# Adaptive Test-Time Compute Allocation with Evolving In-Context Demonstrations

arXiv: https://arxiv.org/abs/2604.21018 · HTML: https://mlsanity.com/paper/2604.21018/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning.
- Builds on 16 of its 54 references that are in the map.
- First posted on arXiv 22 Apr 2026.

## Placed in

- LLM reasoning / [Test-time compute and efficient thinking](https://mlsanity.com/lr/test-time-compute-and-efficient-thinking/)

## Builds on (most cited first, 16 of 16)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [What Makes Good In-Context Examples for GPT-3?](https://mlsanity.com/paper/2101.06804/) (2021)
- [Large Language Monkeys: Scaling Inference Compute with Repeated Sampling](https://mlsanity.com/paper/2407.21787/) (2024)
- [Solving math word problems with process- and outcome-based feedback](https://mlsanity.com/paper/2211.14275/) (2022)
- [Hallucination is Inevitable: An Innate Limitation of Large Language Models](https://mlsanity.com/paper/2401.11817/) (2024)
- [Why Language Models Hallucinate](https://mlsanity.com/paper/2509.04664/) (2025)
- [Adaptive Inference-Time Compute: LLMs Can Predict if They Can Do Better, Even Mid-Generation](https://mlsanity.com/paper/2410.02725/) (2024)
- [An optimal algorithm for the Thresholding Bandit Problem](https://mlsanity.com/paper/1605.08671/) (2016)
- [Self-Improving LLM Agents at Test-Time](https://mlsanity.com/paper/2510.07841/) (2025)
- [Rethinking Inference-Time Scaling: Efficiency Limits and Linguistic Signals](https://mlsanity.com/paper/2504.14047/) (2025)
- [On the Role of Temperature Sampling in Test-Time Scaling](https://mlsanity.com/paper/2510.02611/) (2025)
- [Adaptive Rectification Sampling for Test-Time Compute Scaling](https://mlsanity.com/paper/2504.01317/) (2025)
- [Rethinking the Unsolvable: When In-Context Search Meets Test-Time Scaling](https://mlsanity.com/paper/2505.22290/) (2025)

## Built on by (most cited first, 1 of 1)

- [Active Testing of Large Language Models via Approximate Neyman Allocation](https://mlsanity.com/paper/2605.10075/) (2026)

## Abstract (arXiv)

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.