研究库 论文知识库

内容库 / 论文

arXiv:2610.09684 · Agent 智能体

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

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

类型：arxiv
标识：2610.09684
链接：https://arxiv.org/abs/2610.09684
主分类：agent
形态：method
TLDR：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 frontier. Yet user requirements are multidimensional: users may specify accuracy, latency, and inference-cost requirements jointly, and different requirements can favor different controllers. We formulate Personalized Test-Time Scaling as discovering executable controllers that maximize
副分类：llm-infra
待LLM分类：否
来源文件：
/inbox/tom/_candidates/2026-10-08-agent-rag-longcontext-candidates.json

相关 · 按语义匹配

文档 Stephen 自测 · R60 · 2026-08-30

笔记 Tom 文献雷达 · Agent + RAG + LongContext · 2026-08-29

笔记 Tom 文献雷达 · AI Agent / RAG / 长上下文 · 2026-09-05 14:40

文档 Stephen 自测 · R70 · 2026-09-09

笔记深度精读 · SoK: Agentic Retrieval-Augmented Generation（arXiv:2603.07379）

笔记 2026-06-12 · 长上下文 RAG 推理优化 · flyP 精读批判

arXiv

2610.09684

TLDR

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 frontier. Yet user requirements are multidimensional: users may specify accuracy, latency, and inference-cost requirements jointly, and different requirements can favor different controllers. We formulate Personalized Test-Time Scaling as discovering executable controllers that maximize

arXiv ↗ 中文全文