{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T05:15:07Z","timestamp":1784178907788,"version":"3.55.0"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T00:00:00Z","timestamp":1768953600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T00:00:00Z","timestamp":1768953600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci. China Inf. Sci."],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1007\/s11432-024-4554-x","type":"journal-article","created":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T02:46:18Z","timestamp":1769827578000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["WESE: weak exploration to strong exploitation for LLM agents"],"prefix":"10.1007","volume":"69","author":[{"given":"Xu","family":"Huang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weiwen","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaolong","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xingmei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Defu","family":"Lian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yasheng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruiming","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Enhong","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,1,21]]},"reference":[{"key":"4554_CR1","unstructured":"Zhao W X, Zhou K, Li J, et al. A survey of large language models. 2023. ArXiv:2303.18223"},{"key":"4554_CR2","unstructured":"Wang L, Ma C, Feng X, et al. A survey on large language model based autonomous agents. 2023. ArXiv:2308.11432"},{"key":"4554_CR3","unstructured":"Xi Z, Chen W, Guo X, et al. The rise and potential of large language model based agents: a survey. 2023. ArXiv:2309.07864"},{"key":"4554_CR4","unstructured":"Huang X, Liu W, Chen X, et al. Understanding the planning of LLM agents: a survey. 2024. ArXiv:2402.02716"},{"key":"4554_CR5","first-page":"24824","volume-title":"Proceedings of Advances in Neural Information Processing Systems","author":"J Wei","year":"2022","unstructured":"Wei J, Wang X, Schuurmans D, et al. Chain-of-thought prompting elicits reasoning in large language models. In: Proceedings of Advances in Neural Information Processing Systems, 2022. 35: 24824\u201324837"},{"key":"4554_CR6","unstructured":"Wang X, Wei J, Schuurmans D, et al. Self-consistency improves chain of thought reasoning in language models. 2022. ArXiv:2203.11171"},{"key":"4554_CR7","unstructured":"Yao S, Zhao J, Yu D, et al. React: synergizing reasoning and acting in language models. 2022. ArXiv:2210.03629"},{"key":"4554_CR8","first-page":"22199","volume-title":"Proceedings of Advances in Neural Information Processing Systems","author":"T Kojima","year":"2022","unstructured":"Kojima T, Gu S S, Reid M, et al. Large language models are zero-shot reasoners. In: Proceedings of Advances in Neural Information Processing Systems, 2022. 35: 22199\u201322213"},{"key":"4554_CR9","unstructured":"Shinn N, Labash B, Gopinath A. Reflexion: an autonomous agent with dynamic memory and self-reflection. 2023. ArXiv:2303.11366"},{"key":"4554_CR10","first-page":"41","volume-title":"Proceedings of the 27th International Conference on Artificial Intelligence","author":"M A C\u00f4t\u00e9","year":"2019","unstructured":"C\u00f4t\u00e9 M A, K\u00e1d\u00e1r A, Yuan X, et al. Textworld: a learning environment for text-based games. In: Proceedings of the 27th International Conference on Artificial Intelligence, Stockholm, 2019. 41\u201375"},{"key":"4554_CR11","unstructured":"Shridhar M, Yuan X, C\u00f4t\u00e9 M A, et al. Alfworld: aligning text and embodied environments for interactive learning. 2020. ArXiv:2010.03768"},{"key":"4554_CR12","doi-asserted-by":"crossref","unstructured":"Wang R, Jansen P, C\u00f4t\u00e9 M A, et al. Scienceworld: is your agent smarter than a 5th grader? 2022. ArXiv:2203.07540","DOI":"10.18653\/v1\/2022.emnlp-main.775"},{"key":"4554_CR13","doi-asserted-by":"crossref","unstructured":"Wang L, Xu W, Lan Y, et al. Plan-and-solve prompting: improving zero-shot chain-of-thought reasoning by large language models. 2023. ArXiv:2305.04091","DOI":"10.18653\/v1\/2023.acl-long.147"},{"key":"4554_CR14","unstructured":"Yao S, Yu D, Zhao J, et al. Tree of thoughts: deliberate problem solving with large language models. 2023. ArXiv:2305.10601"},{"key":"4554_CR15","unstructured":"Besta M, Blach N, Kubicek A, et al. Graph of thoughts: solving elaborate problems with large language models. 2023. ArXiv:2308.09687"},{"key":"4554_CR16","unstructured":"Liu B, Jiang Y, Zhang X, et al. LLM+ P: empowering large language models with optimal planning proficiency. 2023. ArXiv:2304.11477"},{"key":"4554_CR17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3704435","volume":"57","author":"Y Qin","year":"2025","unstructured":"Qin Y, Hu S, Lin Y, et al. Tool learning with foundation models. ACM Comput Surv, 2025, 57: 1\u201340","journal-title":"ACM Comput Surv"},{"key":"4554_CR18","unstructured":"Wu C, Yin S, Qi W, et al. Visual ChatGPT: talking, drawing and editing with visual foundation models. 