Impossible Research的[schema]让LLM像物理学家推理，ARC-AGI-3刷到99% RHAE，太强了
Impossible Research团队发布了名为[schema]的agent harness，能使LLM像物理学家一样推理。在ARC-AGI-3公开测试中，该harness结合Opus 4.8与Fable 5达到99% RHAE，使用GPT-5.6 Sol达到95.35% RHAE。它还能玩游戏、写代码。
From our team at Impossible Research - an agent harness that plays games, writes code, reasons like ...
From our team at Impossible Research - an agent harness that plays games, writes code, reasons like a physicist, and saturates the ARC-AGI-3 benchmark. Haven Feng @HavenFeng Today, we’re introducing [schema]: a harness reaching 99% RHAE with Opus 4.8 + Fable 5 and 95.35% with GPT-5.6 Sol on ARC-AGI-3 Public set. [schema] makes an LLM think like a physicist. 🧵 Your browser does not support the video tag. 🔗 View on Twitter 🔗 View Quoted Tweet 💬 42 🔄 31 ❤️ 305 👀 60850 📊 63 ⚡