A Survey of Test-time Compute: From Intuitive Inference to Deliberate Reasoning

Yixin Ji, Juntao Li, Yang Xiang, Hai Ye, Kaixin Wu, Kai Yao, Jia Xu, Linjian Mo and Min Zhang published "A Survey of Test-time Compute: From Intuitive Inference to Deliberate Reasoning" in Computational Linguistics, Volume 52, Issue 3, pages 1253–1307, dated September 2026. The survey traces test-time compute from System-1 models, where it addresses distribution shifts and improves robustness and generalization through parameter updating, input modification, representation editing and output calibration, to System-2 models, where repeated sampling, self-correction and tree search enhance reasoning on complex problems. The authors frame the work around the transition from System-1 models to weak System-2 models and then to strong System-2 models, citing the o1 model's performance on complex reasoning as evidence that test-time compute scaling can unlock System-2 thinking.

Abstract The remarkable performance of the o1 model in complex reasoning demonstrates that test-time compute scaling can further unlock the model’s potential, enabling powerful System-2 thinking. However, there is still a lack of comprehensive surveys for test-time compute scaling. We trace the concept of test-time compute back to System-1 models. In System-1 models, test-time compute addresses distribution shifts and improves robustness and generalization through parameter updating, input modification, representation editing, and output calibration. In System-2 models, it enhances the model’s reasoning ability to solve complex problems through repeated sampling, self-correction, and tree search. We organize this survey according to the trend of System-1 to System-2 thinking, highlighting the key role of test-time compute in the transition from System-1 models to weak System-2 models, and then to strong System-2 models. We also point out advanced topics and future directions.1 - Anthology ID: - 2026.cl-3.10 - Volume: - Computational Linguistics, Volume 52, Issue 3 - September 2026 https://aclanthology.org/volumes/2026.cl-3/ - Month: - September - Year: - 2026 - Address: - Cambridge, MA - Venue: - CL https://aclanthology.org/venues/cl/ - SIG: - Publisher: - MIT Press - Note: - Pages: - 1253–1307 - Language: - URL: - https://aclanthology.org/2026.cl-3.10/ https://aclanthology.org/2026.cl-3.10/ - DOI: - 10.1162/coli.a.629 https://doi.org/10.1162/coli.a.629 - Cite ACL : - Yixin Ji, Juntao Li, Yang Xiang, Hai Ye, Kaixin Wu, Kai Yao, Jia Xu, Linjian Mo, and Min Zhang. 2026. A Survey of Test-time Compute: From Intuitive Inference to Deliberate Reasoning https://aclanthology.org/2026.cl-3.10/ . Computational Linguistics , 52 3 :1253–1307. - Cite Informal : - A Survey of Test-time Compute: From Intuitive Inference to Deliberate Reasoning https://aclanthology.org/2026.cl-3.10/ Ji et al., CL 2026 - PDF: - https://aclanthology.org/2026.cl-3.10.pdf https://aclanthology.org/2026.cl-3.10.pdf