Super Research: Answering Highly Complex Questions with Large Language Models through Super Deep and Super Wide Research

TL;DR

Super Research introduces a comprehensive framework and benchmark for evaluating large language models on highly complex research questions requiring extensive evidence gathering, planning, and synthesis, serving as a robustness test for research capabilities.

Contribution

The paper presents a novel task, benchmark, and evaluation protocol for assessing LLMs on complex research tasks involving structured decomposition, wide retrieval, and deep investigation.

Findings

Super Research benchmark includes 300 expert-written questions across domains.

Models require over 100 retrieval steps and 1,000 web pages to answer complex questions.

Proficiency in Super Research correlates with overall research competence of LLMs.

Abstract

While Large Language Models (LLMs) have demonstrated proficiency in Deep Research or Wide Search, their capacity to solve highly complex questions-those requiring long-horizon planning, massive evidence gathering, and synthesis across heterogeneous sources-remains largely unexplored. We introduce Super Research, a task for complex autonomous research tasks that integrates (i) structured decomposition into a research plan, (ii) super wide retrieval for diverse perspectives, and (iii) super deep investigation to resolve uncertainties through iterative queries. To evaluate this capability, we curated a benchmark of 300 expert-written questions across diverse domains, each requiring up to 100+ retrieval steps and 1,000+ web pages to reconcile conflicting evidence. Super Research produces verifiable reports with fine-grained citations and intermediate artifacts (e.g., outlines and tables) to ensure traceable reasoning. Furthermore, we present a graph-anchored auditing protocol that evaluates Super Research along five dimensions: Coverage, Logical Consistency, Report Utility, Objectivity and Citation Health. While super-complex questions may be infrequent in standard applications, Super Research serves as a critical ceiling evaluation and stress test for LLM capabilities. A model's proficiency within Super Research acts as a powerful proxy for its general research competence; success here suggests the robustness necessary to navigate nearly any subordinate research task. Leaderboard is available at: https://cnsdqd-dyb.github.io/Super-Research-Benchmark/