From Pareto to Preference: Personalized Test-Time Scaling via Amortized Agentic Policy Discovery

Shared on Bluesky by 2 AI experts

• A arxiv cs.CL @arxiv-cs-cl.bsky.social: Xinglin Wang, Zishen Liu, Tong Zheng, Shaoxiong Feng, Peiwen Yuan, Yiwei Li, Jiayi Shi, Yueqi Zhang, Chuyi Tan, Ji Zhang, Boyuan Pan, Kan Li… →
• A AI Firehose @ai-firehose.column.social: PersonTTS redefines test-time scaling for language models by customizing controllers for user needs, enhancing accuracy and cost efficiency.… →