ARE：擴展智能體環境與評估規模

摘要

我們推出了元代理研究環境（Meta Agents Research Environments, ARE），這是一個用於可擴展環境創建、合成或真實應用集成以及代理編排執行的研究平台。ARE提供了簡單的抽象層，用於構建複雜且多樣的環境，每個環境都有其獨特的規則、工具、內容和驗證器，有助於彌合模型開發與實際部署之間的差距。我們還提出了Gaia2，這是一個基於ARE構建的基準測試，旨在衡量代理的通用能力。除了搜索和執行，Gaia2要求代理處理模糊性和噪聲，適應動態環境，與其他代理協作，並在時間約束下運作。與之前的基準測試不同，Gaia2以異步方式運行，揭示了在靜態設置中不可見的新故障模式。我們的實驗表明，沒有任何系統能在整個智能譜系中佔據主導地位：更強的推理能力往往以效率為代價，且預算擴展曲線趨於平穩，這凸顯了對新架構和自適應計算策略的需求。或許更重要的是，ARE的抽象層使得Gaia2能夠持續擴展到其他環境，使社區能夠快速創建針對其領域量身定制的新基準測試。在人工智能的下半場，進步越來越依賴於定義有意義的任務和穩健的評估，以推動前沿能力的發展。

English

We introduce Meta Agents Research Environments (ARE), a research platform for scalable creation of environments, integration of synthetic or real applications, and execution of agentic orchestrations. ARE provides simple abstractions to build complex and diverse environments, each with their own rules, tools, content, and verifiers, helping to bridge the gap between model development and real-world deployment. We also propose Gaia2, a benchmark built in ARE and designed to measure general agent capabilities. Beyond search and execution, Gaia2 requires agents to handle ambiguities and noise, adapt to dynamic environments, collaborate with other agents, and operate under temporal constraints. Unlike prior benchmarks, Gaia2 runs asynchronously, surfacing new failure modes that are invisible in static settings. Our experiments show that no system dominates across the intelligence spectrum: stronger reasoning often comes at the cost of efficiency, and budget scaling curves plateau, highlighting the need for new architectures and adaptive compute strategies. Perhaps more importantly, ARE abstractions enable continuous extension of Gaia2 to other environments, empowering the community to rapidly create new benchmarks tailored to their domains. In AI's second half, progress increasingly depends on defining meaningful tasks and robust evaluations to drive frontier capabilities forward.

ARE：擴展智能體環境與評估規模

ARE: Scaling Up Agent Environments and Evaluations

摘要

Support