Update README.md

README.md

@@ -1,6 +1,6 @@
 # AriGraph: Learning Knowledge Graph World Models with Episodic Memory for LLM Agents
 
-AriGraph serves as the external memory architecture for large language models (LLMs), utilizing a knowledge graph that is constructed from scratch. Memory in the form of a semantic knowledge graph extended with episodic vertices and edges significantly enhances the performance of Retrieval-Augmented Generation (RAG) in text-based games.  In the current implementation, AriGraph constitutes the core component of the Ariadne agent, which is designed to navigate text-based games within the [TextWorld](https://github.com/microsoft/TextWorld) framework. This agent significantly outperforms all established baselines in text-based game scenarios and demonstrates robust scalability in larger environments. Detailed information about the AriGraph and the Ariadne agent can be found in the [paper](https://arxiv.org/abs/2304.11062).
+AriGraph serves as the external memory architecture for large language models (LLMs), utilizing a knowledge graph that is constructed from scratch. Memory in the form of a semantic knowledge graph extended with episodic vertices and edges significantly enhances the performance of Retrieval-Augmented Generation (RAG) in text-based games.  In the current implementation, AriGraph constitutes the core component of the Ariadne agent, which is designed to navigate text-based games within the [TextWorld](https://github.com/microsoft/TextWorld) framework. This agent significantly outperforms all established baselines in text-based game scenarios and demonstrates robust scalability in larger environments. Detailed information about the AriGraph and the Ariadne agent can be found in the [paper](https://arxiv.org/abs/2304.11062). You can try yourself in three games which were used for evaluate our agent by following the [link](http://158.255.5.225/).
 
 ![**Ariadne agent and his results**](img/Architecture.png?raw=True)