arXiv Machine Learning
Towards Better Exploration in Sequential Test-Time Scaling
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
Jun 2
Beyond the Frontier: Stochastic Backtracking for Efficient Test-Time Scaling
arXiv:2605. 25143v2 Announce Type: replace Abstract: Test-time scaling improves language model reasoning by spending additional compute to explore multiple solution trajectories.
arXiv AI
Jul 1
Optimal Self-Consistency for Efficient Reasoning with Large Language Models
arXiv:2511. 12309v2 Announce Type: replace-cross Abstract: Self-consistency (SC) is a widely used test-time inference technique for improving performance in chain-of-thought reasoning.
arXiv AI
Aug 12
ThinkRetrieve: Retrieval-Augmented Reasoning Traces for Test-Time Scaling
arXiv:2608. 10928v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) improve performance by allocating additional inference-time compute to generate extended chain-of-thought reasoning.
arXiv AI
Jun 16
Parallel Test-Time Scaling with Multi-Sequence Verifiers
arXiv:2603. 03417v2 Announce Type: replace-cross Abstract: Parallel test-time scaling, which generates multiple candidate solutions for a single problem, is a powerful technique for improving large language model performance.
arXiv Machine Learning
Jul 24
Test-Time Scaling via Error Localization
arXiv:2607. 21453v1 Announce Type: new Abstract: Scaling inference-time computation has emerged as a reliable method to improve the performance of large language models on complex reasoning and programming tasks.
arXiv Computation and Language
Aug 31
Ladders in Chaos: When, How, (and Perhaps Why) Does Test-Time Scaling Improve LLM Machine Translation
The paper examines two test‑time scaling methods for large language models in machine translation: sequential sampling, where later attempts build on earlier ones, and parallel sampling, such as independent i.i.d. sampling with reranking. Sequential sampling shows a higher performance ceiling, offering a more diverse and effective set of translations, especially with limited sampling budgets. Human analysis reveals that while sequential sampling improves fluency and naturalness, it can reduce accuracy when the inference budget is large, and the authors attribute this effect to the model’s access to a larger target‑side context.