跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.23154 · v1

Learning Stratified Policies for Inference-Time Objectives

面向推理时目标的分层策略学习

首次提交 2026-11-18 02:06
版本更新 2026-11-18 02:06
雷达观测 2026-11-18 12:34
arXiv ↗PDF ↗

摘要

Inference-time scaling improves the performance of large language models by sampling multiple responses and evaluating their collective utility. However, many existing approaches obtain these samples by repeatedly sampling from a single policy. In this work, we study if the sample budget at inference time can instead be allocated across a population of policies. We introduce stratified policies, where each of kk learned policies contributes one response to a kk-sample inference-time objective. We realize this policy population using separate LoRA adapters on a shared language model backbone and optimize it for pass@kk. We theoretically motivate the approach by analyzing the linear setting; a population of LoRAs can achieve zero best-of-kk approximation error in settings where every single LoRA has strictly positive prediction error. Empirically, we demonstrate that stratified policies consistently improve pass@kk over a single-policy baseline across multiple reasoning tasks. Overall, our results highlight how distributing samples across complementary policies can be a more effective use of sample budget than repeated i.i.d. sampling from a single policy at inference time.

AI 论文解读

基于摘要 · 非全文审阅

作者提出将推理时的采样预算分配给一组互补的 LoRA 策略(分层策略),以提升大语言模型的 pass@k 表现。

正在读取账号与研究记录…

版本差异

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v1 · 2026-11-18 02:06 · 最新观测版本

Learning Stratified Policies for Inference-Time Objectives

Inference-time scaling improves the performance of large language models by sampling multiple responses and evaluating their collective utility. However, many existing approaches obtain these samples by repeatedly sampling from a single policy. In this work, we study if the sample budget at inference time can instead be allocated across a population of policies. We introduce stratified policies, where each of kk learned policies contributes one response to a kk-sample inference-time objective. We realize this policy population using separate LoRA adapters on a shared language model backbone and optimize it for pass@kk. We theoretically motivate the approach by analyzing the linear setting; a population of LoRAs can achieve zero best-of-kk approximation error in settings where every single LoRA has strictly positive prediction error. Empirically, we demonstrate that stratified policies consistently improve pass@kk over a single-policy baseline across multiple reasoning tasks. Overall, our results highlight how distributing samples across complementary policies can be a more effective use of sample budget than repeated i.i.d. sampling from a single policy at inference time.

查看此版本解读 →查看此版本原文 ↗