{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T15:56:07Z","timestamp":1786463767448,"version":"build-2736575974"},"reference-count":54,"publisher":"Association for Computing Machinery (ACM)","issue":"6","license":[{"start":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T00:00:00Z","timestamp":1785456000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"crossref","award":["#62376027"],"award-info":[{"award-number":["#62376027"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Beijing Natural Science Foundation","award":["#L251037"],"award-info":[{"award-number":["#L251037"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Inf. Syst."],"published-print":{"date-parts":[[2026,7,31]]},"abstract":"<jats:p>Hallucination remains a major obstacle to the domain generalizability and reliability of Large Language Models (LLMs). Recent approaches address this issue by integrating Retrieval-Augmented Generation (RAG) with stepwise reasoning processes to iteratively retrieve knowledge. However, indiscriminate incorporation of external knowledge may interfere with reasoning, increasing latency and amplifying error accumulation. Moreover, existing methods rely on a unidirectional flow of external knowledge into LLMs while neglecting internal\u2013external knowledge synergy, limiting autonomous reasoning capability. To address these limitations, we propose the Reasoning\u2013Evidence Interactive Augmented Graph (RE-IAG), a framework that couples reasoning with evidence through a staged triggering mechanism and structured interaction. RE-IAG performs localized refinement of intermediate reasoning via adaptive branching under uncertainty and selectively triggers retrieval when internal reasoning stagnates. Crucially, it organizes both internal reasoning and retrieved evidence into aligned graph structures, enabling structure-guided verification and fine-grained refinement of intermediate conclusions. This design transforms retrieval from passive augmentation into an active constraint on reasoning, reducing error propagation, alleviating knowledge conflicts, and improving knowledge integration for hallucination mitigation. Extensive experiments on four multi-hop QA benchmarks show that RE-IAG outperforms adaptive RAG baselines, achieves competitive or superior performance to RL-based approaches, and demonstrates strong robustness and generalization across model scales and architectures.<\/jats:p>","DOI":"10.1145\/3827609","type":"journal-article","created":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T15:03:14Z","timestamp":1783004594000},"page":"1-41","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Decomposition, Think, and Action: Alleviating Hallucinations of Large Language Models with Reasoning\u2013Evidence Interactive Augmented Graph"],"prefix":"10.1145","volume":"44","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-3674-8671","authenticated-orcid":false,"given":"Yi","family":"Sui","sequence":"first","affiliation":[{"name":"Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8179-7503","authenticated-orcid":false,"given":"Chaozhuo","family":"Li","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6981-3873","authenticated-orcid":false,"given":"Litian","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8660-3608","authenticated-orcid":false,"given":"Dawei","family":"Song","sequence":"additional","affiliation":[{"name":"Beijing Institute of Technology, Beijing, China and The Open University, Milton Keynes, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0390-3657","authenticated-orcid":false,"given":"Haiming","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Southampton, Southampton, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,8,11]]},"reference":[{"key":"e_1_3_1_2_2","unstructured":"Zechen Bai Pichao Wang Tianjun Xiao Tong He Zongbo Han Zheng Zhang and Mike Zheng Shou. 2024. Hallucination of multimodal large language models: A survey. Retrieved from arXiv:2404.18930. Retrieved from