Mind2Report: A Cognitive Deep Research Agent for Expert-Level Commercial Report Synthesis

TL;DR

Mind2Report introduces a training-free cognitive deep research agent designed for expert-level commercial report synthesis. It combines an intent-driven outline formulation, memory-augmented adaptive search, and coherent-preserved iterative synthesis, supported by QRC-Eval, a 200-task evaluation suite. Experiments show Mind2Report outperforms leading baselines in quality, reliability, and coverage, with ablation studies confirming the necessity of each component and strong alignment with human judgments. The work lays a foundation for next-generation commercial deep research agents and robust long-form report evaluation strategies.

Abstract

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.

Figures (9)

• Figure 1: Mind2Report emulates a commercial analyst to synthesis expert-level reports from massive and noisy web sources via a cognitive deep research workflow.
• Figure 2: The illustration of Mind2Report. Given a imprecise commercial query, Mind2Report operates through three key components: intent-driven outline formulation, memory-augmented adaptive search and coherent-preserved iterative synthesis, which work collaboratively to synthesize an expert-level commercial report.
• Figure 3: Overview of the QRC-Eval, a query suite and a holistic evaluation strategy assessing commercial report via quality, reliability, and coverage.
• Figure 4: Performance comparison demonstrating the superiority of Mind2Report over LLMs with thinking and search across four key dimensions.
• Figure 5: Fine-grained analysis across six commercial domains covering quality, reliability, and coverage. Mind2Report demonstrates strong generalization by maintaining high performance across diverse sectors, validating its effectiveness in synthesizing complex vertical knowledge required for high-stake business decision-making.