Research
Adaptive Test-Time Compute Allocation with Evolving In-Context Demonstrations
arXiv:2604.21018v1 Announce Type: new Abstract: While scaling test-time compute can substantially improve model performance, existing approaches either rely on static compute allocation or sample from
arXiv:2604.21018v1 Announce Type: new 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 test-time 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 demonstrations -- conditioning 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.
Related
- When More Thinking Hurts: Overthinking in LLM Test-Time Compute Scaling
- $S^3$: Stratified Scaling Search for Test-Time in Diffusion Language Models
- Putting the Value Back in RL: Better Test-Time Scaling by Unifying LLM Reasoners With Verifiers
- TokUR: Token-Level Uncertainty Estimation for Large Language Model Reasoning
Source: arXiv cs.AI | 2026-04-24