用拓扑地图引导小模型推理，解决卡顿问题
External Hippocampus: Topological Cognitive Maps for Guiding Large Language Model Reasoning
- 通过降维构建语义空间拓扑图，动态导航推理能量流
- 7B以下模型在500题上达81.2%准确率，提速超15倍
- 无需训练，可自动生长，适合资源受限场景
本文提出外部海马体框架，将语言模型推理视为语义空间中的信息能量流动。不同于传统权重优化，该框架通过降维投影构建拓扑认知地图，在测试时实现对能量流的精准导航与干预，且计算开销低，干预模式可预测。该方法有效缓解小模型多步推理中的认知死锁问题。在≤7B参数模型上实验显示：地图引导方法在500个难题上达到81.20%准确率（相对基线提升16.80%），推理时间减少≥15倍。关键发现表明，推理停滞表现为“认知漩涡”和低熵势阱，温度扰动可有效重启能量流动。框架无需额外训练，具备自主增长能力，为小模型推理提供高效可控的拓扑感知解决方案。
原文摘要 · Abstract (English)
This paper proposes the External Hippocampus framework, which models language model reasoning from a cognitive dynamics perspective as the flow of information energy in semantic space. Unlike traditional weight-space optimization methods, this framework constructs topological cognitive maps through dimensionality reduction projection, enabling precise navigation and intervention of energy flow at test time while avoiding substantial computational requirements and demonstrating predictable intervention patterns. The method effectively addresses the cognitive deadlock problem in multi-step reasoning for small models. Experiments on models <=7B parameters show: map-guided methods achieve 81.20% accuracy on 500 challenging problems (relative baseline +16.80%), reduce reasoning time by >= 15x, with key findings revealing that reasoning stagnation manifests as "Cognitive Vortex" and low-entropy potential wells, while temperature perturbations effectively restart energy flow. The framework requires no additional training, possesses autonomous growth capability, and provides an efficient and controllable topological-aware solution for small model reasoning.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。