Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2511.18303 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914178166423552 |
|---|---|
| author | Ding, Rui Ferreira, Rodrigo Pires Chen, Yuxin Chen, Junhong |
| author_facet | Ding, Rui Ferreira, Rodrigo Pires Chen, Yuxin Chen, Junhong |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_18303 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Hierarchical Deep Research with Local-Web RAG: Toward Automated System-Level Materials Discovery Ding, Rui Ferreira, Rodrigo Pires Chen, Yuxin Chen, Junhong Machine Learning Mesoscale and Nanoscale Physics Materials Science 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. |
| title | Hierarchical Deep Research with Local-Web RAG: Toward Automated System-Level Materials Discovery |
| topic | Machine Learning Mesoscale and Nanoscale Physics Materials Science |
| url | https://arxiv.org/abs/2511.18303 |