AGORA: An Archive-Grounded Benchmark for Agentic Workplace Document Reasoning
AGORA is a new test for AI agents to see if they can reason over large, messy collections of workplace documents. It pairs 362 questions with eight different professional domains, forcing agents to actively explore and reconcile conflicting information across many files. Results show even the best models only achieve 59.4% accuracy, proving true reasoning requires deliberate exploration.