{"ID":2864486,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.24116","arxiv_id":"2509.24116","title":"Dual-Scale World Models for LLM Agents Towards Hard-Exploration Problems","abstract":"LLM-based agents have seen promising advances, yet they are still limited in \"hard-exploration\" tasks requiring learning new knowledge through exploration. We present GLoW, a novel approach leveraging dual-scale world models, maintaining a trajectory frontier of high-value discoveries at the global scale, while learning from local trial-and-error in exploration through a Multi-path Advantage Reflection mechanism which infers advantage-based progress signals to guide exploration. To evaluate our framework for hard-exploration, we tackle the Jericho benchmark suite of text-based games, where GLoW achieves a new state-of-theart performance for LLM-based approaches. Compared to state-of-the-art RLbased methods, our approach achieves comparable performance while requiring 100-800x fewer environment interactions.","short_abstract":"LLM-based agents have seen promising advances, yet they are still limited in \"hard-exploration\" tasks requiring learning new knowledge through exploration. We present GLoW, a novel approach leveraging dual-scale world models, maintaining a trajectory frontier of high-value discoveries at the global scale, while learnin...","url_abs":"https://arxiv.org/abs/2509.24116","url_pdf":"https://arxiv.org/pdf/2509.24116v2","authors":"[\"Minsoo Kim\",\"Seung-won Hwang\"]","published":"2025-09-28T23:19:27Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"Large Language Model\",\"LoRA\"]","has_code":false}