AI at Meta· X：AI at Meta (@AIatMeta)·· 3 小时前AI 评分30
Meta Muse Wonder 面向智能体长任务
AI 导读
Meta Muse Wonder 面向智能体日常的长时多步任务，靠两项能力支撑：Active Memory 跨对话携带上下文并在相关时呈现，Active Focus 在任务变难时让模型持续朝目标推进，尝试替代方案、突破阻塞并坚持到完成。
正文
Two things make Muse Wonder suited for long-running, multi-step work an agent faces every day:
-> Active Memory carries your context across conversations and surfaces it when it's relevant.
-> Active Focus keeps the models working toward your goal when a task gets challenging, trying alternative approaches, working through blockers, and following through to completion.
来源：AI at Meta · x.com