# Efficient and Transferable Agentic Knowledge Graph RAG via Reinforcement Learning

arXiv: https://arxiv.org/abs/2509.26383 · HTML: https://mlsanity.com/paper/2509.26383/

## Key facts

- Cited by 5 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 32 of its 55 references that are in the map.
- First posted on arXiv 30 Sep 2025.

## Placed in

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

## Builds on (most cited first, 30 of 32)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [HybridFlow: A Flexible and Efficient RLHF Framework](https://mlsanity.com/paper/2409.19256/) (2024)
- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning](https://mlsanity.com/paper/2503.09516/) (2025)
- [Understanding R1-Zero-Like Training: A Critical Perspective](https://mlsanity.com/paper/2503.20783/) (2025)
- [The Web as a Knowledge-base for Answering Complex Questions](https://mlsanity.com/paper/1803.06643/) (2018)
- [ToolRL: Reward is All Tool Learning Needs](https://mlsanity.com/paper/2504.13958/) (2025)
- [CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning](https://mlsanity.com/paper/2207.01780/) (2022)
- [Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning](https://mlsanity.com/paper/2310.01061/) (2023)
- [KG-BERT: BERT for Knowledge Graph Completion](https://mlsanity.com/paper/1909.03193/) (2019)
- [Beyond I.I.D.: Three Levels of Generalization for Question Answering on Knowledge Bases](https://mlsanity.com/paper/2011.07743/) (2020)
- [Large-scale Simple Question Answering with Memory Networks](https://mlsanity.com/paper/1506.02075/) (2015)
- [Chatlaw: A Multi-Agent Legal Assistant based on a Role-Aligned Mixture-of-Experts Architecture](https://mlsanity.com/paper/2306.16092/) (2023)
- [Gold-medalist Performance in Solving Olympiad Geometry with AlphaGeometry2](https://mlsanity.com/paper/2502.03544/) (2025)
- [MedRAG: Enhancing Retrieval-augmented Generation with Knowledge Graph-Elicited Reasoning for Healthcare Copilot](https://mlsanity.com/paper/2502.04413/) (2025)
- [Acting Less is Reasoning More! Teaching Model to Act Efficiently](https://mlsanity.com/paper/2504.14870/) (2025)
- [Plan-on-Graph: Self-Correcting Adaptive Planning of Large Language Model on Knowledge Graphs](https://mlsanity.com/paper/2410.23875/) (2024)
- [Knowledge Graph-Guided Retrieval Augmented Generation](https://mlsanity.com/paper/2502.06864/) (2025)
- [Knowledge Graph Retrieval-Augmented Generation for LLM-based Recommendation](https://mlsanity.com/paper/2501.02226/) (2025)
- [Temporal Knowledge Question Answering via Abstract Reasoning Induction](https://mlsanity.com/paper/2311.09149/) (2023)
- [Reasoning of Large Language Models over Knowledge Graphs with Super-Relations](https://mlsanity.com/paper/2503.22166/) (2025)
- [Grounding Dialogue Systems via Knowledge Graph Aware Decoding with Pre-trained Transformers](https://mlsanity.com/paper/2103.16289/) (2021)
- [Beyond Seen Data: Improving KBQA Generalization Through Schema-Guided Logical Form Generation](https://mlsanity.com/paper/2502.12737/) (2025)
- [GETT-QA: Graph Embedding based T2T Transformer for Knowledge Graph Question Answering](https://mlsanity.com/paper/2303.13284/) (2023)

## Built on by (most cited first, 5 of 5)

- [GraphWalker: Agentic Knowledge Graph Question Answering via Synthetic Trajectory Curriculum](https://mlsanity.com/paper/2603.28533/) (2026)
- [S-Path-RAG: Semantic-Aware Shortest-Path Retrieval Augmented Generation for Multi-Hop Knowledge Graph Question Answering](https://mlsanity.com/paper/2603.23512/) (2026)
- [Text-to-SPARQL Generation with Reinforcement Learning: A GRPO-based Approach on DBLP](https://mlsanity.com/paper/2605.20066/) (2026)
- [TRIAGE: Trustworthy Retrieval Instrumentation And Graph Evaluation](https://mlsanity.com/paper/2607.03447/) (2026)
- [GTA-RAG: Graph-Trajectory-Augmented Reinforcement Learning for Multi-Turn Retrieval-Augmented Reasoning](https://mlsanity.com/paper/2608.22479/) (2026)

## Abstract (arXiv)

Knowledge-graph retrieval-augmented generation (KG-RAG) couples large language models (LLMs) with structured, verifiable knowledge graphs (KGs) to reduce hallucination and provide reasoning traces. However, current KG-RAG systems often rely on fixed pipelines of multiple LLM modules (e.g., planning, reasoning, and responding), which inflate inference costs and tie performance to specific graph schemas. To address this, we introduce KG-R1, an agentic framework that optimizes KG-RAG through reinforcement learning (RL). Unlike modular workflows, KG-R1 uses a single agent that interacts with KGs as its environment, learning to retrieve information at each step and incorporating it into its reasoning and generation in a unified process. Across Knowledge-Graph Question Answering (KGQA) benchmarks, KG-R1 demonstrates both efficiency and transferability-using Qwen 2.5-3B, KG-R1 improves answer accuracy with fewer generation tokens than prior multi-module workflow methods that use much larger foundation or fine-tuned models. Furthermore, KG-R1 exhibits strong plug-and-play capability: after training, maintaining accuracy on unseen KGs without retraining. These properties make KG-R1 a promising KG-RAG framework for real-world deployment. Our code is publicly available at github.com/junhongmit/KG-R1/.