{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T01:45:54Z","timestamp":1787017554123,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":42,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,7,13]]},"DOI":"10.1145\/3726302.3730009","type":"proceedings-article","created":{"date-parts":[[2025,7,14]],"date-time":"2025-07-14T01:25:28Z","timestamp":1752456328000},"page":"1413-1422","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["InstructRAG: Leveraging Retrieval-Augmented Generation on Instruction Graphs for LLM-Based Task Planning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7064-6267","authenticated-orcid":false,"given":"Zheng","family":"Wang","sequence":"first","affiliation":[{"name":"Huawei Singapore Research Center, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3816-6507","authenticated-orcid":false,"given":"Shu Xian","family":"Teo","sequence":"additional","affiliation":[{"name":"Huawei Singapore Research Center, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1621-1569","authenticated-orcid":false,"given":"Jun Jie","family":"Chew","sequence":"additional","affiliation":[{"name":"Huawei Singapore Research Center, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2717-4192","authenticated-orcid":false,"given":"Wei","family":"Shi","sequence":"additional","affiliation":[{"name":"Huawei Singapore Research Center, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,7,13]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al.","author":"Achiam Josh","year":"2023","unstructured":"Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al. 2023. Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29720"},{"key":"e_1_3_2_1_3_1","volume-title":"Fireact: Toward language agent fine-tuning. arXiv preprint arXiv:2310.05915","author":"Chen Baian","year":"2023","unstructured":"Baian Chen, Chang Shu, Ehsan Shareghi, Nigel Collier, Karthik Narasimhan, and Shunyu Yao. 2023. Fireact: Toward language agent fine-tuning. arXiv preprint arXiv:2310.05915 (2023)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"crossref","unstructured":"Yanda Chen Ruiqi Zhong Sheng Zha George Karypis and He He. 2022. Meta-learning via Language Model In-context Tuning. In ACL. 719--730.","DOI":"10.18653\/v1\/2022.acl-long.53"},{"key":"e_1_3_2_1_5_1","volume-title":"Dynamic planning with a llm. arXiv preprint arXiv:2308.06391","author":"Dagan Gautier","year":"2023","unstructured":"Gautier Dagan, Frank Keller, and Alex Lascarides. 2023. Dynamic planning with a llm. arXiv preprint arXiv:2308.06391 (2023)."},{"key":"e_1_3_2_1_6_1","unstructured":"Budhaditya Deb Ahmed Hassan and Guoqing Zheng. 2022. Boosting Natural Language Generation from Instructions with Meta-Learning. In EMNLP. 6792--6808."},{"key":"e_1_3_2_1_7_1","volume-title":"A Strong, Economical, and Efficient Mixture-of-Experts Language Model. arXiv preprint arXiv:2405.04434","author":"AI.","year":"2024","unstructured":"DeepSeek-AI. 2024. DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model. arXiv preprint arXiv:2405.04434 (2024)."},{"key":"e_1_3_2_1_8_1","unstructured":"Chelsea Finn Pieter Abbeel and Sergey Levine. 2017. Model-agnostic meta-learning for fast adaptation of deep networks. In ICML. PMLR 1126--1135."},{"key":"e_1_3_2_1_9_1","unstructured":"Team GLM Aohan Zeng Bin Xu Bowen Wang Chenhui Zhang Da Yin Diego Rojas Guanyu Feng Hanlin Zhao Hanyu Lai et al. 2024. ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools. arXiv preprint arXiv:2406.12793 (2024)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1705"},{"key":"e_1_3_2_1_11_1","volume-title":"Yuxuan Lou, Jayashree Karlekar, Sugiri Pranata, Akira Kinose, Koki Oguri, Felix Wick, and Yang You.","author":"Kagaya Tomoyuki","year":"2024","unstructured":"Tomoyuki Kagaya, Thong Jing Yuan, Yuxuan Lou, Jayashree Karlekar, Sugiri Pranata, Akira Kinose, Koki Oguri, Felix Wick, and Yang You. 2024. Rap: Retrieval-augmented planning with contextual memory for multimodal llm agents. arXiv preprint arXiv:2402.03610 (2024)."},{"key":"e_1_3_2_1_12_1","volume-title":"PlanRAG: A Plan-then-Retrieval Augmented Generation for Generative Large Language Models as Decision Makers. arXiv preprint arXiv:2406.12430","author":"Lee Myeonghwa","year":"2024","unstructured":"Myeonghwa Lee, Seonho An, and Min-Soo Kim. 2024. PlanRAG: A Plan-then-Retrieval Augmented Generation for Generative Large Language Models as Decision Makers. arXiv preprint arXiv:2406.12430 (2024)."},{"key":"e_1_3_2_1_13_1","volume-title":"Llm p: Empowering large language models with optimal planning proficiency. arXiv preprint arXiv:2304.11477","author":"Liu Bo","year":"2023","unstructured":"Bo Liu, Yuqian Jiang, Xiaohan Zhang, Qiang Liu, Shiqi Zhang, Joydeep Biswas, and Peter Stone. 2023a. Llm p: Empowering large language models with optimal planning proficiency. arXiv preprint arXiv:2304.11477 (2023)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","unstructured":"Jerry Liu. 2022. LlamaIndex. doi:10.5281\/zenodo.1234","DOI":"10.5281\/zenodo.1234"},{"key":"e_1_3_2_1_15_1","volume-title":"Devansh Arpit, et al.","author":"Liu Zhiwei","year":"2023","unstructured":"Zhiwei Liu, Weiran Yao, Jianguo Zhang, Le Xue, Shelby Heinecke, Rithesh Murthy, Yihao Feng, Zeyuan Chen, Juan Carlos Niebles, Devansh Arpit, et al. 2023b. Bolaa: Benchmarking and orchestrating llm-augmented autonomous agents. arXiv preprint arXiv:2308.05960 (2023)."},{"key":"e_1_3_2_1_16_1","volume-title":"NeurIPS","volume":"36","author":"Madaan Aman","year":"2024","unstructured":"Aman Madaan, Niket Tandon, Prakhar Gupta, Skyler Hallinan, Luyu Gao, Sarah Wiegreffe, Uri Alon, Nouha Dziri, Shrimai Prabhumoye, Yiming Yang, et al. 2024. Self-refine: Iterative refinement with self-feedback. NeurIPS, Vol. 36 (2024)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889473"},{"key":"e_1_3_2_1_18_1","volume-title":"Metaicl: Learning to learn in context. arXiv preprint arXiv:2110.15943","author":"Min Sewon","year":"2021","unstructured":"Sewon Min, Mike Lewis, Luke Zettlemoyer, and Hannaneh Hajishirzi. 2021. Metaicl: Learning to learn in context. arXiv preprint arXiv:2110.15943 (2021)."},{"key":"e_1_3_2_1_19_1","volume-title":"Agent Planning with World Knowledge Model. arXiv preprint arXiv:2405.14205","author":"Qiao Shuofei","year":"2024","unstructured":"Shuofei Qiao, Runnan Fang, Ningyu Zhang, Yuqi Zhu, Xiang Chen, Shumin Deng, Yong Jiang, Pengjun Xie, Fei Huang, and Huajun Chen. 2024. Agent Planning with World Knowledge Model. arXiv preprint arXiv:2405.14205 (2024)."},{"key":"e_1_3_2_1_20_1","volume-title":"Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al.","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. 2021. Learning transferable visual models from natural language supervision. In ICML. PMLR, 8748--8763."},{"key":"e_1_3_2_1_21_1","volume-title":"NeurIPS Workshop.","author":"Raman Shreyas Sundara","year":"2022","unstructured":"Shreyas Sundara Raman, Vanya Cohen, Eric Rosen, Ifrah Idrees, David Paulius, and Stefanie Tellex. 2022. Planning with large language models via corrective re-prompting. In NeurIPS Workshop."},{"key":"e_1_3_2_1_22_1","volume-title":"Generate-then-Ground in Retrieval-Augmented Generation for Multi-hop Question Answering. ACL","author":"Shi Zhengliang","year":"2024","unstructured":"Zhengliang Shi, Shuo Zhang, Weiwei Sun, Shen Gao, Pengjie Ren, Zhumin Chen, and Zhaochun Ren. 2024. Generate-then-Ground in Retrieval-Augmented Generation for Multi-hop Question Answering. ACL (2024)."