Deep Research

Goal

To perform an in-depth, iterative, and comprehensive literature and web research campaign to answer complex scientific questions (e.g., "What are the synthesis methods and solid-state electrolyte performance of LiInCl3?"). This skill produces a high-quality, synthesized research report with citations, significantly exceeding the depth of a single simple literature query.

Instructions

When the user requests deep research on a topic, the agent MUST follow this multi-step iterative protocol. Do not implement this as a python script, but rather execute these steps logically using your own tool-calling capabilities.

Step 1: Query Formulation & Planning

Break down the user's broad research topic into 3-5 specific sub-queries. CRITICAL: You must try different permutations and synonyms for the material or topic. For example, if the topic is LiInCl3, your queries must include variations like LiInCl3, Li-In-Cl, Lithium Indium Chloride, Li3InCl6, etc., to ensure no literature is missed.

Create a rough outline for the final research report in your task plan.

Step 2: Iterative Literature Search

For each sub-query, use the mcp_base_search_literature tool to search the OpenAlex database. Always set download=True to attempt downloading the full text of discovered papers.