SE-Bench：基于知识内化的自我进化基准测试框架

SE-Bench: Benchmarking Self-Evolution with Knowledge Internalization

February 4, 2026

作者: Jiarui Yuan, Tailin Jin, Weize Chen, Zeyuan Liu, Zhiyuan Liu, Maosong Sun

cs.AI

摘要

真正的自我进化要求智能体作为终身学习者，通过内化新经验来解决未来问题。然而，这一基础能力的严谨评估面临两大障碍：先验知识的纠缠性（即"新"知识可能已存在于预训练数据中）与推理复杂性的纠缠性（即失败可能源于问题难度而非知识回忆能力）。我们推出SE-Bench诊断环境，通过将NumPy库及其API文档混淆为随机命名的伪新包，构建出纯净测试场景：智能体需内化该包后在不查阅文档的情况下完成基础编码任务——这些任务在使用新API文档时极为简单，但基础模型若无此知识则无法解决。研究发现三大关键洞见：（1）开卷训练悖论：使用参考文档的训练会抑制知识留存，必须采用"闭卷训练"强制知识压缩至权重；（2）强化学习鸿沟：标准RL因PPO裁剪和负梯度问题难以完整内化新知识；（3）自我博弈的可行性：模型能通过SFT从自生成的噪声任务中学习知识，但RL方法无效。SE-Bench为知识内化的自我进化研究建立了严谨诊断平台，代码与数据集详见https://github.com/thunlp/SE-Bench。

English

True self-evolution requires agents to act as lifelong learners that internalize novel experiences to solve future problems. However, rigorously measuring this foundational capability is hindered by two obstacles: the entanglement of prior knowledge, where ``new'' knowledge may appear in pre-training data, and the entanglement of reasoning complexity, where failures may stem from problem difficulty rather than an inability to recall learned knowledge. We introduce SE-Bench, a diagnostic environment that obfuscates the NumPy library and its API doc into a pseudo-novel package with randomized identifiers. Agents are trained to internalize this package and evaluated on simple coding tasks without access to documentation, yielding a clean setting where tasks are trivial with the new API doc but impossible for base models without it. Our investigation reveals three insights: (1) the Open-Book Paradox, where training with reference documentation inhibits retention, requiring "Closed-Book Training" to force knowledge compression into weights; (2) the RL Gap, where standard RL fails to internalize new knowledge completely due to PPO clipping and negative gradients; and (3) the viability of Self-Play for internalization, proving models can learn from self-generated, noisy tasks when coupled with SFT, but not RL. Overall, SE-Bench establishes a rigorous diagnostic platform for self-evolution with knowledge internalization. Our code and dataset can be found at https://github.com/thunlp/SE-Bench.