https:\/\/arxiv.org\/abs\/2404.18930"},{"key":"e_1_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1145\/3641289"},{"key":"e_1_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3476"},{"key":"e_1_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671470"},{"key":"e_1_3_1_6_2","unstructured":"Yunfan Gao Yun Xiong Yijie Zhong Yuxi Bi Ming Xue and Haofen Wang. 2025. Synergizing rag and reasoning: A systematic review. arXiv:2504.15909. Retrieved from https:\/\/arxiv.org\/abs\/2504.15909"},{"key":"e_1_3_1_7_2","unstructured":"Xinyan Guan Jiali Zeng Fandong Meng Chunlei Xin Yaojie Lu Hongyu Lin Xianpei Han Le Sun and Jie Zhou. 2025. DeepRAG: Thinking to retrieval step by step for large language models. arXiv:2502.01142. Retrieved from https:\/\/arxiv.org\/abs\/2502.01142"},{"key":"e_1_3_1_8_2","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:2501.12948. Retrieved from https:\/\/arxiv.org\/abs\/2501.12948"},{"key":"e_1_3_1_9_2","unstructured":"Minghao Guo Qingcheng Zeng Xujiang Zhao Yanchi Liu Wenchao Yu Mengnan Du Haifeng Chen and Wei Cheng. 2025. DeepSieve: Information sieving via LLM-as-a-knowledge-router. Retrieved from arXiv:2507.22050. Retrieved from https:\/\/arxiv.org\/abs\/2507.22050"},{"key":"e_1_3_1_10_2","unstructured":"Muhammad Usman Hadi Rizwan Qureshi Abbas Shah Muhammad Irfan Anas Zafar Muhammad Bilal Shaikh Naveed Akhtar Jia Wu Seyedali Mirjalili et al. 2023. A Survey on Large Language Models: Applications Challenges Limitations and Practical Usage. Authorea."},{"key":"e_1_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.1319"},{"key":"e_1_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.580"},{"key":"e_1_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/3703155"},{"key":"e_1_3_1_14_2","unstructured":"Binyuan Hui Jian Yang Zeyu Cui Jiaxi Yang Dayiheng Liu Lei Zhang Tianyu Liu Jiajun Zhang Bowen Yu Keming Lu et al. 2024. Qwen2.5-coder technical report. Retrieved from arXiv:2409.12186. Retrieved from https:\/\/arxiv.org\/abs\/2409.12186"},{"key":"e_1_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.389"},{"key":"e_1_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICKG63256.2024.00026"},{"key":"e_1_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.495"},{"key":"e_1_3_1_18_2","unstructured":"Bowen Jin Hansi Zeng Zhenrui Yue Jinsung Yoon Sercan Arik Dong Wang Hamed Zamani and Jiawei Han. 2025. Search-R1: Training LLMs to reason and leverage search engines with reinforcement learning. Retrieved from arXiv:2503.09516. Retrieved from https:\/\/arxiv.org\/abs\/2503.09516"},{"key":"e_1_3_1_19_2","unstructured":"Chaozhuo Li Pengbo Wang Chenxu Wang Litian Zhang Zheng Liu Qiwei Ye Yuanbo Xu Feiran Huang Xi Zhang and Philip S. Yu. 2025. Loki\u2019s dance of illusions: A comprehensive survey of hallucination in large language models. Retrieved from arXiv:2507.02870. Retrieved from https:\/\/arxiv.org\/abs\/2507.02870"},{"key":"e_1_3_1_20_2","unstructured":"Xiaoxi Li Guanting Dong Jiajie Jin Yuyao Zhang Yujia Zhou Yutao Zhu Peitian Zhang and Zhicheng Dou. 2025. Search-o1: Agentic search-enhanced large reasoning models. Retrieved from arXiv:2501.05366. Retrieved from https:\/\/arxiv.org\/abs\/2501.05366"},{"key":"e_1_3_1_21_2","volume-title":"Proceedings of the 42nd International Conference on Machine Learning","author":"Luo Haoran","year":"2025","unstructured":"Haoran Luo, Yikai Guo, Qika Lin, Xiaobao Wu, 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 42nd International Conference on Machine Learning."},{"key":"e_1_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/3701228"},{"key":"e_1_3_1_23_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Ma Shengjie","year":"2024","unstructured":"Shengjie Ma, Chengjin Xu, Xuhui Jiang, Muzhi Li, Huaren Qu, Cehao Yang, Jiaxin Mao, and Jian Guo. 2024. Think-on-graph 2.0: Deep and faithful large language model reasoning with knowledge-guided retrieval augmented generation. In Proceedings of the International Conference on Learning Representations. Retrieved from https:\/\/api.semanticscholar.org\/CorpusID:273185432"},{"key":"e_1_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/3676957"},{"key":"e_1_3_1_25_2","unstructured":"AI Meta. 2024. Introducing meta llama 3: The most capable openly available LLM to date. 2024. Retrieved April 2024 from https:\/\/ai.meta.com\/blog\/meta-llama-3\/"},{"key":"e_1_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/3774904.3792524"},{"key":"e_1_3_1_27_2","unstructured":"Jianfeng Pan Senyou Deng and Shaomang Huang. 