},{"key":"e_1_3_2_1_23_1","volume-title":"NeurIPS","volume":"36","author":"Shinn Noah","year":"2024","unstructured":"Noah Shinn, Federico Cassano, Ashwin Gopinath, Karthik Narasimhan, and Shunyu Yao. 2024. Reflexion: Language agents with verbal reinforcement learning. NeurIPS, Vol. 36 (2024)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01075"},{"key":"e_1_3_2_1_25_1","volume-title":"Alfworld: Aligning text and embodied environments for interactive learning. arXiv preprint arXiv:2010.03768","author":"Shridhar Mohit","year":"2020","unstructured":"Mohit Shridhar, Xingdi Yuan, Marc-Alexandre C\u00f4t\u00e9, Yonatan Bisk, Adam Trischler, and Matthew Hausknecht. 2020b. Alfworld: Aligning text and embodied environments for interactive learning. arXiv preprint arXiv:2010.03768 (2020)."},{"key":"e_1_3_2_1_26_1","volume-title":"MAML-en-LLM: Model agnostic meta-training of LLMs for improved in-context learning. KDD","author":"Sinha Sanchit","year":"2024","unstructured":"Sanchit Sinha, Yuguang Yue, Victor Soto, Mayank Kulkarni, Jianhua Lu, and Aidong Zhang. 2024. MAML-en-LLM: Model agnostic meta-training of LLMs for improved in-context learning. KDD (2024)."},{"key":"e_1_3_2_1_27_1","volume-title":"Trial and error: Exploration-based trajectory optimization for llm agents. arXiv preprint arXiv:2403.02502","author":"Song Yifan","year":"2024","unstructured":"Yifan Song, Da Yin, Xiang Yue, Jie Huang, Sujian Li, and Bill Yuchen Lin. 2024. Trial and error: Exploration-based trajectory optimization for llm agents. arXiv preprint arXiv:2403.02502 (2024)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-024-40231-1"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"crossref","unstructured":"Ruoyao Wang Peter Jansen Marc-Alexandre C\u00f4t\u00e9 and Prithviraj Ammanabrolu. 2022a. ScienceWorld: Is your Agent Smarter than a 5th Grader?. In EMNLP. 11279--11298.","DOI":"10.18653\/v1\/2022.emnlp-main.775"},{"key":"e_1_3_2_1_30_1","volume-title":"Learning From Failure: Integrating Negative Examples when Fine-tuning Large Language Models as Agents. arXiv preprint arXiv:2402.11651","author":"Wang Renxi","year":"2024","unstructured":"Renxi Wang, Haonan Li, Xudong Han, Yixuan Zhang, and Timothy Baldwin. 2024a. Learning From Failure: Integrating Negative Examples when Fine-tuning Large Language Models as Agents. arXiv preprint arXiv:2402.11651 (2024)."},{"key":"e_1_3_2_1_31_1","volume-title":"Aakanksha Chowdhery, and Denny Zhou.","author":"Wang Xuezhi","year":"2022","unstructured":"Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc Le, Ed Chi, Sharan Narang, Aakanksha Chowdhery, and Denny Zhou. 2022c. Self-consistency improves chain of thought reasoning in language models. arXiv preprint arXiv:2203.11171 (2022)."},{"key":"e_1_3_2_1_32_1","unstructured":"Yizhong Wang Swaroop Mishra et al. 2022b. Benchmarking generalization via in-context instructions on 1 600 language tasks. arXiv preprint arXiv:2204.07705 Vol. 2 (2022)."},{"key":"e_1_3_2_1_33_1","volume-title":"Rat: Retrieval augmented thoughts elicit context-aware reasoning in long-horizon generation. arXiv preprint arXiv:2403.05313","author":"Wang Zihao","year":"2024","unstructured":"Zihao Wang, Anji Liu, Haowei Lin, Jiaqi Li, Xiaojian Ma, and Yitao Liang. 2024b. Rat: Retrieval augmented thoughts elicit context-aware reasoning in long-horizon generation. arXiv preprint arXiv:2403.05313 (2024)."