{"ID":2837918,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.18303","arxiv_id":"2511.18303","title":"Hierarchical Deep Research with Local-Web RAG: Toward Automated System-Level Materials Discovery","abstract":"We present a long-horizon, hierarchical deep research (DR) agent designed for complex materials and device discovery problems that exceed the scope of existing Machine Learning (ML) surrogates and closed-source commercial agents. Our framework instantiates a locally deployable DR instance that integrates local retrieval-augmented generation with large language model reasoners, enhanced by a Deep Tree of Research (DToR) mechanism that adaptively expands and prunes research branches to maximize coverage, depth, and coherence. We systematically evaluate across 27 nanomaterials/device topics using a large language model (LLM)-as-judge rubric with five web-enabled state-of-the-art models as jurors. In addition, we conduct dry-lab validations on five representative tasks, where human experts use domain simulations (e.g., density functional theory, DFT) to verify whether DR-agent proposals are actionable. Results show that our DR agent produces reports with quality comparable to--and often exceeding--those of commercial systems (ChatGPT-5-thinking/o3/o4-mini-high Deep Research) at a substantially lower cost, while enabling on-prem integration with local data and tools.","short_abstract":"We present a long-horizon, hierarchical deep research (DR) agent designed for complex materials and device discovery problems that exceed the scope of existing Machine Learning (ML) surrogates and closed-source commercial agents. Our framework instantiates a locally deployable DR instance that integrates local retrieva...","url_abs":"https://arxiv.org/abs/2511.18303","url_pdf":"https://arxiv.org/pdf/2511.18303v2","authors":"[\"Rui Ding\",\"Rodrigo Pires Ferreira\",\"Yuxin Chen\",\"Junhong Chen\"]","published":"2025-11-23T05:57:42Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cond-mat.mes-hall\",\"cond-mat.mtrl-sci\"]","methods":"[\"RAG\",\"Large Language Model\",\"Language Model\"]","has_code":false}