# DRBench: A Realistic Benchmark for Enterprise Deep Research

arXiv: https://arxiv.org/abs/2510.00172 · HTML: https://mlsanity.com/paper/2510.00172/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Sep 2025.

## Built on by (most cited first, 22 of 22)

- [Enterprise Deep Research: Steerable Multi-Agent Deep Research for Enterprise Analytics](https://mlsanity.com/paper/2510.17797/) (2025)
- [Calibrate-Then-Act: Cost-Aware Exploration in LLM Agents](https://mlsanity.com/paper/2602.16699/) (2026)
- [DRACO: a Cross-Domain Benchmark for Deep Research Accuracy, Completeness, and Objectivity](https://mlsanity.com/paper/2602.11685/) (2026)
- [How Far Are We from Genuinely Useful Deep Research Agents?](https://mlsanity.com/paper/2512.01948/) (2025)
- [AutoResearch AI: Towards AI-Powered Research Automation for Scientific Discovery](https://mlsanity.com/paper/2605.23204/) (2026)
- [MiroEval: Benchmarking Multimodal Deep Research Agents in Process and Outcome](https://mlsanity.com/paper/2603.28407/) (2026)
- [Where Do Deep-Research Agents Go Wrong? Span-Level Error Localization in Agent Trajectories](https://mlsanity.com/paper/2606.02060/) (2026)
- [Why Your Deep Research Agent Fails? On Hallucination Evaluation in Full Research Trajectory](https://mlsanity.com/paper/2601.22984/) (2026)
- [IntentRL: Training Proactive User-intent Agents for Open-ended Deep Research via Reinforcement Learning](https://mlsanity.com/paper/2602.03468/) (2026)
- [Dr-CiK: A Benchmark testing Deep Research for Context-Aided Forecasting](https://mlsanity.com/paper/2605.27904/) (2026)
- [NGDBench: Towards Neural Graph Data Management](https://mlsanity.com/paper/2603.05529/) (2026)
- [MosaicLeaks:Privacy Risks in Querying-in-the-Open for Deep Research Agents](https://mlsanity.com/paper/2605.30727/) (2026)
- [Multi-Turn Evaluation of Deep Research Agents Under Process-Level Feedback](https://mlsanity.com/paper/2606.09748/) (2026)
- [DailyReport: An Open-ended Benchmark for Evaluating Search Agents on Daily Search Tasks](https://mlsanity.com/paper/2606.12871/) (2026)
- [MCompassRAG: Topic Metadata as a Semantic Compass for Paragraph-Level Retrieval](https://mlsanity.com/paper/2606.18508/) (2026)
- [Dual-Confidence Contrastive Decoding for Retrieval-Augmented Generation](https://mlsanity.com/paper/2607.00570/) (2026)
- [READY or Not: Reliable Enterprise Agent Deployment](https://mlsanity.com/paper/2609.02095/) (2026)
- [DI-Bench: Systematically Generating In-Domain Data Intelligence Benchmarks for Enterprise Agents](https://mlsanity.com/paper/2609.05776/) (2026)
- [WinSyn: An Automated Pipeline for Realistic Enterprise Question-Answering Evaluation](https://mlsanity.com/paper/2609.12171/) (2026)
- ["Nothing to See Here'': Unintended Disclosure through Revision Traces of LLM Deliverables](https://mlsanity.com/paper/2609.35408/) (2026)
- [DeepRewind: Predicting and Repairing Premature Commitments in Deep Research Agents](https://mlsanity.com/paper/2609.36344/) (2026)
- [RIVO: Lightweight Adaptive Rerouting for Deep Research Agents](https://mlsanity.com/paper/2610.15910/) (2026)

## Abstract (arXiv)

We introduce DRBench, a benchmark for evaluating AI agents on complex, open-ended deep research tasks in enterprise settings. Unlike prior benchmarks that focus on simple questions or web-only queries, DRBench evaluates agents on multi-step queries (for example, "What changes should we make to our product roadmap to ensure compliance with this standard?") that require identifying supporting facts from both the public web and private company knowledge base. Each task is grounded in realistic user personas and enterprise context, spanning a heterogeneous search space that includes productivity software, cloud file systems, emails, chat conversations, and the open web. Tasks are generated through a carefully designed synthesis pipeline with human-in-the-loop verification, and agents are evaluated on their ability to recall relevant insights, maintain factual accuracy, and produce coherent, well-structured reports. We release 100 deep research tasks across 10 domains, such as Sales, Cybersecurity, and Compliance. We demonstrate the effectiveness of DRBench by evaluating diverse DR agents across open- and closed-source models (such as GPT, Llama, and Qwen) and DR strategies, highlighting their strengths, weaknesses, and the critical path for advancing enterprise deep research. Code and data are available at https://github.com/ServiceNow/drbench.