MEGA Hub
New

Cognitive Kernel-Pro: A Framework for Deep Research Agents and Agent Foundation Models Training

Published on Aug 1 Submitted by MEGAon Aug 4#1 Paper of the day

Authors

Do you know Tianqing Fang?You can claim authorship or link another user.Do you know Zhisong Zhang?You can claim authorship or link another user.Do you know Xiaoyang Wang?You can claim authorship or link another user.Do you know Rui Wang?You can claim authorship or link another user.Do you know Can Qin?You can claim authorship or link another user.Do you know Yuxuan Wan?You can claim authorship or link another user.Do you know Jun-Yu Ma?You can claim authorship or link another user.Do you know Ce Zhang?You can claim authorship or link another user.Do you know Jiaqi Chen?You can claim authorship or link another user.Do you know Xiyun Li?You can claim authorship or link another user.Do you know Hongming Zhang?You can claim authorship or link another user.Do you know Haitao Mi?You can claim authorship or link another user.Do you know Dong Yu?You can claim authorship or link another user.

Abstract

General AI Agents are increasingly recognized as foundational frameworks for the next generation of artificial intelligence, enabling complex reasoning, web interaction, coding, and autonomous research capabilities. However, current agent systems are either closed-source or heavily reliant on a variety of paid APIs and proprietary tools, limiting accessibility and reproducibility for the research community. In this work, we present Cognitive Kernel-Pro, a fully open-source and (to the maximum extent) free multi-module agent framework designed to democratize the development and evaluation of advanced AI agents. Within Cognitive Kernel-Pro, we systematically investigate the curation of high-quality training data for Agent Foundation Models, focusing on the construction of queries, trajectories, and verifiable answers across four key domains: web, file, code, and general reasoning. Furthermore, we explore novel strategies for agent test-time reflection and voting to enhance agent robustness and performance. We evaluate Cognitive Kernel-Pro on GAIA, achieving state-of-the-art results among open-source and free agents. Notably, our 8B-parameter open-source model surpasses previous leading systems such as WebDancer and WebSailor, establishing a new performance standard for accessible, high-capability AI agents. Code is available at https://github.com/Tencent/CognitiveKernel-Pro

Community

00