Apodex 1.1：擴展智能體智能以應對複雜工作

Apodex 1.1: Scaling Agentic Intelligence for Complex Work

August 24, 2026

作者: Apodex Team, B. An, B. Li, B. Wang, B. Zhang, B. L. Wang, C. Feng, C. Wei, C. Xue, C. Zhang, D. Ng, D. Ye, E. Min, F. Chen, F. Liu, F. Yang, F. Ye, H. Xu, H. Yang, H. Ye, H. Zhang, H. Zhao, J. Li, J. Lin, J. Xia, K. Jin, K. Wang, K. Yang, L. Bing, L. Lei, L. Su, Le. Wang, Lu. Wang, N. Wang, Q. Ren, Q. Yang, R. Li, S. Bai, S. Du, S. Li, S. Lin, S. Nie, S. Wang, S. Zhang, S. Z. Wang, Ta. Q. Fang, Ti. Q. Fang, W. Fang, W. Li, W. Zhang, X. Chen, X. Li, X. Tang, X. Wang, X. Xu, X. Zhang, X. Q. Wang, X. Y. Wang, Y. Deng, Y. Gao, Y. Hu, Y. Li, Y. Sui, Y. Wang, Y. Xiao, Y. Zhang, Z. Chen, Z. Cheng, Z. Feng, Z. Liang, Z. Zhang

cs.AI

摘要

通用語言模型能夠推理與整合知識，但複雜工作還需要與檔案、資訊來源及可執行程式碼進行持續互動，同時具備狀態維護、故障恢復與可驗證的交付能力。我們將此稱之為「工作能力」：對真實世界目標持續且可驗證的進展。Apodex 1.1 沿兩個互補維度發展此能力。「環境擴展」提升可執行檔案、搜尋與程式碼環境的多樣性與可驗證性；「智能體協調擴展」則訓練智能體分解長時程任務、委派並行工作、整合非同步結果並重新規劃。共享的執行框架與 AgentOS 負責跨工具與智能體維護任務狀態及來源追蹤，而訓練過程則將環境軌跡與協調痕跡轉化為可靠的行為。在複雜專業工作、金融、科學研究、數學、程式設計與搜尋等領域，Apodex 1.1 儘管使用的模型規模遠小於許多前沿系統，仍達到領先的效能區間。350億參數的 Apodex 1.1 Mini 更以本地可部署的型態保留了強大的工作能力。這些成果將智能體智慧奠基於隨時間推進、有用且可驗證的工作之上，並推進我們建構「重型求解器」以處理宏大且長期的任務之目標。

English

General-purpose language models can reason and synthesize knowledge, but complex work also requires sustained interaction with files, information sources, and executable code, together with state maintenance, failure recovery, and verifiable delivery. We call this working capability: sustained, verifiable progress toward a real-world objective. Apodex 1.1 develops this capability along two complementary dimensions. Environment Scaling expands the diversity and verifiability of executable file, search, and code environments, while Agentic Coordination Scaling trains agents to decompose long-horizon tasks, delegate parallel work, integrate asynchronous results, and replan. A shared execution harness and AgentOS maintain task state and provenance across tools and agents, and training turns environment trajectories and coordination traces into reliable behavior. Across complex professional work, finance, scientific research, mathematics, coding, and search, Apodex 1.1 reaches the leading performance band despite using a substantially smaller model than many frontier systems. The 35B-parameter Apodex 1.1 Mini further retains strong working capability in a locally deployable form. These results ground agentic intelligence in useful, verifiable work completed over time and advance our goal of building a Heavy-Duty Solver for ambitious, long-running tasks.