图上的认知：通过认知循环与双向图-文本协同导航大规模知识空间
Cognition on Graph: Navigating Massive Knowledge Space via Cognitive Cycles and Bidirectional Graph-Text Synergy
- Beijing University of Posts and Telecommunications（北京邮电大学）
- Zhongguancun Academy（中关村学院）
- MAIS, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所多模态人工智能系统全国重点实验室）
- School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
提出CoG框架，受认知启发，通过规划-探索-反思循环和双向图-文本协同，在七个多跳问答基准上超越现有方法，实现高效自适应知识探索。
AI中文摘要：
检索增强生成（RAG）已使大型语言模型（LLMs）能够处理知识密集型任务。然而，在全局、异构的知识库（大规模知识图谱和文本语料库）中进行导航以完成复杂推理仍然是一个挑战。现有方法通常采用反应式、图驱动的探索策略，这些策略盲目地遵循图拓扑结构，而不适应问题上下文或不断演进的探索进度，并且缺乏图与文本之间的深度双向协同。为解决这些局限性，我们提出了CoG（图上的认知），一种受认知启发、无需训练的自适应知识探索框架。受人类问题解决过程的启发，CoG执行一个连续的规划-探索-反思循环，在此过程中，它主动制定调查计划，进行双源检索，并动态反思进度以调整策略。至关重要的是，它在结构化图与非结构化文本之间建立了深度双向协同，其中从文本中提取的实体动态地引导图探索以弥合知识差距。在七个多跳问答基准上的广泛实验表明，CoG显著优于最先进的方法，同时实现了更高的探索效率。我们的代码和数据集可在以下https URL获取。
英文摘要：
Retrieval-Augmented Generation (RAG) has empowered Large Language Models (LLMs) to tackle knowledge-intensive tasks. However, navigating global, heterogeneous knowledge bases (large-scale knowledge graphs and text corpora) for complex reasoning remains a challenge. Existing methods typically employ reactive, graph-driven exploration strategies, which blindly follow graph topology without adapting to the question context or evolving exploration progress, and lack deep bidirectional synergy between graph and text. To address these limitations, we propose CoG (Cognition on Graph), a cognitive-inspired, training-free framework for adaptive knowledge exploration. Drawing inspiration from human problem-solving, CoG performs a continuous plan-explore-reflect cycle, where it proactively formulates investigation plans, performs dual-source retrieval, and dynamically reflects on progress to adjust strategies. Crucially, it establishes deep bidirectional synergy between structured graph and unstructured text, where entities extracted from text dynamically guide graph exploration to bridge knowledge gaps. Extensive experiments on seven multi-hop QA benchmarks demonstrate that CoG significantly outperforms state-of-the-art methods while achieving superior exploration efficiency. Our code and datasets are available at https://github.com/zhougengxian/CoG.
