{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,4]],"date-time":"2026-09-04T21:13:22Z","timestamp":1788556402850,"version":"build-2803163510"},"publisher-location":"New York, NY, USA","reference-count":73,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,8,8]],"date-time":"2026-08-08T00:00:00Z","timestamp":1786147200000},"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":[[2026,8,9]]},"DOI":"10.1145\/3770855.3817995","type":"proceedings-article","created":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T17:15:37Z","timestamp":1786036537000},"page":"2790-2801","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Causal Abstraction Learning for Multi-Modal Grounded Planning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1202-3993","authenticated-orcid":false,"given":"Xinshu","family":"Li","sequence":"first","affiliation":[{"name":"RMIT University, Melbourne, Australia and Macquarie University, Sydney, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0539-8391","authenticated-orcid":false,"given":"Shiyi","family":"Yang","sequence":"additional","affiliation":[{"name":"University of New South Wales, Sydney, Australia and Data61, CSIRO, Sydney, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1748-5801","authenticated-orcid":false,"given":"Ziqi","family":"Xu","sequence":"additional","affiliation":[{"name":"RMIT University, Melbourne, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8324-1859","authenticated-orcid":false,"given":"Feng","family":"Xia","sequence":"additional","affiliation":[{"name":"RMIT University, Melbourne, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3326-4147","authenticated-orcid":false,"given":"Quan Z.","family":"Sheng","sequence":"additional","affiliation":[{"name":"Macquarie University, Sydney, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4149-839X","authenticated-orcid":false,"given":"Lina","family":"Yao","sequence":"additional","affiliation":[{"name":"University of New South Wales, Sydney, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,8,8]]},"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.v38i21.30319"},{"key":"e_1_3_2_1_3_1","unstructured":"Michael Ahn Anthony Brohan Noah Brown Yevgen Chebotar Omar Cortes Byron David Chelsea Finn Chuyuan Fu Keerthana Gopalakrishnan Karol Hausman et al. 2022. Do as i can not as i say: Grounding language in robotic affordances. arXiv preprint arXiv:2204.01691 (2022)."},{"key":"e_1_3_2_1_4_1","volume-title":"Conference on Robot Learning. PMLR, 706-717","author":"Blukis Valts","year":"2022","unstructured":"Valts Blukis, Chris Paxton, Dieter Fox, Animesh Garg, and Yoav Artzi. 2022. A persistent spatial semantic representation for high-level natural language instruction execution. In Conference on Robot Learning. PMLR, 706-717."},{"key":"e_1_3_2_1_5_1","volume-title":"Causal Information Prioritization for Efficient Reinforcement Learning. In The Thirteenth International Conference on Learning Representations.","author":"Cao Hongye","year":"2025","unstructured":"Hongye Cao, Fan Feng, Tianpei Yang, Jing Huo, and Yang Gao. 2025. Causal Information Prioritization for Efficient Reinforcement Learning. In The Thirteenth International Conference on Learning Representations."},{"key":"e_1_3_2_1_6_1","volume-title":"Embodied CoT Distillation From LLM To Off-the-shelf Agents. In International Conference on Machine Learning. PMLR, 8702-8721","author":"Choi Wonje","year":"2024","unstructured":"Wonje Choi, Woo Kyung Kim, Minjong Yoo, and Honguk Woo. 2024. Embodied CoT Distillation From LLM To Off-the-shelf Agents. In International Conference on Machine Learning. PMLR, 8702-8721."},{"key":"e_1_3_2_1_7_1","volume-title":"NeSyC: A Neuro-symbolic Continual Learner For Complex Embodied Tasks In Open Domains. arXiv preprint arXiv:2503.00870","author":"Choi Wonje","year":"2025","unstructured":"Wonje Choi, Jinwoo Park, Sanghyun Ahn, Daehee Lee, and Honguk Woo. 2025. NeSyC: A Neuro-symbolic Continual Learner For Complex Embodied Tasks In Open Domains. arXiv preprint arXiv:2503.00870 (2025)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1924"},{"key":"e_1_3_2_1_9_1","volume-title":"Conference on robot learning. PMLR, 1-16","author":"Dosovitskiy Alexey","year":"2017","unstructured":"Alexey Dosovitskiy, German Ros, Felipe Codevilla, Antonio Lopez, and Vladlen Koltun. 2017. CARLA: An open urban driving simulator. In Conference on robot learning. PMLR, 1-16."