DeepResearch Arena: The First Exam of LLMs' Research Abilities via Seminar-Grounded Tasks
This addresses the problem of faithfully evaluating research capabilities in AI for researchers, though it is incremental as it builds on existing benchmarking efforts.
The authors tackled the challenge of evaluating deep research agents by introducing DeepResearch Arena, a benchmark grounded in academic seminars, which includes over 10,000 high-quality research tasks across 12 disciplines and shows substantial performance gaps for state-of-the-art agents.
Deep research agents have attracted growing attention for their potential to orchestrate multi-stage research workflows, spanning literature synthesis, methodological design, and empirical verification. Despite these strides, evaluating their research capability faithfully is rather challenging due to the difficulty of collecting frontier research questions that genuinely capture researchers' attention and intellectual curiosity. To address this gap, we introduce DeepResearch Arena, a benchmark grounded in academic seminars that capture rich expert discourse and interaction, better reflecting real-world research environments and reducing the risk of data leakage. To automatically construct DeepResearch Arena, we propose a Multi-Agent Hierarchical Task Generation (MAHTG) system that extracts research-worthy inspirations from seminar transcripts. The MAHTG system further translates research-worthy inspirations into high-quality research tasks, ensuring the traceability of research task formulation while filtering noise. With the MAHTG system, we curate DeepResearch Arena with over 10,000 high-quality research tasks from over 200 academic seminars, spanning 12 disciplines, such as literature, history, and science. Our extensive evaluation shows that DeepResearch Arena presents substantial challenges for current state-of-the-art agents, with clear performance gaps observed across different models.