External Hippocampus: Topological Cognitive Maps for Guiding Large Language Model Reasoning

2025/12/20 by Jian Yan, Yan, Jian
Computer Science · Engineering · #Artificial Intelligence (cs.AI) #Cognitive Computing and Networks #Cognitive Science and Mapping #Computation and Language (cs.CL) #FOS: Computer and information sciences #Ferroelectric and Negative Capacitance Devices #I.2.7 #Machine Learning (cs.LG)

paper · doi:10.48550/arxiv.2512.18190

openalex publication_date 2025/12/20 · openalex created_date 2025/12/24 · openalex updated_date 2026/07/28

Abstract

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.

Citations

• Qwen2.5 Technical Report
• Demystifying Chains, Trees, and Graphs of Thoughts
• Let's Verify Step by Step
• Tree of Thoughts: Deliberate Problem Solving with Large Language Models
• Visual Instruction Tuning
• Self-Refine: Iterative Refinement with Self-Feedback
• Sparks of Artificial General Intelligence: Early experiments with GPT-4
• Reflexion: Language Agents with Verbal Reinforcement Learning
• LLaMA: Open and Efficient Foundation Language Models
• Large Language Models are Better Reasoners with Self-Verification
• Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks
• PAL: Program-aided Language Models
• Distributing Accountability, Not Capability: Phase Separation and the LLM Workflow Quadrant in Autonomous AI Agent Architectures
• Large Language Models are Zero-Shot Reasoners
• Least-to-Most Prompting Enables Complex Reasoning in Large Language Models
• Self-Consistency Improves Chain of Thought Reasoning in Language Models
• BNAI, NO-TOKEN, and MIND-UNITY: Pillars of a Systemic Revolution in Artificial Intelligence
• Evaluating Large Language Models Trained on Code
• SimCSE: Simple Contrastive Learning of Sentence Embeddings
• Learning Transferable Visual Models From Natural Language Supervision
• Measuring Massive Multitask Language Understanding
• Dense Passage Retrieval for Open-Domain Question Answering
• Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
• Attention Is All You Need

Related

• Cognitive Load-Aware Inference: A Neuro-Symbolic Framework for Optimizing the Token Economy of Large Language Models
• From Chaos to Order: The Atomic Reasoner Framework for Fine-grained Reasoning in Large Language Models
• Generating Computational Cognitive Models using Large Language Models
• Cognitive Foundations for Reasoning and Their Manifestation in LLMs
• Cognitive Load Traces as Symbolic and Visual Accounts of Deep Model Cognition