Optimal Aggregation of LLM and PRM Signals for Efficient Test-Time Scaling

• URL: http://arxiv.org/abs/2510.13918v1
• Date: Wed, 15 Oct 2025 09:08:51 GMT
• Title: Optimal Aggregation of LLM and PRM Signals for Efficient Test-Time Scaling
• Authors: Peng Kuang, Yanli Wang, Xiaoyu Han, Yaowenqi Liu, Kaidi Xu, Haohan Wang,
• Abstract summary: Process reward models (PRMs) are a cornerstone of test-time scaling (TTS)<n>PRMs are designed to verify and select the best responses from large language models (LLMs)
• Score: 34.20750590384272
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Process reward models (PRMs) are a cornerstone of test-time scaling (TTS), designed to verify and select the best responses from large language models (LLMs). However, this promise is challenged by recent benchmarks where simple majority voting, which ignores PRM signals, occasionally outperforms standard PRM-based selection. This raises a critical question: How can we effectively utilize verification signals from PRMs for TTS? To address this, we start by developing a theoretical framework for optimally combining signals from both the LLM and the PRM. Our framework reveals that the optimal strategy is a weighted aggregation of responses, a strategy whose effectiveness hinges on estimating weights that capture the complex interplay between the models. Based on our theoretical results, we empirically show that these optimal weighting functions differ significantly across LLM-PRM pairs and, notably, often assign substantial negative weights. Motivated by these insights, we propose efficient pre-computation methods to calibrate these weighting functions. Extensive experiments across 5 LLMs and 7 PRMs demonstrate that our calibration method significantly boosts the TTS efficiency, surpassing the performance of vanilla weighted majority voting while using only $21.3\%$ of the computation. Ultimately, our work demonstrates that investing in a more intelligent aggregation strategy can be a more convincing path to performance gains than simply scaling test-time computation.

Related papers

• APLOT: Robust Reward Modeling via Adaptive Preference Learning with Optimal Transport [37.21695864040979]
  The reward model (RM) plays a crucial role in aligning Large Language Models (LLMs) with human preferences through Reinforcement Learning.<n>This paper introduces an effective enhancement to BT-based RMs through an adaptive margin mechanism.
  arXiv  Detail & Related papers  (2025-10-13T03:13:28Z)
• Your Reward Function for RL is Your Best PRM for Search: Unifying RL and Search-Based TTS [62.22644307952087]
  We introduce AIRL-S, the first natural unification of RL-based and search-based TTS.<n>We leverage adversarial inverse reinforcement learning (AIRL) combined with group relative policy optimization (GRPO) to learn a dense, dynamic PRM directly from correct reasoning traces.<n>Our results show that our unified approach improves performance by 9 % on average over the base model, matching GPT-4o.
  arXiv  Detail & Related papers  (2025-08-19T23:41:15Z)
• Good Learners Think Their Thinking: Generative PRM Makes Large Reasoning Model More Efficient Math Learner [31.033131727230277]
  Large reasoning models (LRMs) have recently shown promise in solving complex math problems when optimized with Reinforcement Learning (RL)<n>We propose a novel intrinsic signal-driven generative process evaluation mechanism operating at the thought level to address major bottlenecks in RL-based training.<n>Experiments on 1.5B and 7B parameter LRMs demonstrate that our method achieves higher problem-solving accuracy with significantly fewer training samples than outcome-only reward baselines.
  arXiv  Detail & Related papers  (2025-07-31T07:54:58Z)
• Reward Model Generalization for Compute-Aware Test-Time Reasoning [21.05692631562457]
  External test-time reasoning enhances large language models (LLMs) by decoupling generation and selection.<n>A central challenge in this setting is test-time compute optimality (TCO), i.e., how to maximize answer accuracy under a fixed inference budget.<n>We analyze how the generalization error of the PRM affects compute efficiency and reasoning performance.<n>Motivated by this analysis, we propose Compute-Aware Tree Search (CATS), an actor-critic framework that dynamically controls search behavior.
  arXiv  Detail & Related papers  (2025-05-23T16:12:12Z)
• Trajectory Bellman Residual Minimization: A Simple Value-Based Method for LLM Reasoning [55.33984461046492]
  Policy-based methods currently dominate reinforcement learning pipelines for large language model (LLM) reasoning.<n>We introduce Trajectory Bellman Residual Minimization (TBRM), an algorithm that naturally adapts this idea to LLMs.<n>We prove convergence to the near-optimal KL-regularized policy from arbitrary off-policy via an improved change-of-trajectory-measure analysis.
  arXiv  Detail & Related papers  (2025-05-21T09:41:53Z)
• Process Reward Models That Think [85.06022494911811]
  Step-by-step verifiers -- also known as process reward models (PRMs) -- are a key ingredient for test-time scaling.<n>This work aims to build data-efficient PRMs as verbalized step-wise reward models that verify every step in the solution by generating a verification chain-of-thought (CoT)<n>We propose ThinkPRM, a long CoT verifier fine-tuned on orders of magnitude fewer process labels than those required by discriminative PRMs.
  arXiv  Detail & Related papers  (2025-04-23T15:44:54Z)
• Do We Truly Need So Many Samples? Multi-LLM Repeated Sampling Efficiently Scales Test-Time Compute [54.22256089592864]
  This paper presents a simple, effective, and cost-efficient strategy to improve LLM performance by scaling test-time compute.<n>Our strategy builds upon the repeated-sampling-then-voting framework, with a novel twist: incorporating multiple models, even weaker ones, to leverage their complementary strengths.
  arXiv  Detail & Related papers  (2025-04-01T13:13:43Z)
• VinePPO: Refining Credit Assignment in RL Training of LLMs [66.80143024475635]
  We propose VinePPO, a straightforward approach that leverages the flexibility of language environments to compute unbiased Monte Carlo-based estimates.<n>Our method consistently outperforms PPO and other baselines across MATH and GSM8K datasets in less wall-clock time.
  arXiv  Detail & Related papers  (2024-10-02T15:49:30Z)
• WARM: On the Benefits of Weight Averaged Reward Models [63.08179139233774]
  We propose Weight Averaged Reward Models (WARM) to mitigate reward hacking. Experiments on summarization tasks, using best-of-N and RL methods, shows that WARM improves the overall quality and alignment of LLM predictions.
  arXiv  Detail & Related papers  (2024-01-22T18:27:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.