让AI自己啃教科书再解题
我们总以为大模型的「学习」就是喂给它一段资料再提问。这篇反过来：把参考书整本丢给它，答案不给，让它自己翻书、找原理、再写证明。研究者做了一个「教科书数学解题」任务，配一个叫 BookNavigator 的界面，让模型像人一样在书里来回翻，并用强化学习奖励它「翻得对、用得上」——奖励细到每一步，而不是只看最后答案对不对。结果在一个 35B 模型上，证明正确率从 51.5% 提到 79.5%，换到没见过的教材和学科也涨，还超过「不给书」和「固定检索几段」两种训练方式。连 BrowseComp-Plus 和 CL-bench 这类长上下文任务也各涨了 1.7 和 2.3 个百分点。它不是你明天能用上的东西，但指向一件事：模型可以学会「遇到不会的领域，自己去查、自己学」这套通用动作，而不是每次都等人把材料递到嘴边。
📄 原文摘要(英文)
Large language models (LLMs) draw on parametric knowledge and retrieval-augmented generation (RAG) to solve knowledge-intensive tasks. Yet problem solving in unfamiliar domains calls for tightly coupled knowledge acquisition and reasoning, beyond factual retrieval and aggregation or learning solely from a preassembled context. We study self-learning -- autonomously retrieving, studying, and applying knowledge from long-form reference materials on the fly. To investigate this capability, we formulate a textbook-based mathematical problem-solving task. LLMs must navigate textbook exposition, learn and apply relevant principles, and construct proofs for exercises, with reference solutions withheld. We introduce a BookNavigator interface to support this human-inspired study process and incentivize self-learning through reinforcement learning (RL) with fine-grained rewards. Experiments show that our method improves performance across in-domain and out-of-domain textbooks and subjects, raising Intern-S2-Preview-35B's overall proof accuracy from 51.5% to 79.5% and outperforming RL-trained textbook-free and fixed-retrieval baselines. These gains extend to complex long-context benchmarks involving different task types, with improvements over the base model of 1.7 and 2.3 percentage points on BrowseComp-Plus and CL-bench, respectively. Together, these findings suggest that RL can foster a domain-agnostic self-learning strategy, highlighting the potential of self-learning from long-form corpora to strengthen broader problem-solving capabilities on complex, long-context tasks.