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

arXiv: https://arxiv.org/abs/2502.03283 · HTML: https://mlsanity.com/paper/2502.03283/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning.
- Builds on 0 of its 52 references that are in the map.
- First posted on arXiv 5 Feb 2025.

## Placed in

- LLM reasoning / [Knowledge- and tool-augmented reasoning](https://mlsanity.com/lr/knowledge-and-tool-augmented-reasoning/)
- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Built on by (most cited first, 10 of 10)

- [Rewarding Graph Reasoning Process makes LLMs more Generalized Reasoners](https://mlsanity.com/paper/2503.00845/) (2025)
- [Spinning Straw into Gold: Relabeling LLM Agent Trajectories in Hindsight for Successful Demonstrations](https://mlsanity.com/paper/2607.04235/) (2026)
- [Multi-Sourced, Multi-Agent Evidence Retrieval for Fact-Checking](https://mlsanity.com/paper/2603.00267/) (2026)
- [Learning to Evolve: Bayesian-Guided Continual Knowledge Graph Embedding](https://mlsanity.com/paper/2508.02426/) (2025)
- [Exemplar-Guided Planing: Enhanced LLM Agent for KGQA](https://mlsanity.com/paper/2510.15283/) (2025)
- [RPO-RAG: Aligning Small LLMs with Relation-aware Preference Optimization for Knowledge Graph Question Answering](https://mlsanity.com/paper/2601.19225/) (2026)
- [Curiosity Driven Knowledge Retrieval for Mobile Agents](https://mlsanity.com/paper/2601.19306/) (2026)
- [Ontology-Guided Evidence Path Inference for Multi-hop Knowledge Graph Question Answering](https://mlsanity.com/paper/2606.28076/) (2026)
- [Compositional Chain-of-Relations for Faithful Knowledge Graph Question Answering with Large Language Models](https://mlsanity.com/paper/2608.22762/) (2026)
- [NeuroGraph: An AI Graph-Driven Neuro-Symbolic Framework for Explainable Threat Reasoning in Advanced Manufacturing](https://mlsanity.com/paper/2609.00604/) (2026)

## Abstract (arXiv)

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.