AGORA: An Archive-Grounded Benchmark for Agentic Workplace Document Reasoning
For researchers developing LLM-based agents for real-world document reasoning, AGORA provides a challenging benchmark that jointly tests archive-groundedness, agentic exploration, and cross-domain coverage.
The paper introduces AGORA, a benchmark for evaluating LLM agents on archive-grounded reasoning across large, messy document collections. The strongest model achieves only 59.4% accuracy, showing the task is far from solved.
Large language models are increasingly deployed as agents that reason over documents rather than answer from parametric knowledge. We study archive-grounded reasoning: locating sparse evidence across a large, messy collection of workplace files, reconciling inconsistent terminology, units, and time conventions, and computing an answer. Existing benchmarks address only parts of this setting and none jointly stresses archive-groundedness, agentic exploration, and cross-domain coverage. We introduce Agora, a benchmark pairing 362 questions with eight domain collections of 9,664 authentic documents and 372M tokens, far exceeding any model's context window, so agents must explore deliberately rather than scan exhaustively. Agora is built by an agentic pipeline combining cross-document task synthesis, leakage-preventing obfuscation, and difficulty filtering. Evaluating eight models, we find the task far from solved: even the strongest reaches only 59.4% accuracy, with notable variation across domains.