SOURCE-LINKED INTELLIGENCE
LiveSearch: Questions as Executable Verifier Code for a Live Benchmark of Professional-Source Financial Search Agents
In finance, the answer that matters is usually the current one: prices, rates, and disclosures hold only as of a given day, so retrieving up-to-date facts is a core capability of a financial agent. Yet most financial benchmarks overlook timeliness. They fix each answer at annotation time, so the gold goes stale as markets move and, once leaked into training data, rewards recall rather than search and analysis. We introduce LiveSearch, a live benchmark that stores each question as executable verifier code: a typed program of calls to a professional financial data service, followed by a declarat
Read original source ↗ Open in workspace
- recordType
- paper
- region
- Global
Evidence & attribution
- arXiv · AI, language, vision and robotics · 2026-10-27T12:55:52.000Z
First collected: 2026-10-28T16:15:03.731Z. This is not the publication date.