AI RESEARCH
On the Overscaling Curse of Parallel Thinking: System Efficacy Contradicts Sample Efficiency
arXiv CS.AI
•
ArXi:2601.21619v2 Announce Type: replace-cross Parallel thinking improves LLM reasoning through multi-path sampling and aggregation. In standard evaluations, due to a lack of sample-specific priors, all samples share a global budget chosen to maximize dataset accuracy. However, many samples reach their best accuracy with much smaller budgets, causing low budget utilization. This contradiction between system efficacy and sample efficiency constitutes the Overscaling Curse.