← 研踪 PaperTrailarXiv: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
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 learned policies contributes one response to a -sample inference-time objective. We realize this policy population using separate LoRA adapters on a shared language model backbone and optimize it for pass@. We theoretically motivate the approach by analyzing the linear setting; a population of LoRAs can achieve zero best-of- approximation error in settings where every single LoRA has strictly positive prediction error. Empirically, we demonstrate that stratified policies consistently improve pass@ 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.
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 learned policies contributes one response to a -sample inference-time objective. We realize this policy population using separate LoRA adapters on a shared language model backbone and optimize it for pass@. We theoretically motivate the approach by analyzing the linear setting; a population of LoRAs can achieve zero best-of- approximation error in settings where every single LoRA has strictly positive prediction error. Empirically, we demonstrate that stratified policies consistently improve pass@ 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 ↗