{"slug": "a-survey-of-test-time-compute-from-intuitive-inference-to-deliberate-reasoning", "title": "A Survey of Test-time Compute: From Intuitive Inference to Deliberate Reasoning", "summary": "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.", "body_md": "##### Abstract\n\nThe 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\n- Anthology ID:\n- 2026.cl-3.10\n- Volume:\n- [Computational Linguistics, Volume 52, Issue 3 - September 2026](https://aclanthology.org/volumes/2026.cl-3/)\n- Month:\n- September\n- Year:\n- 2026\n- Address:\n- Cambridge, MA\n- Venue:\n- [CL](https://aclanthology.org/venues/cl/)\n- SIG:\n- Publisher:\n- MIT Press\n- Note:\n- Pages:\n- 1253–1307\n- Language:\n- URL:\n- [https://aclanthology.org/2026.cl-3.10/](https://aclanthology.org/2026.cl-3.10/)\n- DOI:\n- [10.1162/coli.a.629](https://doi.org/10.1162/coli.a.629)\n- Cite (ACL):\n- 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.\n- Cite (Informal):\n- [A Survey of Test-time Compute: From Intuitive Inference to Deliberate Reasoning](https://aclanthology.org/2026.cl-3.10/) (Ji et al., CL 2026)\n- PDF:\n- [https://aclanthology.org/2026.cl-3.10.pdf](https://aclanthology.org/2026.cl-3.10.pdf)", "url": "https://wpnews.pro/news/a-survey-of-test-time-compute-from-intuitive-inference-to-deliberate-reasoning", "canonical_source": "https://aclanthology.org/2026.cl-3.10/", "published_at": "2026-10-26 00:00:00+00:00", "updated_at": "2026-10-26 23:12:33.808296+00:00", "lang": "en", "topics": ["artificial-intelligence", "machine-learning", "large-language-models", "ai-research", "natural-language-processing"], "entities": ["Yixin Ji", "Juntao Li", "Yang Xiang", "Hai Ye", "Kaixin Wu", "Kai Yao", "Jia Xu", "Computational Linguistics"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/a-survey-of-test-time-compute-from-intuitive-inference-to-deliberate-reasoning", "markdown": "https://wpnews.pro/news/a-survey-of-test-time-compute-from-intuitive-inference-to-deliberate-reasoning.md", "text": "https://wpnews.pro/news/a-survey-of-test-time-compute-from-intuitive-inference-to-deliberate-reasoning.txt", "jsonld": "https://wpnews.pro/news/a-survey-of-test-time-compute-from-intuitive-inference-to-deliberate-reasoning.jsonld"}}