From Pareto to Preference: Personalized Test-Time Scaling via Amortized Agentic Policy Discovery
Test-time scaling (TTS) improves the reasoning capabilities of large language models by allocating additional inference computation. Existing approaches to improving TTS efficiency largely optimize accuracy against one resource dimension at a time, advancing either the accuracy--cost or accuracy--latency Pareto frontie...
Xing-Lin Wang, Zi-Shen Liu, Tong Zheng et al.
· 0 citations