Agent Mode 让 AI 智能体从聊天走向真实工作，做自动化、开发或研究的团队可以直接上手测试前沿模型的实际表现，还能影响排行榜排名，值得一试。
Arena.ai 推出了 Agent Mode，允许用户使用前沿 AI 智能体完成深度研究、生成报告、创建图像、构建网站、调试代码等复杂任务。该模式通过集成网页搜索、沙箱环境中的 bash、图像生成、文件写入和追问等功能，让智能体更自主地处理真实工作。用户的使用数据将用于在 Agent Arena 排行榜上对模型进行排名。目前支持的模型包括 GPT-5.5、Claude Opus 4.7、Gemini 3.1 Pro 以及顶级开源模型。这一更新为 AI 智能体的能力评估提供了更贴近实际应用的基准。
Have you tried out Agent Mode yet? Use frontier AI agents to do your real work. Your sessions fee...
Have you tried out Agent Mode yet? Use frontier AI agents to do your real work. Your sessions feed the data that ranks them on the Agent Arena leaderboard. See details in thread to learn more about Agent Mode and Agent Arena. 👇 Arena.ai @arena Introducing Agent Mode: Agentic AI is now measured in the Arena. Agent Mode can do deep research, create reports, generate images, build websites, debug code, and more. It completes more complex tasks by using tools like web search, bash in a sandbox environment, image generation, file writing, and asking follow-up questions. Frontier models are waiting for you in Agent Mode to take on real-world tasks. GPT-5.5, Claude Opus 4.7, Gemini 3.1 Pro, and top open models. Test them yourself. Your browser does not support the video tag. 🔗 View on Twitter 🔗 View Quoted Tweet 💬 2 🔄 5 ❤️ 31 👀 2856 📊 5 ⚡