},{"key":"e_1_3_2_1_34_1","volume-title":"2024 d. DivScene: Benchmarking LVLMs for Object Navigation with Diverse Scenes and Objects. arXiv preprint arXiv:2410.02730","author":"Wang Zhaowei","year":"2024","unstructured":"Zhaowei Wang, Hongming Zhang, Tianqing Fang, Ye Tian, Yue Yang, Kaixin Ma, Xiaoman Pan, Yangqiu Song, and Dong Yu. 2024 d. DivScene: Benchmarking LVLMs for Object Navigation with Diverse Scenes and Objects. arXiv preprint arXiv:2410.02730 (2024)."},{"key":"e_1_3_2_1_35_1","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume":"35","author":"Wei Jason","year":"2022","unstructured":"Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, et al. 2022. Chain-of-thought prompting elicits reasoning in large language models. NeurIPS, Vol. 35 (2022), 24824--24837.","journal-title":"NeurIPS"},{"key":"e_1_3_2_1_36_1","volume-title":"Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine learning","author":"Williams Ronald J","year":"1992","unstructured":"Ronald J Williams. 1992. Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine learning, Vol. 8, 3 (1992), 229--256."},{"key":"e_1_3_2_1_37_1","unstructured":"Zhiheng Xi Wenxiang Chen Xin Guo Wei He Yiwen Ding Boyang Hong Ming Zhang Junzhe Wang Senjie Jin Enyu Zhou et al. 2023. The rise and potential of large language model based agents: A survey. arXiv preprint arXiv:2309.07864 (2023)."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"crossref","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 EMNLP. 2369--2380.","DOI":"10.18653\/v1\/D18-1259"},{"key":"e_1_3_2_1_39_1","first-page":"20744","article-title":"Webshop: Towards scalable real-world web interaction with grounded language agents","volume":"35","author":"Yao Shunyu","year":"2022","unstructured":"Shunyu Yao, Howard Chen, John Yang, and Karthik Narasimhan. 2022a. Webshop: Towards scalable real-world web interaction with grounded language agents. NeurIPS, Vol. 35 (2022), 20744--20757.","journal-title":"NeurIPS"},{"key":"e_1_3_2_1_40_1","volume-title":"NeurIPS","volume":"36","author":"Yao Shunyu","year":"2024","unstructured":"Shunyu Yao, Dian Yu, Jeffrey Zhao, Izhak Shafran, Tom Griffiths, Yuan Cao, and Karthik Narasimhan. 2024. Tree of thoughts: Deliberate problem solving with large language models. NeurIPS, Vol. 36 (2024)."},{"key":"e_1_3_2_1_41_1","volume-title":"React: Synergizing reasoning and acting in language models. arXiv preprint arXiv:2210.03629","author":"Yao Shunyu","year":"2022","unstructured":"Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik Narasimhan, and Yuan Cao. 2022b. React: Synergizing reasoning and acting in language models. arXiv preprint arXiv:2210.03629 (2022)."},{"key":"e_1_3_2_1_42_1","volume-title":"Knowagent: Knowledge-augmented planning for llm-based agents. arXiv preprint arXiv:2403.03101","author":"Zhu Yuqi","year":"2024","unstructured":"Yuqi Zhu, Shuofei Qiao, Yixin Ou, Shumin Deng, Ningyu Zhang, Shiwei Lyu, Yue Shen, Lei Liang, Jinjie Gu, and Huajun Chen. 2024. Knowagent: Knowledge-augmented planning for llm-based agents. arXiv preprint arXiv:2403.03101 (2024)."}],"event":{"name":"SIGIR '25: The 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Padua Italy","acronym":"SIGIR '25","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3726302.3730009","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T12:19:17Z","timestamp":1755865157000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3726302.3730009"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,13]]},"references-count":42,"alternative-id":["10.1145\/3726302.3730009","10.1145\/3726302"],"URL":"https:\/\/doi.org\/10.1145\/3726302.3730009","relation":{},"subject":[],"published":{"date-parts":[[2025,7,13]]},"assertion":[{"value":"2025-07-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}