Year: 2026
Type: conference-paper
Abstract: While scaling test-time compute can substantially improve model performance, existing approaches either rely on static compute allocation or sample from fixed generation distributions.In this work, we introduce a testtime compute allocation framework that jointly adapts where computation is spent and how generation is performed.Our method begins with a warm-up phase that identifies easy queries and assembles an initial pool of question-response pairs from the test set itself.An adaptive phase then concentrates further computation on unresolved queries while reshaping their generation distributions through evolving in-context demonstrationsconditioning each generation on successful responses from semantically related queries rather than resampling from a fixed distribution.Experiments across math, coding, and reasoning benchmarks demonstrate that our approach consistently outperforms existing baselines while consuming substantially less inference-time compute.
Authors: Bowen Zuo, Dongruo Zhou, Yinglun Zhu
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W7166835654