{"type":"ScholarlyArticle","title":"Cross Domain Test Time Scaling: Scale Knowledge and Reasoning on Cross Domains","authors":[{"name":"Minxi Yan","slug":"minxi-yan","given":"Minxi","family":"Yan","affiliation":""},{"name":"Yihua Shao","slug":"yihua-shao","given":"Yihua","family":"Shao","affiliation":""},{"name":"Yanling Pan","slug":"yanling-pan","given":"Yanling","family":"Pan","affiliation":""},{"name":"Siyu Chen","slug":"siyu-chen","given":"Siyu","family":"Chen","affiliation":""},{"name":"Hongjuan Pei","slug":"hongjuan-pei","given":"Hongjuan","family":"Pei","affiliation":""},{"name":"Hao Tang","slug":"hao-tang","given":"Hao","family":"Tang","affiliation":""},{"name":"Fei Ma","slug":"fei-ma","given":"Fei","family":"Ma","affiliation":""},{"name":"Jingcai Guo","slug":"jingcai-guo","given":"Jingcai","family":"Guo","affiliation":""},{"name":"Nicu Sebe","slug":"nicu-sebe","given":"Nicu","family":"Sebe","affiliation":""}],"abstract":"Test-time scaling (TTS) has demonstrated remarkable potential in enhancing the reasoning capabilities of Large Language Models (LLMs) and Large Vision-Language Models (LVLMs). However, its application has primarily been limited to domains such as mathematics and programming, owing to their reasoning-intensive nature and the ease of result verification. Its utility in other knowledge-intensive fields, such as medicine and general scientific research, remains underexplored.\r\nTo bridge this gap and unlock the potential of TTS in broader domains, we propose Cross-Domain TTS, a novel framework that enables task-tailored scaling. This framework consists of two key components: a conformal prediction-based cold-start strategy and an information-gain-based dynamic reasoning adjustment. The CP-based cold-start strategy guides the model's initialization during test-time scaling based on conformal prediction theory, while the information-gain-based dynamic reasoning adjustment guides the model's reasoning progress through a progress vector according to the information gain of reasoning steps. We conducted experiments using LLMs and LVLMs on cross-domain benchmarks. Our results demonstrate that the proposed framework consistently improves performance across various domain-specific datasets. For instance, in the medical domain, it achieves an improvement of up to 17% in pass@1 accuracy while reducing inference latency and saving up to 30% in token consumption. Code is available at https://github.com/Yan0613/Cross-Domain-TTS.","doi":"10.24963/ijcai.2026/217","url":"https://ijcai.org/proceedings/2026/217","pdf":"https://ijcai.org/proceedings/2026/0217.pdf","markdown":"https://ijcai.org/proceedings/2026/217.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/217","volume":{"slug":"2026","title":"Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2026","url":"https://ijcai.org/proceedings/2026/","year":2026,"location":"Bremen, Germany","dates":"15-21 August 2026","editors":"Diego Calvanese","isbn":"978-1-956792-09-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2026"},"section":"Computer Vision","track":"Main Track","number":217,"pages":{"first":1947,"last":1955},"keywords":["Machine Learning: Foundation models","Machine Learning: Cost-sensitive learning","Computer Vision: Transfer, low-shot, semi- and un- supervised learning","Machine Learning: Learning sparse models","Machine Learning: Open-World/Open-Set/OOD Learning"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}