PolitNuggets: Benchmarking Agentic Discovery of Long-Tail Political Facts

TL;DR

PolitNuggets is a multilingual benchmark designed to evaluate agentic models' ability to discover and synthesize long-tail political facts from dispersed sources, emphasizing fine-grained accuracy and efficiency.

Contribution

The paper introduces PolitNuggets, a new benchmark with an evaluation protocol and diagnostics for assessing agentic models' political fact discovery and synthesis capabilities.

Findings

Current systems struggle with fine-grained details.

Model efficiency varies substantially across settings.

Multilingual robustness and tool use are crucial for performance.

Abstract

Large Reasoning Models (LRMs) embedded in agentic frameworks have transformed information retrieval from static, long context question answering into open-ended exploration. Yet real world use requires models to discover and synthesize "long-tail" facts from dispersed sources, a capability that remains under-evaluated. We introduce PolitNuggets, a multilingual benchmark for agentic information synthesis via constructing political biographies for 400 global elites, covering over 10000 political facts. We standardize evaluation with an optimized multi agent system and propose FactNet, an evidence conditional protocol that scores discovery, fine-grained accuracy, and efficiency. Across models and settings, we find that current systems often struggle with fine-grained details, and vary substantially in efficiency. Finally, using benchmark diagnostics, we relate agent performance to underlying model capabilities, highlighting the importance of short-context extraction, multilingual robustness, and reliable tool use.