認知核心專業版：深度研究代理與代理基礎模型訓練框架

摘要

通用人工智能代理正日益被視為下一代人工智慧的基礎框架，其具備複雜推理、網絡互動、編程及自主研究的能力。然而，現有的代理系統要麼是閉源的，要麼嚴重依賴於多種付費API和專有工具，這限制了研究界的可訪問性和可重現性。在本研究中，我們介紹了Cognitive Kernel-Pro，這是一個完全開源且（在最大程度上）免費的多模塊代理框架，旨在普及高級AI代理的開發與評估。在Cognitive Kernel-Pro中，我們系統地探討了為代理基礎模型策劃高質量訓練數據的方法，專注於在四個關鍵領域——網絡、文件、代碼和通用推理——構建查詢、軌跡和可驗證答案。此外，我們探索了代理測試時反思與投票的新策略，以增強代理的魯棒性和性能。我們在GAIA上對Cognitive Kernel-Pro進行了評估，取得了開源和免費代理中的頂尖成果。值得注意的是，我們的8B參數開源模型超越了之前領先的系統，如WebDancer和WebSailor，為可訪問的高能力AI代理樹立了新的性能標準。代碼可在https://github.com/Tencent/CognitiveKernel-Pro獲取。

English

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

認知核心專業版：深度研究代理與代理基礎模型訓練框架

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

摘要

Support