cs.LGNov 17, 2026

Learning Stratified Policies for Inference-Time Objectives

Authors: Mridul Mahajan, Xuezhou Zhang, Aldo Pacchiano

Organizations: Boston University · Broad Institute of MIT and Harvard

Abstract

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.

Figures & tables

Appendix figures & tables8 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Mar 9, 2026

Reject, Resample, Repeat: Understanding Parallel Reasoning in Language Model Inference

Inference-time methods that aggregate and prune multiple samples have emerged as a powerful paradigm for steering large language models, yet we lack any principled understanding of their accuracy-cost tradeoffs. In this paper, we introduce a route to rigorously study such approaches using the lens of particle filtering algorithms such as Sequential Monte Carlo (SMC). Given a base language model and a process reward model estimating expected terminal rewards, we ask: how accurately can we sample from a target distribution given some number of process reward evaluations? Theoretically, we identify (1) simple criteria enabling non-asymptotic guarantees for SMC; (2) algorithmic improvements to SMC; and (3) a fundamental limit faced by all particle filtering methods. Empirically, we demonstrate that our theoretical criteria effectively govern the sampling error of SMC, though not necessarily its final accuracy, suggesting that theoretical perspectives beyond sampling may be necessary.
Aug 15, 2026

Funnel of Thoughts: Efficient Test-Time Scaling via Early Voting and Rollout Pruning

Large Reasoning Models produce diverse, sometimes inconsistent answers across repeated queries on the same problem, so multi-sample inference is a prerequisite for reliable deployment. Majority voting at k rollouts is the standard solution and the de facto accuracy target for this regime, but it is prohibitively expensive at the scale LRMs require. We introduce Funnel of Thoughts (FoT), an inference-time method that preserves the full 32-trajectory voted accuracy while halving its attention FLOPs, a 28.8% reduction in full-model inference cost. Across 115K reasoning trajectories from six LRMs, we find that unproductive trajectories often reveal themselves through repeated hesitation markers such as "Wait", "Actually", and "perhaps." These trajectories are less likely to reach the correct answer and consume disproportionate attention FLOPs, degenerating into no-answer loops in the worst case. Built on this training-free lexical signal, FoT identifies the vocabulary that captures these pathological patterns and prunes affected trajectories before completion, reducing online generation attention FLOPs by 56.1% and wall time by 37.6% without any additional model inference; the same signal transfers without retuning across held-out architectures and out-of-domain tasks.
Mar 5, 2026

∇\nabla-Reasoner: LLM Reasoning via Test-Time Gradient Descent in Latent Space

Scaling inference-time compute for Large Language Models (LLMs) has unlocked unprecedented reasoning capabilities. However, existing inference-time scaling methods typically rely on inefficient and suboptimal discrete search algorithms or trial-and-error prompting to improve the online policy. In this paper, we propose ∇\nabla-Reasoner, an iterative generation framework that integrates differentiable optimization over token logits into the decoding loop to refine the policy on the fly. Our core component, Differentiable Textual Optimization (DTO), leverages gradient signals from both the LLM's likelihood and a reward model to refine textual representations. ∇\nabla-Reasoner further incorporates rejection sampling and acceleration design to robustify and speed up decoding. Theoretically, we show that performing inference-time gradient descent in the sample space to maximize reward is dual to aligning an LLM policy via KL-regularized reinforcement learning. Empirically, ∇\nabla-Reasoner achieves over 20% accuracy improvement on a challenging mathematical reasoning benchmark, while reducing number of model calls by approximately 10-40% compared to strong baselines. Overall, our work introduces a paradigm shift from zeroth-order search to first-order optimization at test time, offering a cost-effective path to amplify LLM reasoning.