Meta的Muse Spark 1.3上线Arena，能更好协作并减少幻觉，比前代更实用。
Muse Spark 1.3由Meta开发，现已加入Agent Arena评测平台。该模型在数百万真实世界长周期智能体任务中进行测试，可使用网络搜索、文件系统和终端工具完成复杂工作流。与Muse Spark 1.2相比，新版本工具调用减少约20%，token使用减少约25%。
Muse Spark 1.3 by @AIatMeta is now in the Arena! Bring your toughest prompts and start voting. Scor...
Muse Spark 1.3 by @AIatMeta is now in the Arena! Bring your toughest prompts and start voting. Scores coming soon. In Agent Arena, we measure models on millions of real-world, long-horizon agentic tasks. Models can access web search, filesystem, and terminal tools to complete complex workflows. The leaderboard measures model performance on outcomes relative to the average model using a causal tracing methodology. Muse Spark 1.3 is also available in Code Arena: WebDev, Text, Vision, and Document. AI at Meta @AIatMeta 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 🔗 View Quoted Tweet 💬 3 🔄 3 ❤️ 82 👀 7827 📊 9 ⚡