Cache Coherent Resampling for Efficient Test Time Scaling in LLM Reasoning via Adaptive Sequential Monte Carlo

^*Corresponding author for this work

Research output: Contribution to journal › Conference article › peer-review

Original language	English
Journal	Proceedings of Machine Learning Research
Publication status	Accepted/In press - 30 Apr 2026
Event	Forty-Third International Conference on Machine Learning - COEX Convention & Exhibition Center, Seoul, Korea, Republic of Duration: 6 Jul 2026 → 11 Jul 2026 https://icml.cc/

Cite this

@article{745964aa4837479495df43133a6bdf11,

title = "Cache Coherent Resampling for Efficient Test Time Scaling in LLM Reasoning via Adaptive Sequential Monte Carlo",

author = "Ke Wang and Zehao Yu and Luwei Wang and Yongchao Huang",

year = "2026",

month = apr,

day = "30",

language = "English",

journal = "Proceedings of Machine Learning Research",

issn = "2640-3498",

publisher = "ML Research Press",

note = "Forty-Third International Conference on Machine Learning, ICML 2026 ; Conference date: 06-07-2026 Through 11-07-2026",

url = "https://icml.cc/",

}

TY - JOUR

T1 - Cache Coherent Resampling for Efficient Test Time Scaling in LLM Reasoning via Adaptive Sequential Monte Carlo

AU - Wang, Ke

AU - Yu, Zehao

AU - Wang, Luwei

AU - Huang, Yongchao

PY - 2026/4/30

Y1 - 2026/4/30

UR - https://icml.cc/

M3 - Conference article

SN - 2640-3498

JO - Proceedings of Machine Learning Research

JF - Proceedings of Machine Learning Research

T2 - Forty-Third International Conference on Machine Learning

Y2 - 6 July 2026 through 11 July 2026

ER -