MoNaCo: More Natural and Complex Questions for Reasoning Across Dozens of Documents
This provides a resource for tracking progress in LLM agents for real-world information-seeking tasks, though it is incremental as it builds on existing QA benchmarks.
The authors tackled the lack of natural and complex evaluation benchmarks for LLM agents by introducing MoNaCo, a dataset of 1,315 time-consuming questions requiring dozens to hundreds of steps, on which frontier LLMs achieve at most 61.2% F1 due to low recall and hallucinations.
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