PETS: A Principled Framework Towards Optimal Trajectory Allocation for Efficient Test-Time Self-Consistency

2026-02-18 · Zhangyi Liu, Huaizhi Qu, Xiaowei Yin, He Sun, Yanjun Han, Tianlong Chen, Zhun Deng arxiv

Test-time scaling can improve model performance by aggregating stochastic reasoning trajectories. However, achieving sample-efficient test-time self-consistency under a limited budget remains an open challenge. We introduce PETS (Principled and Efficient Test-TimeSelf-Consistency), which initiates a principled study of trajectory allocation through an optimization framework. Central to our approach is the self-consistency rate, a new measure defined as agreement with the infinite-budget majority vote. This formulation makes sample-efficient test-time allocation theoretically grounded and amenable to rigorous analysis. We study both offline and online settings. In the offline regime, where all questions are known in advance, we connect trajectory allocation to crowdsourcing, a classic and well-developed area, by modeling reasoning traces as workers. This perspective allows us to leverage rich existing theory, yielding theoretical guarantees and an efficient majority-voting-based allocation algorithm. In the online streaming regime, where questions arrive sequentially and allocations must be made on the fly, we propose a novel method inspired by the offline framework. Our approach adapts budgets to question difficulty while preserving strong theoretical guarantees and computational efficiency. Experiments show that PETS consistently outperforms uniform allocation. On GPQA, PETS achieves perfect self-consistency in both settings while reducing the sampling budget by up to 75% (offline) and 55% (online) relative to uniform allocation. Code is available at https://github.com/ZDCSlab/PETS.

📄 PDF Abstract BibTeX arXiv:2602.16745

Code (0)

등록된 구현이 없습니다.

Tasks

Computational Efficiency

Integrated Multi-Drone Task Allocation, Sequencing, and Optimal Trajectory Generation in Obstacle-Rich 3D Environments

2026-03-26 · Yunes Alqudsi, Murat Makaraci arxiv

Coordinating teams of aerial robots in cluttered three-dimensional (3D) environments requires a principled integration of discrete mission planning-deciding which robot serves which goals and in what order -- with contin…

Collision Avoidance

Practical Probabilistic Model-based Deep Reinforcement Learning by Integrating Dropout Uncertainty and Trajectory Sampling

2023-09-20 · Wenjun Huang, Yunduan Cui, Huiyun Li, Xinyu Wu

This paper addresses the prediction stability, prediction accuracy and control capability of the current probabilistic model-based reinforcement learning (MBRL) built on neural networks. A novel approach dropout-based pr…

Deep Reinforcement Learning Model-based Reinforcement Learning MuJoCo Prediction

Variational Inference MPC for Bayesian Model-based Reinforcement Learning

2019-07-08 · Masashi Okada, Tadahiro Taniguchi

In recent studies on model-based reinforcement learning (MBRL), incorporating uncertainty in forward dynamics is a state-of-the-art strategy to enhance learning performance, making MBRLs competitive to cutting-edge model…

Bayesian Inference Model-based Reinforcement Learning Model Predictive Control reinforcement-learning+4

DR-PETS: Learning-Based Control With Planning in Adversarial Environments

2025-03-26 · Hozefa Jesawada, Antonio Acernese, Giovanni Russo, Carmen Del Vecchio

Ensuring robustness against epistemic, possibly adversarial, perturbations is essential for reliable real-world decision-making. While the Probabilistic Ensembles with Trajectory Sampling (PETS) algorithm inherently hand…

Decision Making

Beyond Accuracy: A Decision-Theoretic Framework for Allocation-Aware Healthcare AI

2026-01-06 · Rifa Ferzana arxiv

Artificial intelligence (AI) systems increasingly achieve expert-level predictive accuracy in healthcare, yet improvements in model performance often fail to produce corresponding gains in patient outcomes. We term this …