Meta 发布 Muse Spark 1.3，改进智能体与编码任务表现
We’re excited to release Muse Spark 1.3 with improved performance on agentic and coding tasks, and a focus on real-world usability.
Meta 发布 Muse Spark 1.3，在智能体与编码任务上性能提升，并聚焦真实场景可用性。该版本可在单线程中跨多个工作流维持更长周期的任务，会更主动地向用户提问、在卡住时说明并确认后再执行关键操作，对自身能力边界的判断也更准确。Meta 内部对比显示，相比 Muse Spark 1.2，其工具调用减少约 20%、token 消耗减少约 25%。Muse Spark 1.3 今日起在 Muse Code 和 Meta Model API 上线，max reasoning 将在完成安全测试后推出。
推荐理由
AI 评分 58
官方给出 Muse Spark 1.3 在智能体与编码任务上的能力变化，以及工具调用和 token 消耗的对比数据。
主题
正文
当前显示原文，中文全文译文尚未就绪。
We’re excited to release Muse Spark 1.3 with improved performance on agentic and coding tasks, and a focus on real-world usability.
Key capabilities: → Sustains longer-horizon work across multiple workflows in a single thread → More actively collaborates with users: it asks clarifying questions, flags when it's stuck, confirms before consequential actions → Better calibrated on its own limits instead of hallucinating outcomes → ~20% fewer tool calls and ~25% fewer tokens vs. Muse Spark 1.2 in internal comparisons