Cover Image

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

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Golowich, Noah, Chen, Fan, Rohatgi, Dhruv, Singhal, Raghav, Domingo-Enrich, Carles, Foster, Dylan J., Krishnamurthy, Akshay
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence Computation and Language Statistics Theory
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Is a Good Foundation Necessary for Efficient Reinforcement Learning? The Computational Role of the Base Model in Exploration
by: Foster, Dylan J., et al.
Published: (2025)

The Coverage Principle: How Pre-Training Enables Post-Training
by: Chen, Fan, et al.
Published: (2025)

Compress Then Test: Powerful Kernel Testing in Near-linear Time
by: Domingo-Enrich, Carles, et al.
Published: (2023)

Cheap Permutation Testing
by: Domingo-Enrich, Carles, et al.
Published: (2025)

Self-Improvement in Language Models: The Sharpening Mechanism
by: Huang, Audrey, et al.
Published: (2024)

Exploration is Harder than Prediction: Cryptographically Separating Reinforcement Learning from Supervised Learning
by: Golowich, Noah, et al.
Published: (2024)

On Learning Parities with Dependent Noise
by: Golowich, Noah, et al.
Published: (2024)

Near-Optimal Learning and Planning in Separated Latent MDPs
by: Chen, Fan, et al.
Published: (2024)

Resampling-free Inference for Time Series via RKHS Embedding
by: Ghoshal, Deep, et al.
Published: (2026)

Lasso with Latents: Efficient Estimation, Covariate Rescaling, and Computational-Statistical Gaps
by: Kelner, Jonathan, et al.
Published: (2024)

Computational-Statistical Tradeoffs at the Next-Token Prediction Barrier: Autoregressive and Imitation Learning under Misspecification
by: Rohatgi, Dhruv, et al.
Published: (2025)

Is Behavior Cloning All You Need? Understanding Horizon in Imitation Learning
by: Foster, Dylan J., et al.
Published: (2024)

First-Extinction Law for Resampling Processes
by: Benati, Matteo, et al.
Published: (2025)

Frequency Domain Resampling for Gridded Spatial Data
by: Bera, Souvick, et al.
Published: (2025)

Necessary and Sufficient Oracles: Toward a Computational Taxonomy For Reinforcement Learning
by: Rohatgi, Dhruv, et al.
Published: (2025)

Conditional Delta-Method for Resampling Empirical Processes in Multiple Sample Problems
by: Munko, Merle, et al.
Published: (2024)

Ensemble Kalman Filters with Resampling
by: Ghattas, Omar Al, et al.
Published: (2023)

Assouad, Fano, and Le Cam with Interaction: A Unifying Lower Bound Framework and Characterization for Bandit Learnability
by: Chen, Fan, et al.
Published: (2024)

Jump Markov Chains and Rejection-Free Metropolis Algorithms
by: Rosenthal, J. S., et al.
Published: (2019)

A Taxonomy of Loss Functions for Stochastic Optimal Control
by: Domingo-Enrich, Carles
Published: (2024)

Online Estimation via Offline Estimation: An Information-Theoretic Framework
by: Foster, Dylan J., et al.
Published: (2024)

Identification and Inference with Invalid Instruments
by: Kang, Hyunseung, et al.
Published: (2024)

Laws of thermodynamics for exponential families
by: Balsubramani, Akshay
Published: (2025)

Deep Regression for Repeated Measurements
by: Yan, Shunxing, et al.
Published: (2023)

Causal Sufficiency and Necessity Improves Chain-of-Thought Reasoning
by: Yu, Xiangning, et al.
Published: (2025)

Stability of a Generalized Debiased Lasso with Applications to Resampling-Based Variable Selection
by: Liu, Jingbo
Published: (2024)

Reasoning with Sampling: Cutting at Decision Points
by: Zhou, Felix, et al.
Published: (2026)

Stability of Sequential and Parallel Coordinate Ascent Variational Inference
by: Pati, Debdeep
Published: (2026)

Information theoretic limits of robust sub-Gaussian mean estimation under star-shaped constraints
by: Prasadan, Akshay, et al.
Published: (2024)

Characterizing the minimax rate of nonparametric regression under bounded star-shaped constraints
by: Prasadan, Akshay, et al.
Published: (2024)

Some facts about the optimality of the LSE in the Gaussian sequence model with convex constraint
by: Prasadan, Akshay, et al.
Published: (2024)

Resampling-based multi-resolution false discovery exceedance control
by: Hemerik, Jesse
Published: (2025)

Statistical Analysis of Data Repeatability Measures
by: Wang, Zeyi, et al.
Published: (2020)

No Compute Left Behind: Rethinking Reasoning and Sampling with Masked Diffusion Models
by: Horvitz, Zachary, et al.
Published: (2025)

Universal Rank Inference via Residual Subsampling with Application to Large Networks
by: Han, Xiao, et al.
Published: (2019)

Growth-Optimal E-Variables and an extension to the multivariate Csiszár-Sanov-Chernoff Theorem
by: Grünwald, Peter, et al.
Published: (2024)

A Simplified and Numerically Stable Approach to the BG/NBD Churn Prediction model
by: Zammit, Dylan, et al.
Published: (2025)

Robust Detection of Watermarks for Large Language Models Under Human Edits
by: Li, Xiang, et al.
Published: (2024)

Sequences of Logits Reveal the Low Rank Structure of Language Models
by: Golowich, Noah, et al.
Published: (2025)

$K$-Nearest-Neighbor Resampling for Off-Policy Evaluation in Stochastic Control
by: Giegrich, Michael, et al.
Published: (2023)