998. Reinforcement Learning: An Introduction. MIT Press, Cambridge, Mass."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/N18-1059"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3696410.3714892"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657723"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale Dan Bikel Lukas Blecher Cristian Canton-Ferrer Moya Chen Guillem Cucurull David Esiobu Jude Fernandes Jeremy Fu Wenyin Fu Brian Fuller Cynthia Gao Vedanuj Goswami Naman Goyal Anthony Hartshorn Saghar Hosseini Rui Hou Hakan Inan Marcin Kardas Viktor Kerkez Madian Khabsa Isabel Kloumann Artem Korenev Punit Singh Koura Marie-Anne Lachaux Thibaut Lavril Jenya Lee Diana Liskovich Yinghai Lu Yuning Mao Xavier Martinet Todor Mihaylov Pushkar Mishra Igor Molybog Yixin Nie Andrew Poulton Jeremy Reizenstein Rashi Rungta Kalyan Saladi Alan Schelten Ruan Silva Eric Michael Smith Ranjan Subramanian Xiaoqing Ellen Tan Binh Tang Ross Taylor Adina Williams Jian Xiang Kuan Puxin Xu Zheng Yan Iliyan Zarov Yuchen Zhang Angela Fan Melanie Kambadur Sharan Narang Aur\u00e9lien Rodriguez Robert Stojnic Sergey Edunov and Thomas Scialom. 2023. Llama 2: Open Foundation and Fine-Tuned Chat Models. CoRR abs\/2307.09288 (2023). arXiv:2307.09288 doi:10.48550\/ARXIV.2307.09288","DOI":"10.48550\/ARXIV.2307.09288"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2022.103040"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.63317\/3vxue5y8m4xy"},{"key":"e_1_3_2_1_38_1","volume-title":"QA-LoRA: Quantization- Aware Low-Rank Adaptation of Large Language Models. In The Twelfth International Conference on Learning Representations, ICLR 2024","author":"Xu Yuhui","year":"2024","unstructured":"Yuhui Xu, Lingxi Xie, Xiaotao Gu, Xin Chen, Heng Chang, Hengheng Zhang, Zhengsu Chen, Xiaopeng Zhang, and Qi Tian. 2024. QA-LoRA: Quantization- Aware Low-Rank Adaptation of Large Language Models. In The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024. OpenReview.net. https:\/\/openreview.net\/forum?id=WvFoJccpo8"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/P16-2033"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681327"},{"key":"e_1_3_2_1_41_1","volume-title":"Cone: Cone embeddings for multi-hop reasoning over knowledge graphs. Advances in Neural Information Processing Systems 34","author":"Zhang Zhanqiu","year":"2021","unstructured":"Zhanqiu Zhang, Jie Wang, Jiajun Chen, Shuiwang Ji, and Feng Wu. 2021. Cone: Cone embeddings for multi-hop reasoning over knowledge graphs. Advances in Neural Information Processing Systems 34 (2021)."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657838"}],"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":"2026-07-15T17:29:00Z","timestamp":1784136540000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805712.3809649"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,19]]},"references-count":42,"alternative-id":["10.1145\/3805712.3809649","10.1145\/3805712"],"URL":"https:\/\/doi.org\/10.1145\/3805712.3809649","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"}}]}}