{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T06:13:21Z","timestamp":1783923201067,"version":"3.55.0"},"publisher-location":"Singapore","reference-count":31,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819234400","type":"print"},{"value":"9789819234417","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T00:00:00Z","timestamp":1783987200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T00:00:00Z","timestamp":1783987200000},"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\/978-981-92-3441-7_50","type":"book-chapter","created":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T05:39:29Z","timestamp":1783921169000},"page":"605-615","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Reflection-Ranker: Efficient Reflection Selection via Hidden-State Utility for Mathematical Reasoning"],"prefix":"10.1007","author":[{"given":"Yuxiang","family":"Feng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuqi","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiwei","family":"Xing","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,14]]},"reference":[{"key":"50_CR1","doi-asserted-by":"publisher","unstructured":"Wang, J., Zhu, B., Leong, C.T., Li, Y., Li, W.: Scaling over scaling: exploring test-time scaling plateau in large reasoning models. arXiv. (2025). https:\/\/doi.org\/10.48550\/arXiv.2505.20522","DOI":"10.48550\/arXiv.2505.20522"},{"key":"50_CR2","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"J Wei","year":"2022","unstructured":"Wei, J., et al.: Chain-of-thought prompting elicits reasoning in large language models. In: Advances in Neural Information Processing Systems (NeurIPS) (2022)"},{"key":"50_CR3","volume-title":"NeurIPS Datasets and Benchmarks Track","author":"D Hendrycks","year":"2021","unstructured":"Hendrycks, D., Burns, C., Kadavath, S., et al.: Measuring mathematical problem solving with the MATH dataset. In: NeurIPS Datasets and Benchmarks Track (2021)"},{"key":"50_CR4","doi-asserted-by":"publisher","unstructured":"Madaan, A., et al.: Self-refine: iterative refinement with self-feedback. arXiv. (2023). https:\/\/doi.org\/10.48550\/arXiv.2303.17651","DOI":"10.48550\/arXiv.2303.17651"},{"key":"50_CR5","doi-asserted-by":"publisher","unstructured":"Shinn, N., et al.: Reflexion: language agents with verbal reinforcement learning. arXiv. (2023). https:\/\/doi.org\/10.48550\/arXiv.2303.11366","DOI":"10.48550\/arXiv.2303.11366"},{"key":"50_CR6","doi-asserted-by":"publisher","unstructured":"Zhang, W., et al.: Self-contrast: better reflection through inconsistent solving perspectives. arXiv. (2024). https:\/\/doi.org\/10.48550\/arXiv.2401.02009","DOI":"10.48550\/arXiv.2401.02009"},{"key":"50_CR7","doi-asserted-by":"publisher","unstructured":"Xu, Z., et al.: Pride and prejudice: LLMs amplify self-bias in self-refinement. arXiv. (2024). https:\/\/doi.org\/10.48550\/arXiv.2402.11436","DOI":"10.48550\/arXiv.2402.11436"},{"key":"50_CR8","volume-title":"International Conference on Learning Representations (ICLR)","author":"X Wang","year":"2023","unstructured":"Wang, X., Wei, J., Schuurmans, D., et al.: Self-consistency improves chain of thought reasoning in language models. In: International Conference on Learning Representations (ICLR) (2023)"},{"key":"50_CR9","volume-title":"EMNLP","author":"P Aggarwal","year":"2023","unstructured":"Aggarwal, P., et al.: Let\u2019s sample step by step: adaptive-consistency for efficient reasoning and coding with LLMs. In: EMNLP (2023)"},{"key":"50_CR10","volume-title":"International Conference on Learning Representations (ICLR)","author":"Y Li","year":"2024","unstructured":"Li, Y., et al.: Escape sky-high cost: early-stopping self-consistency for multi-step reasoning. In: International Conference on Learning Representations (ICLR) (2024)"},{"key":"50_CR11","volume-title":"Math-Shepherd: Verify and Reinforce LLMs Step-by-Step without Human Annotations","author":"P Wang","year":"2024","unstructured":"Wang, P., et al.: Math-Shepherd: Verify and Reinforce LLMs Step-by-Step without Human Annotations. ACL (2024)"},{"key":"50_CR12","doi-asserted-by":"publisher","unstructured":"Alain, G., Bengio, Y.: Understanding intermediate layers using linear classifier probes. arXiv. (2016). https:\/\/doi.org\/10.48550\/arXiv.1610.01644","DOI":"10.48550\/arXiv.1610.01644"},{"key":"50_CR13","doi-asserted-by":"publisher","unstructured":"Skean, O., Arefin, M.R., LeCun, Y., Shwartz-Ziv, R.: Does representation matter? Exploring intermediate layers in large language