eMoT 解决了大模型在多步推理中容易出错和产生幻觉的痛点，做推理增强或数学推理的开发者可以直接参考其记忆腐蚀和符号锚定机制，值得一试。
eMoT 提出了一种名为“演化思维记忆”的新框架，将推理轨迹视为动态演化的记忆而非静态模板，以解决大模型在多步推理中的幻觉和数值计算问题。该框架包含三个核心模块：记忆腐蚀机制（强化高效用推理结构并衰减低频结构）、符号锚定引擎（利用 Python 进行确定性计算，类似人类使用计算器）以及一致性驱动精炼过程（对齐神经推理与符号结果，减少逻辑偏差）。在 Game of 24 任务上，eMoT 达到 100% 准确率，比基线提升 17.6%；在 GSM8K、ASDiv、SVAMP 和 MGSM 等数学推理基准上也有持续改进。即使使用轻量级模型，eMoT 也优于依赖大规模模型的方法，表明性能提升主要来自框架的推理控制而非模型规模。
eMoT: evolving Memory-of-Thought via Symbolic Anchoring and Memory Corrosion
While Large Language Models (LLMs) achieve impressive performance on multi-step reasoning tasks, their reliability is persistently hindered by critical limitations such as unconstrained hallucinations and poor numerical computation. Fundamentally, these issues arise because standard models treat reasoning as a transient, one-off generation process rather than retaining and refining successful procedural logic. To address these challenges, we propose eMoT (evolving Memory-of-Thought), a unified framework that stabilizes multi-step reasoning by treating reasoning trajectories as dynamic, evolving memories rather than static templates. The framework primarily consists of three interconnected modules: (i) a memory corrosion mechanism that reinforces high-utility reasoning structures while gradually decaying less frequent ones; (ii) a symbolic anchoring engine that utilizes Python for deterministic computation, much like a human uses a calculator; and (iii) a consistency-driven refinement process that aligns neural inference with symbolic outcomes, reducing the accumulation of logical discrepancies. Across multiple reasoning benchmarks, eMoT improves accuracy and solution consistency over standard Chain-of-Thought and structured reasoning baselines.On the traditional task Game of 24, eMoT achieves 100% accuracy, surpassing the baseline by up to 17.6%. Evaluations on mathematical task GSM8K, ASDiv, SVAMP, and MGSM further show consistent gains in multi-step mathematical reasoning. In our evaluation, we achieve superior performance despite utilizing a lightweight backbone model with constrained baseline capabilities. Compared to alternative methods that rely on massively scaled models, our results demonstrate that the performance gains are fundamentally driven by the eMoT framework's reasoning control rather than sheer model size.