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1333"},{"key":"e_1_3_2_1_11_1","volume-title":"Jianfeng Gao, et al.","author":"Gupta Tarun","year":"2024","unstructured":"Tarun Gupta, Wenbo Gong, Chao Ma, Nick Pawlowski, Agrin Hilmkil, Meyer Scetbon, Marc Rigter, Ade Famoti, Ashley Juan Llorens, Jianfeng Gao, et al., 2024. The essential role of causality in foundation world models for embodied AI. arXiv preprint arXiv:2402.06665 (2024)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i18.29991"},{"key":"e_1_3_2_1_13_1","first-page":"20064","article-title":"Causality-driven hierarchical structure discovery for reinforcement learning","volume":"35","author":"Hu Xing","year":"2022","unstructured":"Xing Hu, Rui Zhang, Ke Tang, Jiaming Guo, Qi Yi, Ruizhi Chen, Zidong Du, Ling Li, Qi Guo, Yunji Chen, et al., 2022. Causality-driven hierarchical structure discovery for reinforcement learning. Advances in Neural Information Processing Systems, Vol. 35 (2022), 20064-20076.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_14_1","volume-title":"International conference on machine learning. PMLR, 9118-9147","author":"Huang Wenlong","year":"2022","unstructured":"Wenlong Huang, Pieter Abbeel, Deepak Pathak, and Igor Mordatch. 2022. Language models as zero-shot planners: Extracting actionable knowledge for embodied agents. In International conference on machine learning. PMLR, 9118-9147."},{"key":"e_1_3_2_1_15_1","volume-title":"Causal reasoning and large language models: Opening a new frontier for causality. Transactions on Machine Learning Research","author":"Kiciman Emre","year":"2023","unstructured":"Emre Kiciman, Robert Ness, Amit Sharma, and Chenhao Tan. 2023. Causal reasoning and large language models: Opening a new frontier for causality. Transactions on Machine Learning Research (2023)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01004"},{"key":"e_1_3_2_1_17_1","volume-title":"Forty-first International Conference on Machine Learning.","author":"Kim Sehoon","year":"2024","unstructured":"Sehoon Kim, Suhong Moon, Ryan Tabrizi, Nicholas Lee, Michael W Mahoney, Kurt Keutzer, and Amir Gholami. 2024b. An llm compiler for parallel function calling. In Forty-first International Conference on Machine Learning."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i4.32455"},{"key":"e_1_3_2_1_19_1","volume-title":"ReALFRED: An Embodied Instruction Following Benchmark in Photo-Realistic Environments. In European Conference on Computer Vision. Springer, 346-364","author":"Kim Taewoong","year":"2024","unstructured":"Taewoong Kim, Cheolhong Min, Byeonghwi Kim, Jinyeon Kim, Wonje Jeung, and Jonghyun Choi. 2024a. ReALFRED: An Embodied Instruction Following Benchmark in Photo-Realistic Environments. In European Conference on Computer Vision. Springer, 346-364."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671782"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755820"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM54844.2022.00130"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i12.29271"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2379"},{"key":"e_1_3_2_1_25_1","volume-title":"Breaking down and building up: Mixture of skill-based vision-and-language navigation agents. arXiv preprint arXiv:2508.07642","author":"Ma Tianyi","year":"2025","unstructured":"Tianyi Ma, Yue Zhang, Zehao Wang, and Parisa Kordjamshidi. 2025. Breaking down and building up: Mixture of skill-based vision-and-language navigation agents. arXiv preprint arXiv:2508.07642 (2025)."},{"key":"e_1_3_2_1_26_1","volume-title":"A survey on vision-language-action models for embodied ai. arXiv preprint arXiv:2405.14093","author":"Ma Yueen","year":"2024","unstructured":"Yueen Ma, Zixing Song, Yuzheng Zhuang, Jianye Hao, and Irwin King. 2024. A survey on vision-language-action models for embodied ai. arXiv preprint arXiv:2405.14093 (2024)."},{"key":"e_1_3_2_1_27_1","volume-title":"FILM: Following Instructions in Language with Modular Methods. In International Conference on Learning Representations.","author":"Min So Yeon","year":"2022","unstructured":"So Yeon Min, Devendra Singh Chaplot, Pradeep Kumar Ravikumar, Yonatan Bisk, and Ruslan Salakhutdinov. 2022. FILM: Following Instructions in Language with Modular Methods. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.492"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00886"},{"key":"e_1_3_2_1_30_1","volume-title":"Discriminator-Guided Embodied Planning for LLM Agent. In The Thirteenth International Conference on Learning Representations.","author":"Qian Haofu","year":"2025","unstructured":"Haofu Qian, Chenjia Bai, Jiatao Zhang, Fei Wu, Wei Song, and Xuelong Li. 2025. Discriminator-Guided Embodied Planning for LLM Agent. In The Thirteenth International Conference on Learning Representations."