SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2608.14747 · 2026

WANDR: A Benchmark for Wide and Deep Research

Jerry Ma, Denis Yarats, Vitaliy Polshkov, Marcin Pitera, Jeremy Yang, Kirill Priemko, Maksim Gaiduk, Aleksandr Nikolenko, Denis Bykov, Clare Southern

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. If it links a repository, it is listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

) is a benchmark of 500 realistic and challenging agentic data-collection tasks for knowledge work. Each task asks a system to discover a large collection of members satisfying specified criteria (the wide axis) and establish specific facts about each member through orchestrated web searches (the deep axis). We represent a task as a qualification key hierarchy such as company (n) → employee (m) → url (k), meaning "find n qualifying companies, m qualifying employees per company, and k qualifying source pages per employee." This hierarchy defines a target of n × m × k records. Instead of comparing submissions against a static gold answer set, a task-specific judge re-fetches the cited pages and verifies each record's claims against the cited evidence, allowing the benchmark to cover current and changing facts. Record-level verdicts are aggregated into soft and hard precision, recall, and F1 at the task level. Required record counts range from dozens to thousands, shifting the central challenge from finding a single correct answer or writing a polished report to open-ended discovery at high volume without sacrificing per-record factual correctness. Tasks are derived from de-identified product-usage logs and produced by a semi-automated pipeline. Automated checks and empirical audits screen them, with human review where needed; the final set is curated to stress-test recurring failure modes of frontier agentic search systems. The benchmark remains far from saturated: at a high effort setting, the strongest system achieves only 0.363 soft F1 and 0.133 hard F1. The tasks and evaluation harness are available at https://github.com/perplexityai/wandr.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2608.14747")
get_code_for_paper("2608.14747")
have("2608.14747")

Connect an agent — have() is free.