Learning on the Job: Test-Time Curricula for Targeted Reinforcement Learning
This addresses the need for efficient, automated learning during test-time without human curation, though it is incremental as it builds on existing reinforcement learning and curriculum methods.
The paper tackles the problem of enabling models to learn on the job by proposing a test-time curriculum for targeted reinforcement learning, which automatically selects task-relevant data to improve performance on target tasks, resulting in pass@1 improvements of approximately 1.8x on AIME25 and 2.1x on CodeElo for Qwen3-8B.
Humans are good at learning on the job: We learn how to solve the tasks we face as we go along. Can a model do the same? We propose an agent that assembles a task-specific curriculum, called test-time curriculum (TTC-RL), and applies reinforcement learning to continue training the model for its target task. The test-time curriculum avoids time-consuming human curation of datasets by automatically selecting the most task-relevant data from a large pool of available training data. Our experiments demonstrate that reinforcement learning on a test-time curriculum consistently improves the model on its target tasks, across a variety of evaluations and models. Notably, on challenging math and coding benchmarks, TTC-RL improves the pass@1 of Qwen3-8B by approximately 1.8x on AIME25 and 2.1x on CodeElo. Moreover, we find that TTC-RL significantly raises the performance ceiling compared to the initial model, increasing pass@8 on AIME25 from 40% to 62% and on CodeElo from 28% to 43%. Our findings show the potential of test-time curricula in extending the test-time scaling paradigm to continual training on thousands of task-relevant experiences during test-time.