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2418"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2997"},{"key":"e_1_3_2_1_33_1","first-page":"22905","article-title":"Causal influence detection for improving efficiency in reinforcement learning","volume":"34","author":"Seitzer Maximilian","year":"2021","unstructured":"Maximilian Seitzer, Bernhard Sch\u00f6lkopf, and Georg Martius. 2021. Causal influence detection for improving efficiency in reinforcement learning. Advances in Neural Information Processing Systems, Vol. 34 (2021), 22905-22918.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_34_1","volume-title":"Socratic Planner: Self-QA-Based Zero-Shot Planning for Embodied Instruction Following. In 2025 IEEE International Conference on Robotics and Automation (ICRA). IEEE, 16217-16224","author":"Shin Suyeon","year":"2025","unstructured":"Suyeon Shin, Sujin Jeon, Junghyun Kim, Gi-Cheon Kang, and Byoung-Tak Zhang. 2025. Socratic Planner: Self-QA-Based Zero-Shot Planning for Embodied Instruction Following. In 2025 IEEE International Conference on Robotics and Automation (ICRA). IEEE, 16217-16224."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0377"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01075"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161317"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00280"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01365"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00995"},{"key":"e_1_3_2_1_41_1","unstructured":"Gemini Team Rohan Anil Sebastian Borgeaud Jean-Baptiste Alayrac Jiahui Yu Radu Soricut Johan Schalkwyk Andrew M Dai Anja Hauth Katie Millican et al. 2023. Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805 (2023)."},{"key":"e_1_3_2_1_42_1","volume-title":"Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971","author":"Touvron Hugo","year":"2023","unstructured":"Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timoth\u00e9e Lacroix, Baptiste Rozi\u00e8re, Naman Goyal, Eric Hambro, Faisal Azhar, et al., 2023. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00835"},{"key":"e_1_3_2_1_44_1","volume-title":"Forty-second International Conference on Machine Learning.","author":"Wang Xubin","year":"2025","unstructured":"Xubin Wang, Jianfei Wu, Yuan Yichen, Deyu Cai, Mingzhe Li, and Weijia Jia. 2025a. Demonstration Selection for In-Context Learning via Reinforcement Learning. In Forty-second International Conference on Machine Learning."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i14.29507"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11128047"},{"key":"e_1_3_2_1_47_1","volume-title":"Denny Zhou, et al.","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. Advances in neural information processing systems, Vol. 35 (2022), 24824-24837."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i18.30044"},{"key":"e_1_3_2_1_49_1","volume-title":"Towards robust and secure embodied ai: A survey on vulnerabilities and attacks. arXiv preprint arXiv:2502.13175","author":"Xing Wenpeng","year":"2025","unstructured":"Wenpeng Xing, Minghao Li, Mohan Li, and Meng Han. 2025. Towards robust and secure embodied ai: A survey on vulnerabilities and attacks. arXiv preprint arXiv:2502.13175 (2025)."},{"key":"e_1_3_2_1_50_1","volume-title":"VGAS: Value-Guided Action-Chunk Selection for Few-Shot Vision-Language-Action Adaptation. arXiv preprint arXiv:2602.07399","author":"Xu Changhua","year":"2026","unstructured":"Changhua Xu, Jie Lu, Junyu Xuan, and En Yu. 2026. VGAS: Value-Guided Action-Chunk Selection for Few-Shot Vision-Language-Action Adaptation. arXiv preprint arXiv:2602.07399 (2026)."},{"key":"e_1_3_2_1_51_1","volume-title":"Disentangled Representation for Causal Mediation Analysis. In Thirty-Seventh AAAI Conference on Artificial Intelligence, AAAI. 10666-10674","author":"Xu Ziqi","year":"2023","unstructured":"Ziqi Xu, Debo Cheng, Jiuyong Li, Jixue Liu, Lin Liu, and Ke Wang. 2023. Disentangled Representation for Causal Mediation Analysis. In Thirty-Seventh AAAI Conference on Artificial Intelligence, AAAI. 10666-10674."},{"key":"e_1_3_2_1_52_1","volume-title":"Causal Inference with Conditional Front-Door Adjustment and Identifiable Variational Autoencoder. In The Twelfth International Conference on Learning Representations, ICLR.","author":"Xu Ziqi","year":"2024","unstructured":"Ziqi Xu, Debo Cheng, Jiuyong Li, Jixue Liu, Lin Liu, and Kui Yu. 2024. Causal Inference with Conditional Front-Door Adjustment and Identifiable Variational Autoencoder. In The Twelfth International Conference on Learning Representations, ICLR."},{"key":"e_1_3_2_1_53_1","first-page":"6853","volume-title":"Proceedings of the ACM Web Conference","author":"Yang Shiyi","year":"2026","unstructured":"Shiyi Yang, Zhibo Hu, Xinshu Li, Chen Wang, Tong Yu, Xiwei Xu, Liming Zhu, and Lina Yao. 2026 a. Drunkagent: Stealthy memory corruption in llm-powered recommender agents. In Proceedings of the ACM Web Conference 2026. 