Problem
Research questions and friction points this paper is trying to address.
Knowledge Exploration
Graph-Text Synergy
Complex Reasoning
Heterogeneous Knowledge Bases
Cognition on Graph: Navigating Massive Knowledge Space via Cognitive Cycles and Bidirectional Graph-Text Synergy
🤖 AI Summary
为解决复杂推理中导航大规模异构知识库的挑战，提出CoG框架，通过认知循环和图文双向协同方法，实现自适应知识探索。
📝 Abstract
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.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Cognition on Graph
adaptive knowledge exploration
bidirectional graph-text synergy
plan-explore-reflect cycle
🔎 Similar Papers
No similar papers found.
