Synthesizing informative commercial reports from massive and noisy web sources is critical for high-stakes business decisions. Although current deep research agents achieve notable progress, their reports still remain limited in terms of quality, reliability, and coverage. In this work, we propose Mind2Report, a cognitive deep research agent that emulates the commercial analyst to synthesize expert-level reports. Specifically, it first probes fine-grained intent, then searches web sources and records distilled information on the fly, and subsequently iteratively synthesizes the report. We design Mind2Report as a training-free agentic workflow that augments general large language models (LLMs) with dynamic memory to support these long-form cognitive processes. To rigorously evaluate Mind2Report, we further construct QRC-Eval comprising 200 real-world commercial tasks and establish a holistic evaluation strategy to assess report quality, reliability, and coverage. Experiments demonstrate that Mind2Report outperforms leading baselines, including OpenAI and Gemini deep research agents. Although this is a preliminary study, we expect it to serve as a foundation for advancing the future design of commercial deep research agents. Our code and data are available at https://github.com/Melmaphother/Mind2Report.

翻译：从海量且嘈杂的网络资源中合成信息丰富的商业报告对于高风险商业决策至关重要。尽管当前的深度研究智能体取得了显著进展，但其生成报告在质量、可靠性和覆盖范围方面仍然存在局限。在本工作中，我们提出了Mind2Report，一种模拟商业分析师以合成专家级报告的认知深度研究智能体。具体而言，它首先探查细粒度意图，随后搜索网络资源并实时记录提炼出的信息，进而迭代式地合成报告。我们将Mind2Report设计为一个免训练的智能体工作流，通过动态记忆增强通用大语言模型，以支持这些长形式的认知过程。为严谨评估Mind2Report，我们进一步构建了包含200个真实世界商业任务的QRC-Eval数据集，并建立了一套评估报告质量、可靠性与覆盖范围的整体评估策略。实验表明，Mind2Report的表现优于包括OpenAI和Gemini深度研究智能体在内的领先基线方法。尽管这是一项初步研究，我们期望它能作为推动未来商业深度研究智能体设计的基础。我们的代码与数据可在 https://github.com/Melmaphother/Mind2Report 获取。