MoNaCo: More Natural and Complex Questions for Reasoning Across Dozens of Documents

TL;DR

MoNaCo introduces a large benchmark of 1,315 natural, time-consuming questions requiring extensive reasoning across dozens of documents, exposing current LLM limitations in handling complex, real-world information-seeking tasks.

Contribution

The paper presents MoNaCo, a novel benchmark with real-world, complex questions, and a scalable annotation pipeline to evaluate LLMs on challenging reasoning tasks.

Findings

Frontier LLMs achieve at most 61.2% F1 on MoNaCo.

LLMs struggle with recall and hallucinations on complex questions.

MoNaCo highlights current limitations of LLMs in real-world reasoning.

Abstract

Automated agents, powered by Large language models (LLMs), are emerging as the go-to tool for querying information. However, evaluation benchmarks for LLM agents rarely feature natural questions that are both information-seeking and genuinely time-consuming for humans. To address this gap we introduce MoNaCo, a benchmark of 1,315 natural and time-consuming questions that require dozens, and at times hundreds, of intermediate steps to solve -- far more than any existing QA benchmark. To build MoNaCo, we developed a decomposed annotation pipeline to elicit and manually answer real-world time-consuming questions at scale. Frontier LLMs evaluated on MoNaCo achieve at most 61.2% F1, hampered by low recall and hallucinations. Our results underscore the limitations of LLM-powered agents in handling the complexity and sheer breadth of real-world information-seeking tasks -- with MoNaCo providing an effective resource for tracking such progress. The MoNaCo benchmark, codebase, prompts and models predictions are all publicly available at: https://tomerwolgithub.github.io/monaco