Hierarchical Deep Research with Local-Web RAG: Toward Automated System-Level Materials Discovery

TL;DR

This paper introduces a hierarchical deep research agent that combines local retrieval, large language models, and adaptive research branching to enhance materials discovery beyond existing ML tools, with validated results showing high-quality outputs at lower costs.

Contribution

The paper presents a novel hierarchical deep research framework integrating local web data, LLM reasoning, and adaptive research expansion for system-level materials discovery.

Findings

Comparable or superior report quality to commercial systems

Lower cost and on-premise deployment capability

Validated effectiveness through domain simulations and expert review

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.