Test-Time Reinforcement Learning for LLMs

This June 2025 paper introduces a novel methodology called **Test-Time Reinforcement Learning (TTRL)**, which enables Large Language Models (LLMs) to improve their performance on reasoning tasks using unlabeled test data. The core innovation addresses the challenge of reward estimation without ground-truth labels by employing **Test-Time Scaling (TTS)** practices, specifically **majority voting**, to generate effective pseudo-labels and rule-based rewards. TTRL facilitates the **self-evolution of LLMs** during inference, demonstrating substantial performance gains—up to a 211% boost on challenging mathematical benchmarks like AIME 2024—and even surpassing the performance ceiling of the initial majority voting signal. This unsupervised **online learning** approach is shown to be compatible with different reinforcement learning algorithms and effective across various models, suggesting a path toward continually learning AI systems less reliant on extensive human annotation.Source:https://arxiv.org/pdf/2504.16084

There are no comments yet.

Please log in to write the first comment.