SymAgent: A Neural-Symbolic Self-Learning Agent Framework for Complex Reasoning over Knowledge Graphs

2025-02-05

AI Summary

Large language models (LLMs) suffer from hallucination in complex reasoning, while existing knowledge graph (KG)-enhanced approaches are hindered by KG incompleteness and static modeling. Method: We propose a neuro-symbolic self-learning agent framework that treats the KG as a dynamic reasoning environment, integrating rule-guided question decomposition and multi-step interactive reasoning. Our framework features a synergistic self-learning mechanism combining online exploration with offline policy iteration, enabling automatic trajectory synthesis and identification of missing KG triples. Technically, it unifies a 7B-scale LLM, symbolic rule extraction, tool invocation, reinforcement learning–based policy updates, and KG embedding/querying. Contribution/Results: Experiments demonstrate that our method achieves performance on par with—or even surpassing—that of stronger baseline LLMs when deployed on weaker base models, while enabling autonomous KG evolution.

Technology Category

• Machine Learning: Neuro-Symbolic Learning
• Multiagent Systems: Multiagent Learning
• Search and Optimization: Learning to Search

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Recent advancements have highlighted that Large Language Models (LLMs) are prone to hallucinations when solving complex reasoning problems, leading to erroneous results. To tackle this issue, researchers incorporate Knowledge Graphs (KGs) to improve the reasoning ability of LLMs. However, existing methods face two limitations: 1) they typically assume that all answers to the questions are contained in KGs, neglecting the incompleteness issue of KGs, and 2) they treat the KG as a static repository and overlook the implicit logical reasoning structures inherent in KGs. In this paper, we introduce SymAgent, an innovative neural-symbolic agent framework that achieves collaborative augmentation between KGs and LLMs. We conceptualize KGs as dynamic environments and transform complex reasoning tasks into a multi-step interactive process, enabling KGs to participate deeply in the reasoning process. SymAgent consists of two modules: Agent-Planner and Agent-Executor. The Agent-Planner leverages LLM's inductive reasoning capability to extract symbolic rules from KGs, guiding efficient question decomposition. The Agent-Executor autonomously invokes predefined action tools to integrate information from KGs and external documents, addressing the issues of KG incompleteness. Furthermore, we design a self-learning framework comprising online exploration and offline iterative policy updating phases, enabling the agent to automatically synthesize reasoning trajectories and improve performance. Experimental results demonstrate that SymAgent with weak LLM backbones (i.e., 7B series) yields better or comparable performance compared to various strong baselines. Further analysis reveals that our agent can identify missing triples, facilitating automatic KG updates.

Problem

• Address hallucination in LLMs for complex reasoning
• Enhance reasoning by integrating dynamic Knowledge Graphs
• Develop self-learning agent for automatic KG updates

Innovation

• Neural-symbolic framework for KG-LLM collaboration
• Dynamic KG environment for multi-step reasoning
• Self-learning agent with online and offline phases