{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,10]],"date-time":"2025-11-10T21:22:37Z","timestamp":1762809757734,"version":"3.44.0"},"publisher-location":"California","reference-count":0,"publisher":"International Joint Conferences on Artificial Intelligence Organization","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,9]]},"abstract":"<jats:p>Advancements in the capabilities of Large Language Models (LLMs) have created a promising foundation for developing autonomous agents. With the right tools, these agents could learn to solve tasks in new environments by accumulating and updating their knowledge. Current LLM-based agents process past experiences using a full history of observations, summarization, retrieval augmentation. However, these unstructured memory representations do not facilitate the reasoning and planning essential for complex decision-making. In our study, we introduce AriGraph, a novel method wherein the agent constructs and updates a memory graph that integrates semantic and episodic memories while exploring the environment. We demonstrate that our Ariadne LLM agent, consisting of the proposed memory architecture augmented with planning and decision-making, effectively handles complex tasks within interactive text game environments difficult even for human players. Results show that our approach markedly outperforms other established memory methods and strong RL baselines in a range of problems of varying complexity. Additionally, AriGraph demonstrates competitive performance compared to dedicated knowledge graph-based methods in static multi-hop question-answering.<\/jats:p>","DOI":"10.24963\/ijcai.2025\/2","type":"proceedings-article","created":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T08:10:40Z","timestamp":1758269440000},"page":"12-20","source":"Crossref","is-referenced-by-count":1,"title":["AriGraph: Learning Knowledge Graph World Models with Episodic Memory for LLM Agents"],"prefix":"10.24963","author":[{"given":"Petr","family":"Anokhin","sequence":"first","affiliation":[{"name":"AIRI, Moscow, Russia"}]},{"given":"Nikita","family":"Semenov","sequence":"additional","affiliation":[{"name":"Skoltech, Moscow, Russia"}]},{"given":"Artyom","family":"Sorokin","sequence":"additional","affiliation":[{"name":"AIRI, Moscow, Russia"}]},{"given":"Dmitry","family":"Evseev","sequence":"additional","affiliation":[{"name":"Skoltech, Moscow, Russia"}]},{"given":"Andrey","family":"Kravchenko","sequence":"additional","affiliation":[{"name":"University of Oxford, UK"}]},{"given":"Mikhail","family":"Burtsev","sequence":"additional","affiliation":[{"name":"London Institute for Mathematical Sciences, London, UK"}]},{"given":"Evgeny","family":"Burnaev","sequence":"additional","affiliation":[{"name":"Skoltech, Moscow, Russia"},{"name":"AIRI, Moscow, Russia"}]}],"member":"10584","event":{"number":"34","sponsor":["International Joint Conferences on Artificial Intelligence Organization (IJCAI)"],"acronym":"IJCAI-2025","name":"Thirty-Fourth International Joint Conference on Artificial Intelligence {IJCAI-25}","start":{"date-parts":[[2025,8,16]]},"theme":"Artificial Intelligence","location":"Montreal, Canada","end":{"date-parts":[[2025,8,22]]}},"container-title":["Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence"],"original-title":[],"deposited":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T11:32:32Z","timestamp":1758627152000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2025\/2"}},"subtitle":[],"proceedings-subject":"Artificial Intelligence Research Articles","short-title":[],"issued":{"date-parts":[[2025,9]]},"references-count":0,"URL":"https:\/\/doi.org\/10.24963\/ijcai.2025\/2","relation":{},"subject":[],"published":{"date-parts":[[2025,9]]}}}