Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2509.26383 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913153547239424 |
|---|---|
| author | Lin, Junhong Liu, Shicheng Song, Jinyeop Wang, Song Shun, Julian Zhu, Yada |
| author_facet | Lin, Junhong Liu, Shicheng Song, Jinyeop Wang, Song Shun, Julian Zhu, Yada |
| contents | 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/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_26383 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Efficient and Transferable Agentic Knowledge Graph RAG via Reinforcement Learning Lin, Junhong Liu, Shicheng Song, Jinyeop Wang, Song Shun, Julian Zhu, Yada Computation and Language Artificial Intelligence 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/. |
| title | Efficient and Transferable Agentic Knowledge Graph RAG via Reinforcement Learning |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2509.26383 |