2025. CoAT: Chain-of-associated-thoughts framework for enhancing large language models reasoning. arXiv:2502.02390. Retrieved from https:\/\/arxiv.org\/abs\/2502.02390"},{"key":"e_1_3_1_28_2","first-page":"5687","volume-title":"Proceedings of the Findings of the Association for Computational Linguistics (EMNLP \u201923)","author":"Press Ofir","year":"2022","unstructured":"Ofir Press, Muru Zhang, Sewon Min, Ludwig Schmidt, Noah A. Smith, and Mike Lewis. 2022. Measuring and narrowing the compositionality gap in language models. In Proceedings of the Findings of the Association for Computational Linguistics (EMNLP \u201923), 5687\u20135711."},{"key":"e_1_3_1_29_2","first-page":"154","volume-title":"Proceedings of the World Congress in Computer Science, Computer Engineering and Applied Computing","author":"Quevedo Ernesto","year":"2024","unstructured":"Ernesto Quevedo, Jorge Yero Salazar, Rachel Koerner, Pablo Rivas, and Tomas Cerny. 2024. Detecting hallucinations in large language model generation: A token probability approach. In Proceedings of the World Congress in Computer Science, Computer Engineering and Applied Computing. Springer, 154\u2013173."},{"key":"e_1_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00605"},{"key":"e_1_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1561\/1500000019"},{"key":"e_1_3_1_32_2","unstructured":"Aman Sharma and Paras Chopra. 2025. Think just enough: Sequence-level entropy as a confidence signal for LLM reasoning. arXiv:2510.08146. Retrieved from https:\/\/arxiv.org\/abs\/2510.08146"},{"key":"e_1_3_1_33_2","unstructured":"Valentin Six Evan Dufraisse and Ga\u00ebl de Chalendar. 2025. Decompositional reasoning for graph retrieval with large language models. arXiv:2506.13380. Retrieved from https:\/\/arxiv.org\/abs\/2506.13380"},{"key":"e_1_3_1_34_2","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:2503.05592. Retrieved from https:\/\/arxiv.org\/abs\/2503.05592"},{"key":"e_1_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.emnlp-main.549"},{"key":"e_1_3_1_36_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Sun Jiashuo","year":"2023","unstructured":"Jiashuo Sun, Chengjin Xu, Lumingyuan Tang, Sai Wang, Chen Lin, Yeyun Gong, Lionel M. Ni, Heung Yeung Shum, and Jian Guo. 2023. Think-on-graph: Deep and responsible reasoning of large language model on knowledge graph. In Proceedings of the International Conference on Learning Representations. Retrieved from https:\/\/api.semanticscholar.org\/CorpusID:263333907"},{"key":"e_1_3_1_37_2","unstructured":"Zhongxiang Sun Qipeng Wang Weijie Yu Xiaoxue Zang Kai Zheng Jun Xu Xiao Zhang Song Yang and Han Li. 2025. ReARTeR: Retrieval-augmented reasoning with trustworthy process rewarding. arXiv:2501.07861. Retrieved from https:\/\/arxiv.org\/abs\/2501.07861"},{"key":"e_1_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00475"},{"key":"e_1_3_1_39_2","unstructured":"Yiteng Tu Weihang Su Yujia Zhou Yiqun Liu and Qingyao Ai. 2025. RbFT: Robust fine-tuning for retrieval-augmented generation against retrieval defects. arXiv:2501.18365. Retrieved from https:\/\/arxiv.org\/abs\/2501.18365"},{"key":"e_1_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1145\/3727144"},{"key":"e_1_3_1_41_2","unstructured":"Liang Wang Haonan Chen Nan Yang Xiaolong Huang Zhicheng Dou and Furu Wei. 2025. Chain-of-retrieval augmented generation. arXiv:2501.14342. Retrieved from https:\/\/arxiv.org\/abs\/2501.14342"},{"key":"e_1_3_1_42_2","unstructured":"Zihao Wang Anji Liu Haowei Lin Jiaqi Li Xiaojian Ma and Yitao Liang. 