2023. ArXiv:2303.04671"},{"key":"4554_CR19","unstructured":"Qin Y, Liang S, Ye Y, et al. ToolLLM: facilitating large language models to master 16000+ real-world APIs. 2023. ArXiv:2307.16789"},{"key":"4554_CR20","first-page":"1","volume-title":"Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology","author":"J S Park","year":"2023","unstructured":"Park J S, O\u2019Brien J, Cai C J, et al. Generative agents: interactive simulacra of human behavior. In: Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology, 2023. 1\u201322"},{"key":"4554_CR21","unstructured":"Zhang D, Chen L, Zhang S, et al. Large language model is semi-parametric reinforcement learning agent. 2023. ArXiv:2306.07929"},{"key":"4554_CR22","unstructured":"Wang W, Dong L, Cheng H, et al. Augmenting language models with long-term memory. 2023. ArXiv:2306.07174"},{"key":"4554_CR23","unstructured":"Wang G, Xie Y, Jiang Y, et al. Voyager: an open-ended embodied agent with large language models. 2023. ArXiv:2305.16291"},{"key":"4554_CR24","volume-title":"Proceedings of the 37th Conference on Neural Information Processing Systems","author":"Z Wang","year":"2023","unstructured":"Wang Z, Cai S, Chen G, et al. Describe, explain, plan and select: interactive planning with LLMs enables open-world multi-task agents. In: Proceedings of the 37th Conference on Neural Information Processing Systems, 2023"},{"key":"4554_CR25","doi-asserted-by":"crossref","unstructured":"Yang Z, Qi P, Zhang S, et al. Hotpotqa: a dataset for diverse, explainable multi-hop question answering. 2018. ArXiv:1809.09600","DOI":"10.18653\/v1\/D18-1259"},{"key":"4554_CR26","unstructured":"Thorne J, Vlachos A, Christodoulopoulos C, et al. Fever: a large-scale dataset for fact extraction and verification. 2018. ArXiv:1803.05355"},{"key":"4554_CR27","unstructured":"Huang J, Chang K C C. Towards reasoning in large language models: a survey. 2022. ArXiv:2212.10403"},{"key":"4554_CR28","unstructured":"Sun J, Zheng C, Xie E, et al. A survey of reasoning with foundation models. 2023. ArXiv:2312.11562"},{"key":"4554_CR29","unstructured":"Yang S, Nachum O, Du Y, et al. Foundation models for decision making: problems, methods, and opportunities. 2023. ArXiv:2303.04129"},{"key":"4554_CR30","doi-asserted-by":"publisher","first-page":"3580","DOI":"10.1109\/TKDE.2024.3352100","volume":"36","author":"S Pan","year":"2024","unstructured":"Pan S, Luo L, Wang Y, et al. Unifying large language models and knowledge graphs: a roadmap. IEEE Trans Knowl Data Eng, 2024, 36: 3580\u20133599","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"4554_CR31","unstructured":"Wadhwa S, Amir S, Wallace B C. Revisiting relation extraction in the era of large language models. 2023. ArXiv:2305.05003"},{"key":"4554_CR32","unstructured":"Papaluca A, Krefl D, Rodriguez S M, et al. Zero-and few-shots knowledge graph triplet extraction with large language models. 2023. ArXiv:2312.01954"},{"key":"4554_CR33","unstructured":"Zeng A, Liu M, Lu R, et al. Agenttuning: enabling generalized agent abilities for LLMs. 2023. ArXiv:2310.12823"},{"key":"4554_CR34","unstructured":"Xi Z, Ding Y, Chen W, et al. Agentgym: evolving large language model-based agents across diverse environments. 2024. ArXiv:2406.04151"},{"key":"4554_CR35","unstructured":"Touvron H, Martin L, Stone K, et al. Llama 2: open foundation and fine-tuned chat models. 2023. ArXiv:2307.09288"},{"key":"4554_CR36","volume-title":"Llama 3 model card","author":"AI@Meta","year":"2024","unstructured":"AI@Meta. Llama 3 model card. 2024. https:\/\/github.com\/meta-llama\/llama3\/blob\/main\/MODELCARD.md"},{"key":"4554_CR37","unstructured":"Yang A, Yang B, Hui B, et al. Qwen2 technical report. 2024. ArXiv:2407.10671"},{"key":"4554_CR38","unstructured":"Kaplan J, McCandlish S, Henighan T, et al. Scaling laws for neural language models. 2020. ArXiv:2001.08361"}],"container-title":["Science China Information Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11432-024-4554-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11432-024-4554-x","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11432-024-4554-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T02:46:22Z","timestamp":1769827582000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11432-024-4554-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,21]]},"references-count":38,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,3]]}},"alternative-id":["4554"],"URL":"https:\/\/doi.org\/10.1007\/s11432-024-4554-x","relation":{},"ISSN":["1674-733X","1869-1919"],"issn-type":[{"value":"1674-733X","type":"print"},{"value":"1869-1919","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,21]]},"assertion":[{"value":"8 May 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 January 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 August 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 January 2026","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"132104"}}