investigation
The models trained on the easier examples are tested on problems harder than those they saw in post-training and still succeed much more than models trained directly on the test difficulty level, without receiving full solutions or feedback on intermediate steps.
A investigation by המחברים. Statements are as reported by the cited publishers — not verified by DecisionGateway.
המודלים שהתאמנו על הדוגמאות הקלות נבחנים על בעיות קשות יותר מאלו שראו באימון המשך ועדיין מצליחים הרבה יותר מהמודלים שהתאמנו ישירות על רמת הקושי של המבחן.
Discussion
Related claims
When the authors train the models only on problems at the test difficulty level, the models reach about 50% accuracy, almost like random guessing.המחברים · investigationThe researchers confirm their claims in experiments: they post-train models such as Qwen and Llama on a task of solving systems of equations, where the final answer is 0 or 1 so about half the cases can be solved by guessing.החוקרים · investigationWhen the test-difficulty examples are replaced with a mixture of easier examples, Qwen jumps to 91.6% and Llama to 98.6%, while the test remains at exactly the same difficulty level.המחברים · investigationThe researchers prove that in their synthetic framework, the training data must include enough simple examples (requiring few reasoning steps); with enough such examples the model learns to solve problems step by step, and without them it does not learn.החוקרים · investigationThe researchers show that training leads the model to learn an efficient solution path, even though it receives no extra reward for choosing that path.החוקרים · investigationThe paper proves that when training reasoning models with RL, it is not always true that training data should match the test-time distribution; sometimes data different from what the model will see at test time yields much better test-time results.המאמר · investigation