Cognitive Kernel-Pro: A Framework for Deep Research Agents and Agent Foundation Models Training
Tianqing Fang, Zhisong Zhang, Xiaoyang Wang, Rui Wang, Can Qin, Yuxuan Wan, Jun-Yu Ma, Ce Zhang, Jiaqi Chen, Xiyun Li, Yonglin Wang, Jingchen Ni, Tianshi Zheng, Chun Chen, Wenhao Yu, Zhenwen Liang, Hongming Zhang, Haitao Mi, Dong Yu

TL;DR
Cognitive Kernel-Pro is an open-source framework for developing and evaluating advanced AI agents, focusing on high-quality training data, robustness, and achieving state-of-the-art results among free models.
Contribution
It introduces a fully open-source multi-module agent framework and explores novel training and evaluation strategies for agent foundation models.
Findings
Achieved state-of-the-art results among open-source agents
Surpassed previous models like WebDancer and WebSailor
Demonstrated the effectiveness of high-quality data curation and test-time strategies
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 \textbf{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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