2024. RAT: Retrieval augmented thoughts elicit context-aware reasoning in long-horizon generation. arXiv:2403.05313. Retrieved from https:\/\/arxiv.org\/abs\/2403.05313"},{"key":"e_1_3_1_43_2","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1800"},{"key":"e_1_3_1_44_2","first-page":"82731","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Wei Zhepei","year":"2025","unstructured":"Zhepei Wei, Wei-Lin Chen, and Yu Meng. 2025. InstructRAG: Instructing retrieval-augmented generation via self-synthesized rationales. In Proceedings of the International Conference on Learning Representations, 82731\u201382754."},{"key":"e_1_3_1_45_2","unstructured":"Shangyu Wu Ying Xiong Yufei Cui Haolun Wu Can Chen Ye Yuan Lianming Huang Xue Liu Tei-Wei Kuo Nan Guan et al. 2024. Retrieval-augmented generation for natural language processing: A survey. arXiv:2407.13193. Retrieved from https:\/\/arxiv.org\/abs\/2407.13193"},{"key":"e_1_3_1_46_2","unstructured":"Wenjie Wu Yongcheng Jing Yingjie Wang Wenbin Hu and Dacheng Tao. 2025. Graph-augmented reasoning: Evolving step-by-step knowledge graph retrieval for LLM reasoning. arXiv:2503.01642. Retrieved from https:\/\/arxiv.org\/abs\/2503.01642"},{"key":"e_1_3_1_47_2","volume-title":"Proceedings of the ICML 2024 Next Generation of AI Safety Workshop","author":"Xiang Chong","unstructured":"Chong Xiang, Tong Wu, Zexuan Zhong, David Wagner, Danqi Chen, and Prateek Mittal. n.\u2009d. Certifiably robust RAG against retrieval corruption. In Proceedings of the ICML 2024 Next Generation of AI Safety Workshop."},{"key":"e_1_3_1_48_2","unstructured":"Guangzhi Xiong Qiao Jin Xiao Wang Yin Fang Haolin Liu Yifan Yang Fangyuan Chen Zhixing Song Dengyu Wang Minjia Zhang et al. 2025. RAG-Gym: Optimizing reasoning and search agents with process supervision. arXiv:2502.13957. Retrieved from https:\/\/arxiv.org\/abs\/2502.13957"},{"key":"e_1_3_1_49_2","unstructured":"Guanming Xiong Haochen Li and Wen Zhao. 2025. MCTS-KBQA: Monte Carlo tree search for knowledge base question answering. Retrieved from arXiv:2502.13428. Retrieved from https:\/\/arxiv.org\/abs\/2502.13428"},{"key":"e_1_3_1_50_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1259"},{"key":"e_1_3_1_51_2","volume-title":"Proceedings of the 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 Proceedings of the International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_1_52_2","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2202"},{"key":"e_1_3_1_53_2","unstructured":"Ge Zhang Mohammad Ali Alomrani Hongjian Gu Jiaming Zhou Yaochen Hu Bin Wang Qun Liu Mark Coates Yingxue Zhang and Jianye Hao. 2024. Path-of-thoughts: Extracting and following paths for robust relational reasoning with large language models. Retrieved from arXiv:2412.17963. Retrieved from https:\/\/arxiv.org\/abs\/2412.17963"},{"key":"e_1_3_1_54_2","unstructured":"Jianan Zhao Meng Qu Chaozhuo Li Hao Yan Qian Liu Rui Li Xing Xie and Jian Tang. 2022. Learning on large-scale text-attributed graphs via variational inference. Retrieved from arXiv:2210.14709. Retrieved from https:\/\/arxiv.org\/abs\/2210.14709"},{"key":"e_1_3_1_55_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.320"}],"container-title":["ACM Transactions on Information Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3827609","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T13:46:10Z","timestamp":1786455970000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3827609"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,31]]},"references-count":54,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2026,7,31]]}},"alternative-id":["10.1145\/3827609"],"URL":"https:\/\/doi.org\/10.1145\/3827609","relation":{},"ISSN":["1046-8188","1558-2868"],"issn-type":[{"value":"1046-8188","type":"print"},{"value":"1558-2868","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,31]]},"assertion":[{"value":"2025-09-26","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-06-11","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-08-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}