Hunt Instead of Wait: Evaluating Deep Data Research on Large Language Models

The agency expected of Agentic Large Language Models goes beyond answering correctly, requiring autonomy to set goals and decide what to explore. We term this investigatory intelligence, distinguishing it from executional intelligence, which merely completes assigned tasks. Data Science provides a natural testbed, as real-world analysis starts from raw data rather than explicit queries, yet few benchmarks focus on it. To address this, we introduce Deep Data Research (DDR), an open-ended task where LLMs autonomously extract key insights from databases, and DDR-Bench, a large-scale, checklist-based benchmark that enables verifiable evaluation. Results show that while frontier models display emerging agency, long-horizon exploration remains challenging. Our analysis highlights that effective investigatory intelligence depends not only on agent scaffolding or merely scaling, but also on intrinsic strategies of agentic models.

Large language models are increasingly capable of answering questions and using tools, but real-world research also requires deciding what questions are worth asking. We introduce Deep Data Research (DDR), a benchmark that evaluates whether AI systems can autonomously explore datasets, identify meaningful patterns, and sustain coherent investigations without predefined tasks. Our results show that current frontier models still struggle with long-horizon exploratory reasoning, often stopping too early or falling into shallow and repetitive analysis. DDR highlights an important gap between executing instructions and independently conducting open-ended research, providing a new framework for evaluating investigatory intelligence in AI systems.