{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,23]],"date-time":"2026-08-23T14:31:12Z","timestamp":1787495472942,"version":"build-2736575974"},"publisher-location":"Singapore","reference-count":18,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819248049","type":"print"},{"value":"9789819248056","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T00:00:00Z","timestamp":1787529600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T00:00:00Z","timestamp":1787529600000},"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":[],"published-print":{"date-parts":[[2027]]},"DOI":"10.1007\/978-981-92-4805-6_12","type":"book-chapter","created":{"date-parts":[[2026,8,23]],"date-time":"2026-08-23T13:46:08Z","timestamp":1787492768000},"page":"175-188","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Characterizing and\u00a0Mitigating Context Redundancy in\u00a0LLM Agent Workflows"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-0433-4729","authenticated-orcid":false,"given":"Rongyu","family":"Luo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3989-0861","authenticated-orcid":false,"given":"Lingxiao","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4351-7993","authenticated-orcid":false,"given":"Yuezhi","family":"Che","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,8,24]]},"reference":[{"key":"12_CR1","unstructured":"Chase, H.: Langchain (2022). https:\/\/github.com\/langchain-ai\/langchain. Accessed 20 May 2024"},{"key":"12_CR2","unstructured":"Dao, T.: Flashattention-2: Faster attention with better parallelism and work partitioning. arXiv preprint arXiv:2307.08691 (2023)"},{"key":"12_CR3","unstructured":"Gim, I., Chen, G., Lee, S.S., Sarda, N., Khandelwal, A., Zhong, L.: Prompt cache: modular attention reuse for low-latency inference. In: Proceedings of Machine Learning and Systems, vol. 6, pp. 325\u2013338 (2024)"},{"key":"12_CR4","doi-asserted-by":"crossref","unstructured":"Han, T., Wang, Z., Fang, C., Zhao, S., Ma, S., Chen, Z.: Token-budget-aware LLM reasoning. In: Findings of the Association for Computational Linguistics: ACL 2025, pp. 24842\u201324855 (2025)","DOI":"10.18653\/v1\/2025.findings-acl.1274"},{"key":"12_CR5","doi-asserted-by":"crossref","unstructured":"Jiang, H., Wu, Q., Lin, C.Y., Yang, Y., Qiu, L.: Llmlingua: compressing prompts for accelerated inference of large language models. In: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pp. 13358\u201313376 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.825"},{"key":"12_CR6","doi-asserted-by":"crossref","unstructured":"Kwon, W., et al.: Efficient memory management for large language model serving with pagedattention. In: Proceedings of the 29th Symposium on Operating Systems Principles (SOSP), pp. 611\u2013626. ACM (2023)","DOI":"10.1145\/3600006.3613165"},{"key":"12_CR7","doi-asserted-by":"crossref","unstructured":"Li, Y., Dong, B., Guerin, F., Lin, C.: Compressing context to enhance inference efficiency of large language models. In: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pp. 6342\u20136353 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.391"},{"issue":"5","key":"12_CR8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3744746","volume":"16","author":"H Naveed","year":"2025","unstructured":"Naveed, H., et al.: A comprehensive overview of large language models. ACM Trans. Intell. Syst. Technol. 16(5), 1\u201372 (2025)","journal-title":"ACM Trans. Intell. Syst. Technol."},{"key":"12_CR9","doi-asserted-by":"publisher","first-page":"126544","DOI":"10.52202\/079017-4020","volume":"37","author":"SG Patil","year":"2024","unstructured":"Patil, S.G., Zhang, T., Wang, X., Gonzalez, J.E.: Gorilla: large language model connected with massive apis. Adv. Neural. Inf. Process. Syst. 37, 126544\u2013126565 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"12_CR10","unstructured":"Pope, R., et al.: Efficiently scaling transformer inference. In: Proceedings of Machine Learning and Systems (MLSys), vol. 5, pp. 1\u201314 (2023)"},{"key":"12_CR11","doi-asserted-by":"publisher","first-page":"68539","DOI":"10.52202\/075280-2997","volume":"36","author":"T Schick","year":"2023","unstructured":"Schick, T., et al.: Toolformer: language models can teach themselves to use tools. Adv. Neural. Inf. Process. Syst. 36, 68539\u201368551 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"12_CR12","doi-asserted-by":"publisher","first-page":"38154","DOI":"10.52202\/075280-1657","volume":"36","author":"Y Shen","year":"2023","unstructured":"Shen, Y., Song, K., Tan, X., Li, D., Lu, W., Zhuang, Y.: Hugginggpt: solving AI tasks with chatgpt and its friends in hugging face. Adv. Neural. Inf. Process. Syst. 36, 38154\u201338180 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"12_CR13","doi-asserted-by":"publisher","first-page":"8634","DOI":"10.52202\/075280-0377","volume":"36","author":"N Shinn","year":"2023","unstructured":"Shinn, N., Cassano, F., Gopinath, A., Narasimhan, K., Yao, S.: Reflexion: language agents with verbal reinforcement learning. Adv. Neural. Inf. Process. Syst. 36, 8634\u20138652 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"12_CR14","doi-asserted-by":"publisher","first-page":"24824","DOI":"10.52202\/068431-1800","volume":"35","author":"J Wei","year":"2022","unstructured":"Wei, J., et al.: Chain-of-thought prompting elicits reasoning in large language models. Adv. Neural. Inf. Process. Syst. 35, 24824\u201324837 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"12_CR15","unstructured":"Wu, Q., et\u00a0al.: Autogen: enabling next-gen LLM applications via multi-agent conversations. In: First Conference on Language Modeling (2024)"},{"key":"12_CR16","unstructured":"Xiao, G., Tian, Y., Chen, B., Han, S., Lewis, M.: Efficient streaming language models with attention sinks. In: International Conference on Learning Representations (ICLR) (2024)"},{"key":"12_CR17","unstructured":"Yao, S., et al.: React: synergizing reasoning and acting in language models. In: International Conference on Learning Representations (ICLR) (2023)"},{"key":"12_CR18","doi-asserted-by":"publisher","first-page":"62557","DOI":"10.52202\/079017-2000","volume":"37","author":"L Zheng","year":"2024","unstructured":"Zheng, L., et al.: Sglang: efficient execution of structured language model programs. Adv. Neural. Inf. Process. Syst. 37, 62557\u201362583 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."}],"container-title":["Lecture Notes in Computer Science","Advanced Parallel Processing Technologies"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-92-4805-6_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,23]],"date-time":"2026-08-23T13:46:10Z","timestamp":1787492770000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-4805-6_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,24]]},"ISBN":["9789819248049","9789819248056"],"references-count":18,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-4805-6_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,24]]},"assertion":[{"value":"24 August 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The technical solution and experimental design presented in this paper were independently completed by the authors. AI tools were used solely for language polishing and formatting optimization, and did not participate in the development of the research ideas or core content.","order":1,"name":"Ethics","label":"Artificial Intelligence Tools","group":{"name":"EthicsHeading","label":"Ethics"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":2,"name":"Ethics","label":"Disclosure of Interests","group":{"name":"EthicsHeading","label":"Ethics"}},{"value":"APPT","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Symposium on Advanced Parallel Processing Technologies","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Brussels","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Belgium","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 July 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 July 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"appt2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.appt-conference.com\/2026","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}