{"ID":2842848,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.09345","arxiv_id":"2511.09345","title":"Seer Self-Consistency: Advance Budget Estimation for Adaptive Test-Time Scaling","abstract":"Test-time scaling improves the inference performance of Large Language Models (LLMs) but also incurs substantial computational costs. Although recent studies have reduced token consumption through dynamic self-consistency, they remain constrained by the high latency of sequential requests. In this paper, we propose SeerSC, a dynamic self-consistency framework that simultaneously improves token efficiency and latency by integrating System 1 and System 2 reasoning. Specifically, we utilize the rapid System 1 to compute the answer entropy for given queries. This score is then used to evaluate the potential of samples for scaling, enabling dynamic self-consistency under System 2. Benefiting from the advance and accurate estimation provided by System 1, the proposed method can reduce token usage while simultaneously achieving a significant decrease in latency through parallel generation. It outperforms existing methods, achieving up to a 47% reduction in token consumption and a 43% reduction in inference latency without significant performance loss.","short_abstract":"Test-time scaling improves the inference performance of Large Language Models (LLMs) but also incurs substantial computational costs. Although recent studies have reduced token consumption through dynamic self-consistency, they remain constrained by the high latency of sequential requests. In this paper, we propose See...","url_abs":"https://arxiv.org/abs/2511.09345","url_pdf":"https://arxiv.org/pdf/2511.09345v2","authors":"[\"Shiyu Ji\",\"Yixuan Wang\",\"Yijun Liu\",\"Qingfu Zhu\",\"Wanxiang Che\"]","published":"2025-11-12T13:57:43Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}