Qwen4-Max 推出 Live Delivery,长任务智能体可中途查看并调整结果
阿里给 Qwen4-Max 加了个 Live Delivery:跑长任务的智能体不用等跑完才看结果,中途就能审查、插话改方向。对比 OpenAI 和 Anthropic 的智能体产品,这个中途干预设计对开发者更友好,长流程场景可以直接试试。
阿里巴巴在 Qwen4-Max 中引入 Live Delivery 功能,改变智能体只在任务结束后输出结果的方式。
面对长时间运行的复杂任务,该模型会自主规划、调用工具并根据反馈迭代执行。Live Delivery 允许用户在任务推进过程中提前查看阶段性成果,并随时给出修改意见引导后续改进,不必等到全部完成再返工。
API 已上线 Alibaba Cloud Model Studio 和 QwenCloud 两个平台,同时提供 Token Plan 计费方案供开发者选择。这一能力对标 OpenAI、Anthropic 等厂商在智能体中途可交互性上的探索,对需要在长流程中保持人机协作的开发者和企业用户更实用。
Why wait until the end of a complex task to see results?
With Qwen4-Max, long-running agents plan, use tools, and iterate on feedback. Live Delivery lets you review early results and guide improvements as work progresses.
Discover more: · API on Alibaba Cloud Model Studio: https://t.co/VQ7tgofHRX · API on QwenCloud: https://t.co/9hbWOi1NXR · Token Plan on Alibaba Cloud Model Studio: https://t.co/hGfP8A0O87 · Token Plan on QwenCloud: https://t.co/Y2dgl9nqxD #Qwen4 #AlibabaCloud #Qwen #AI
This report is categorized under AITOP's "Products" desk, focusing on China's AI industry and domestic foundation model ecosystem. Within our cross-regional analytical framework, it directly maps to US-China foundation model benchmarks and commercialization comparison and AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include Qwen4-Max, Alibaba Cloud, agents, coding assistants.
Source attribution: curated from 阿里云 Alibaba Cloud (@alibaba_cloud). Cross-source corroboration: 11 independent sources have covered this development (including lmarena.ai, 阿里通义 Qwen, SuperTechFans), confirming industry-wide signal strength.