ISM：面向持续数学推理的自我改进策略记忆
ISM:Self-Improving Strategy Memory for Continual Mathematical Reasoning
AI总结：
提出智能模式记忆（ISM），一种自我演进的记忆增强系统，通过从成功和失败案例中学习并维护策略模式库，在不更新模型参数的情况下提升冻结LLM在持续学习中的数学推理能力。
摘要：
我们提出智能模式记忆（ISM），一种自我演进的记忆增强系统，在具有硬性情节重置的持续学习下，提升冻结LLM的数学推理能力。ISM维护一个紧凑、自我精炼的策略模式库，这些模式从成功和失败的情节中学习，并配备符号工具来检查中间步骤并验证最终答案。在不更新模型参数的情况下，ISM在MATH-Hard和OlympiadBench上优于被动、检索和反思基线，分别比最强的被动基线少使用64%和86%的模式。这些结果表明，在严格的情节隔离下，小型、主动维护且经过验证的策略记忆可以支持可靠的持续数学推理。
英文摘要：
We propose Intelligent Schema Memory (ISM), a self-evolving memory-augmented system that improves mathematical reasoning for a frozen LLM under continual learning with hard episodic resets. ISM maintains a compact, self-refined bank of strategy schemas learned from both successful and failed episodes, with symbolic tools that check intermediate steps and certify answers. Without updating model parameters, ISM outperforms passive, retrieval, and reflection baselines on MATH-Hard and OlympiadBench, using 64% and 86% fewer schemas respectively than the strongest passive baseline. These results show that small, actively maintained, and verified strategy memories can support reliable continual mathematical reasoning under strict episodic isolation. The codebase is available at https://github.com/pdx97/ISM .
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
