Deep Research — Iterative Research Engine

An autonomous, multi-step research engine that performs exhaustive information gathering and synthesis. Unlike a single web_search, this skill implements an iterative loop where the agent plans, searches, extracts, synthesizes, and decides when to stop — producing a cited report with structured evidence, source quality tiers, and explicit gaps/contradictions sections.

Inspired by PewDiePie's Odysseus project, Alibaba/Tongyi's IterResearch approach, and the sn-deep-research evidence-structuring architecture (OpenSenseNova/SenseNova-Skills, MIT). The full 9-role sn pipeline was evaluated and intentionally NOT adopted — only the evidence.json layer and refute-polarity requirement were ported, based on empirical side-by-side testing (July 2026). See references/structured-evidence-format.md.

v1.2.0 changes (July 2026): overview-first report structure (comparison table right after executive summary), language anchoring (BCP 47), structured evidence step (3e), refute polarity requirement, source quality classification, explicit contradictions + gaps sections. Architecture diagram corrected.