models. arXiv. (2024). https:\/\/doi.org\/10.48550\/arXiv.2412.09563","DOI":"10.48550\/arXiv.2412.09563"},{"key":"50_CR14","doi-asserted-by":"publisher","unstructured":"Zhu, X., Jiang, J., Khalili, M.M., Zhu, Z.: From emergence to control: probing and modulating self-reflection in language models. arXiv. (2025). https:\/\/doi.org\/10.48550\/arXiv.2506.12217","DOI":"10.48550\/arXiv.2506.12217"},{"key":"50_CR15","doi-asserted-by":"publisher","unstructured":"Yan, G., Sun, C., Weng, L.: ReflCtrl: controlling LLM reflection via representation engineering. arXiv. (2025). https:\/\/doi.org\/10.48550\/arXiv.2512.13979","DOI":"10.48550\/arXiv.2512.13979"},{"key":"50_CR16","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"R Rafailov","year":"2023","unstructured":"Rafailov, R., Sharma, A., Mitchell, E., Ermon, S., Manning, C.D., Finn, C.: Direct preference optimization: your language model is secretly a reward model. In: Advances in Neural Information Processing Systems (NeurIPS) (2023)"},{"key":"50_CR17","volume-title":"International Conference on Machine Learning (ICML)","author":"Z Cao","year":"2007","unstructured":"Cao, Z., Qin, T., Liu, T.-Y., Tsai, M.-F., Li, H.: Learning to rank: from pairwise approach to list wise approach. In: International Conference on Machine Learning (ICML) (2007)"},{"key":"50_CR18","doi-asserted-by":"publisher","unstructured":"Anonymous: Language ranker: a lightweight ranking framework for LLM decoding. arXiv. (2025). https:\/\/doi.org\/10.48550\/arXiv.2510.21883","DOI":"10.48550\/arXiv.2510.21883"},{"key":"50_CR19","unstructured":"Hugging Face, MATH-500. 2024"},{"key":"50_CR20","unstructured":"Math-AI, AMC 2023 benchmark. 2024"},{"key":"50_CR21","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"A Lewkowycz","year":"2022","unstructured":"Lewkowycz, A., et al.: Solving quantitative reasoning problems with language models. In: Advances in Neural Information Processing Systems (NeurIPS) (2022)"},{"key":"50_CR22","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Team, M.-A.: AIME 2024 Dataset (2024)","DOI":"10.5465\/AMPROC.2024.98bp"},{"key":"50_CR23","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Team, M.-A.: AIME 2025 Dataset (2025)","DOI":"10.5465\/AMPROC.2025.23129abstract"},{"key":"50_CR24","unstructured":"Qwen Team: Qwen2.5: A Party of Foundation Models (2024)"},{"key":"50_CR25","unstructured":"Qwen Team: Qwen3 Technical Report (2025)"},{"key":"50_CR26","unstructured":"Meta AI: Llama 3.2: Open Foundation and Fine-Tuned Chat Models (2024)"},{"key":"50_CR27","volume-title":"Language Models Are Unsupervised Multitask Learners","author":"A Radford","year":"2019","unstructured":"Radford, A., et al.: Language Models Are Unsupervised Multitask Learners. OpenAI (2019)"},{"key":"50_CR28","doi-asserted-by":"publisher","unstructured":"Liu, C.-Y., Zeng, L., Xiao, Y., et al.: Skywork-reward-V2: scaling preference data curation via human-AI synergy. arXiv. (2025). https:\/\/doi.org\/10.48550\/arXiv.2507.01352","DOI":"10.48550\/arXiv.2507.01352"},{"key":"50_CR29","volume-title":"ACM Symposium on Operating Systems Principles (SOSP)","author":"W Kwon","year":"2023","unstructured":"Kwon, W., et al.: Efficient memory management for large language model serving with PagedAttention. In: ACM Symposium on Operating Systems Principles (SOSP) (2023)"},{"key":"50_CR30","unstructured":"kyujinpy: Orca-math-DPO (2023)"},{"key":"50_CR31","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"S Yao","year":"2023","unstructured":"Yao, S., et al.: Tree of thoughts: deliberate problem solving with large language models. In: Advances in Neural Information Processing Systems (NeurIPS) (2023)"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-92-3441-7_50","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T05:39:34Z","timestamp":1783921174000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-3441-7_50"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,14]]},"ISBN":["9789819234400","9789819234417"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-3441-7_50","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,14]]},"assertion":[{"value":"14 July 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Toronto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Canada","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":"22 July 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2026a","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/2026\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}