Institution profile

iFLYTEK

Industry researchasia · cn
Official website
Research library97linked papers
Opportunities0open roles
Selected work

Representative Papers

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

Jan 08, 2026arXiv.org

This work addresses the challenge of generating high-quality, comprehensive, and reliable business reports from vast amounts of noisy web data to support high-stakes decision-making. The authors propose a training-free agentic workflow that emulates the cognitive process of professional business analysts. Their approach integrates fine-grained intent parsing, dynamic web retrieval, real-time information distillation, and iterative report generation, augmented by a dynamic memory mechanism to enhance the long-horizon reasoning capabilities of large language models. Evaluated on QRC-Eval—a newly curated benchmark comprising 200 real-world business tasks—the proposed method significantly outperforms state-of-the-art deep research agents from OpenAI and Gemini, achieving expert-level performance in automated business report synthesis.

3 citationsRead paper
Recent publications

Latest Papers

AstronOS: A Unified Execution Model and Runtime for Long-Horizon Agentic Systems

Aug 17, 2026

This study addresses the challenges of cross-session state loss and fragmented execution models in long-horizon agent tasks by proposing a unified execution model based on versioned authoritative states, coupled with a runtime mediator handoff strategy. The approach leverages a Cases/Tasks/Scenario Packs architecture to enable persistent state management and seamless context migration. Experimental results demonstrate that the system achieves a 93% success rate across three-stage tasks, significantly outperforming traditional methods while reducing token costs per successful execution. These findings indicate that the proposed framework effectively resolves state consistency issues in long-horizon agents, thereby enhancing both execution efficiency and operational robustness.

0 citationsRead paper