| title | StudyBench: Can Self-Evolution Squeeze Textbooks for Olympiad Capability? |
|---|---|
| authors | Yinghao Chen, Zixi Chen, Bingxiang He, Ziqing Qiao, Huan-ang Gao, Yinuo Xu, Yuxin Zuo, Zeyuan Liu, Yuhao Zhan, Chaojun Xiao |
| date | 2026-09-01 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2609.00787 |
| affiliation | Tsinghua NLP Group |
| upvotes | 14 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf code |
| abstract | Humans need to study only a handful of well-written textbooks to master a discipline and attempt its hardest problems. We argue that an ideal self-evolution method should share the same property, that is autonomously learning from raw training material for transferable problem-solving capability. However, we still lack a direct measurement for it. We introduce StudyBench, a controlled physics benchmark that directly measures how efficiently a self-evolution method converts training material into capability. We organise the test set into an Application Set, consisting of difficult textbook problems and evaluating absorption ability, and a Transfer Set, consisting of olympiad-level problems and evaluating transfer ability. Benchmarking representative self-evolution methods across three base models, we find that improvements on the Application Set rarely translate to the harder Transfer Set. A guidance ablation exposes a Guidance Gap: even the strongest method closes only a small fraction of what the same material unlocks when supplied as in-context guidance. Besides, every method hits a Compute Plateau, saturating well before exhausting its compute budget. The remaining gap is therefore a method problem rather than a data or compute problem. By offering a clean and controlled benchmark, StudyBench turns self-evolution progress from an open-ended pursuit into a measurable target for future research. Our code is released at https://github.com/thunlp/StudyBench. |
cite
@misc{chen2026studybench,
title={StudyBench: Can Self-Evolution Squeeze Textbooks for Olympiad Capability?},
author={Yinghao Chen and Zixi Chen and Bingxiang He and Ziqing Qiao and Huan-ang Gao and Yinuo Xu and Yuxin Zuo and Zeyuan Liu and Yuhao Zhan and Chaojun Xiao},
year={2026},
eprint={2609.00787},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2609.00787}
}