6853-6864."},{"key":"e_1_3_2_1_54_1","volume-title":"Retrieval-Augmented Review Generation for Poisoning Recommender Systems. arXiv preprint arXiv:2508.15252","author":"Yang Shiyi","year":"2025","unstructured":"Shiyi Yang, Xinshu Li, Guanglin Zhou, Chen Wang, Xiwei Xu, Liming Zhu, and Lina Yao. 2025. Retrieval-Augmented Review Generation for Poisoning Recommender Systems. arXiv preprint arXiv:2508.15252 (2025)."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/3627673.3679828"},{"key":"e_1_3_2_1_56_1","volume-title":"Incorporated Model-Agnostic Profile Injection Attacks on Recommender Systems. In 2023 IEEE International Conference on Data Mining (ICDM). IEEE, 1481-1486","author":"Yang Shiyi","year":"2023","unstructured":"Shiyi Yang, Lina Yao, Chen Wang, Xiwei Xu, and Liming Zhu. 2023. Incorporated Model-Agnostic Profile Injection Attacks on Recommender Systems. In 2023 IEEE International Conference on Data Mining (ICDM). IEEE, 1481-1486."},{"key":"e_1_3_2_1_57_1","first-page":"116167","article-title":"b. Walking the tightrope: Autonomous disentangling beneficial and detrimental drifts in non-stationary custom-tuning","volume":"38","author":"Yang Xiaoyu","year":"2026","unstructured":"Xiaoyu Yang, Jie Lu, and En Yu. 2026 b. Walking the tightrope: Autonomous disentangling beneficial and detrimental drifts in non-stationary custom-tuning. Advances in Neural Information Processing Systems, Vol. 38 (2026), 116167-116193.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02482"},{"key":"e_1_3_2_1_59_1","volume-title":"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 International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_60_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_61_1","doi-asserted-by":"publisher","DOI":"10.1093\/nsr\/nwae403"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2023.03.001"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2140"},{"key":"e_1_3_2_1_64_1","volume-title":"ADAM: An Embodied Causal Agent in Open-World Environments. In The Thirteenth International Conference on Learning Representations.","author":"Yu Shu","year":"2025","unstructured":"Shu Yu and Chaochao Lu. 2025. ADAM: An Embodied Causal Agent in Open-World Environments. In The Thirteenth International Conference on Learning Representations."},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0295"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"crossref","unstructured":"Simon Zhai Hao Bai Zipeng Lin Jiayi Pan Peter Tong Yifei Zhou Alane Suhr Saining Xie Yann LeCun Yi Ma et al. 2024. Fine-tuning large vision-language models as decision-making agents via reinforcement learning. Advances in neural information processing systems Vol. 37 (2024) 110935-110971.","DOI":"10.52202\/079017-3522"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29710"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01039"},{"key":"e_1_3_2_1_69_1","volume-title":"BERTScore: Evaluating Text Generation with BERT. In International Conference on Learning Representations.","author":"Zhang Tianyi","year":"2020","unstructured":"Tianyi Zhang, Varsha Kishore, Felix Wu, Kilian Q Weinberger, and Yoav Artzi. 2020. BERTScore: Evaluating Text Generation with BERT. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29936"},{"key":"e_1_3_2_1_71_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_72_1","doi-asserted-by":"publisher","DOI":"10.5555\/3692070.3694642"},{"key":"e_1_3_2_1_73_1","volume-title":"The Twelfth International Conference on Learning Representations.","author":"Zhuang Yuchen","year":"2024","unstructured":"Yuchen Zhuang, Xiang Chen, Tong Yu, Saayan Mitra, Victor Bursztyn, Ryan A Rossi, Somdeb Sarkhel, and Chao Zhang. 2024. ToolChain*: Efficient Action Space Navigation in Large Language Models with A* Search. In The Twelfth International Conference on Learning Representations."}],"event":{"name":"KDD '26: The 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Jeju Island Republic of Korea","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3770855.3817995","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,4]],"date-time":"2026-09-04T20:26:03Z","timestamp":1788553563000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770855.3817995"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,8]]},"references-count":73,"alternative-id":["10.1145\/3770855.3817995","10.1145\/3770855"],"URL":"https:\/\/doi.org\/10.1145\/3770855.3817995","relation":{},"subject":[],"published":{"date-parts":[[2026,8,8]]},"assertion":[{"value":"2026-08-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}